Audio and video conference processing method and device

Abstract

The embodiment of the present application provides a method and device for processing an audio and video conference, including: receiving language requirement information for a target conference; generating entry verification information for the target conference based on the language requirement information; sending the entry verification information to a service provider that meets the language requirement information; receiving an access request from the service provider for the target conference, the access request carrying the entry verification information; connecting the service provider to the target conference based on the entry verification information; receiving language service information provided by the service provider for the target conference. In the present application, in a system architecture that connects the conference server and the service provider, participants can propose language requirements, and a service provider that meets the language requirements can provide language services to the participants. Moreover, the service provider and the participants are in the same conference, and the participants do not need to frequently switch between the conference system and the translation system, thereby improving the user experience.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and device for processing an audio and video conference. Background Art

[0002] As an important tool for corporate and group communication, audio and video conferencing meets the needs of communication and collaboration.

[0003] In cross-border communication scenarios based on audio and video conferences, the demand for simultaneous interpretation has become a rigid demand. At present, the conference server can provide conference services to participants through the online conference system. When there are translators for providing simultaneous interpretation, the conference server can provide an independent hypertext 5.0 (H5, html5) page for the translator's client to use, specifically obtaining the translator's audio stream and outputting the audio stream in an independent H5 page. Participants with translation needs can listen to the translated audio by accessing the H5 page.

[0004] However, in the current solution, participants need to open an independent H5 page to listen to the translated content. When participants need to listen to the conference content and the translated content at the same time, they need to switch frequently, which is cumbersome and affects the user experience. Summary of the invention

[0005] The embodiment of the present application provides a method for processing an audio and video conference. When a participant raises a language translation requirement according to demand, the conference participant can be provided with a translation service provided by a service provider that meets the requirement. Moreover, the service provider and the participant are in the same conference, and the participant does not need to frequently switch between the conference system and the translation system, thereby improving the user experience.

[0006] Correspondingly, the embodiments of the present application also provide a processing device, an electronic device and a storage medium for an audio and video conference to ensure the implementation and application of the above method.

[0007] In order to solve the above problems, the present application discloses a method for processing an audio and video conference, the method comprising:

[0008] Receive information on language requirements for targeted conferences;

[0009] Generating conference entry verification information for the target conference according to the language requirement information;

[0010] Sending the membership verification information to a service provider that meets the language requirement information;

[0011] receiving an access request from the service provider to the target conference, wherein the access request carries the conference entry verification information;

[0012] connecting the service provider to the target conference according to the conference entry verification information;

[0013] The language service information provided by the service provider for the target conference is received.

[0014] The present application embodiment discloses a method for processing an audio and video conference, the method comprising:

[0015] receiving auxiliary service demand information for a target conference;

[0016] Generating assistant joining verification information for the target conference according to the auxiliary service demand information;

[0017] Sending the assistant membership verification information to the auxiliary service provider that meets the auxiliary service requirement information;

[0018] receiving an access request from the auxiliary service provider to the target conference, wherein the access request carries the assistant conference entry verification information;

[0019] Connecting the auxiliary service provider to the target conference according to the assistant conference entry verification information;

[0020] Auxiliary service information provided by the auxiliary service provider for the target conference is received.

[0021] The present application embodiment discloses a device for processing an audio and video conference, the device comprising:

[0022] A first receiving module, configured to receive language requirement information for a target conference;

[0023] A first generating module, configured to generate conference entry verification information for the target conference according to the language requirement information;

[0024] A first sending module, used to send the membership verification information to a service provider that meets the language requirement information;

[0025] A second receiving module is used to receive an access request from the service provider to the target conference, wherein the access request carries the conference entry verification information;

[0026] A first joining module, configured to connect the service provider to the target conference according to the joining verification information;

[0027] The third receiving module is configured to receive the language service information provided by the service provider for the target conference.

[0028] The present application embodiment discloses a device for processing an audio and video conference, the device comprising:

[0029] A fifth receiving module, configured to receive auxiliary service demand information for a target conference;

[0030] A second generating module, configured to generate assistant joining verification information for the target conference according to the auxiliary service demand information;

[0031] A third sending module, used to send the assistant joining verification information to an auxiliary service provider that meets the auxiliary service requirement information;

[0032] An access request module, configured to receive an access request from the auxiliary service provider to the target conference, wherein the access request carries the assistant conference entry verification information;

[0033] An access module, configured to connect the auxiliary service provider to the target conference according to the assistant conference entry verification information;

[0034] The auxiliary service providing module is used to receive the auxiliary service information provided by the auxiliary service provider for the target conference.

[0035] An embodiment of the present application further discloses an electronic device, including: a processor; and a memory, on which executable code is stored. When the executable code is executed, the processor executes one or more methods described in the embodiments of the present application.

[0036] The embodiments of the present application also disclose one or more machine-readable media on which executable codes are stored. When the executable codes are executed, the processor executes one or more methods described in the embodiments of the present application.

[0037] Compared with the prior art, the embodiments of the present application have the following advantages:

[0038] In the embodiment of the present application, the conference service end that provides conference services is connected with the service provider that provides language services, so that participants participating in the target conference can submit language requirement information to the conference service end. The conference service end generates entry verification information for adding the service provider that provides language services to the target conference based on the language requirement information, and sends the entry verification information to the service provider that meets the language requirement information, so that the service provider joins the target conference to provide language services through the entry verification information. In the embodiment of the present application, the service provider and the participants are in the same conference, and the participants who listen to the language service do not need to frequently switch between the translation content and the conference content, thereby reducing user operations and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a system architecture diagram of a method for processing an audio and video conference in an embodiment of the present application;

[0040] Figure 2 This is a conference interface diagram of an embodiment of the present application;

[0041] Figure 3 This is another conference interface diagram of an embodiment of the present application;

[0042] Figure 4 It is a system architecture diagram of another method for processing audio and video conferences according to an embodiment of the present application;

[0043] Figure 5 This is another conference interface diagram of an embodiment of the present application;

[0044] Figure 6 It is a system architecture diagram of another method for processing audio and video conferences according to an embodiment of the present application;

[0045] Figure 7 This is a live broadcast interface diagram of an embodiment of the present application;

[0046] Figure 8 It is a flowchart of a method for processing an audio and video conference according to an embodiment of the present application;

[0047] Fig. 9 This is another conference interface diagram of an embodiment of the present application;

[0048] Fig.10 This is a flowchart of another method for processing an audio or video conference according to an embodiment of the present application;

[0049] Fig.11 This is an implementation architecture diagram of a method for processing an audio and video conference in an embodiment of the present application;

[0050] Fig.12 This is a flowchart of another method for processing an audio or video conference according to an embodiment of the present application;

[0051] Fig.13 This is a flowchart of another method for processing an audio or video conference according to an embodiment of the present application;

[0052] Fig.14 This is a structural block diagram of a processing device for an audio and video conference in an embodiment of the present application;

[0053] Fig.15 It is a structural block diagram of another audio and video conference processing device according to an embodiment of the present application;

[0054] Fig.16 It is a schematic diagram of the structure of a device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0055] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0056] Reference Figure 1 , which shows a system architecture diagram of a method for processing an audio and video conference provided in an embodiment of the present application, including: a conference participant, a conference server, and a service provider, the service provider may include a translator server and a translator client, and the conference participant may include a client device or a server device used by the participant, Figure 1 In the description, the participant is referred to as the participating client.

[0057] Among them, the conference server can provide audio / video conferencing services to the participants. The participants can fill in the conference reservation information in the conference processing interface provided by the conference server through the conference client, and initiate a conference reservation instruction to the conference server. The conference server can respond to the conference reservation instruction, establish the target conference requested by the participant, and send the participant entry verification information used for the participant to join the target conference to the participant, thereby realizing the establishment and operation of the target conference.

[0058] It should be noted that, refer to Figure 1 After participant 1, who is the conference host, applies to the conference server to reserve a target conference, the conference server can return a general participant entry verification information so that participant 1 can join the target conference. In addition, participant 1 can also send the participant entry verification information to other participants so that other participants can directly join the target conference based on the participant entry verification information.

[0059] Audio and video conferencing is an important scenario for cross-border corporate / group communication. The need for translation in meetings has become a rigid demand. In the case of language barriers, participants can fill in language requirement information in the interpreter reservation interface provided by the conference server and initiate an interpreter reservation instruction to the conference server. The conference server can respond to the interpreter reservation instruction, generate entry verification information for the interpreter to join the target conference, and send the entry verification information to the service provider that meets the language requirement information. The service provider can then initiate an access request for the target conference to the conference server, and the access request carries the entry verification information. The conference server connects the service provider to the target conference based on the entry verification information, and receives the language service information provided by the service provider for the target conference.

[0060] Specifically, in Figure 1In the architecture, the conference server sends the entry verification information to the service provider that meets the language requirement information. This can be achieved in the following ways: the conference server sends the language requirement information and the entry verification information to the interpreter server for the interpreter server to coordinate the reservation of the interpreter. The participant can be a participant with the identity of the conference host or a participant with the identity of an ordinary participant. Furthermore, when the participant has made an appointment with the interpreter, the conference server can also accept the entry verification information sent by the interpreter client, and after the entry verification information is verified, the interpreter client is added to the target conference to provide language service information.

[0061] The translator server can be a server for providing translation service reservations in the framework of the translator company, or a server for directly providing language translation services. In the case where the translator server is a server for providing translation service reservations in the framework of the translator company, the translator server can receive the language requirement information and the conference entry verification information sent by the conference server. In one case, the translator server can assign a translator client that meets the language requirement information, and send the conference entry verification information directly to the translator client, so that the translator client can join the target conference through the conference entry verification information and provide translation services. In another case, the translator server can send the language requirement information and the conference entry verification information to the first translator client used to coordinate the reservation of the translator, so that the user of the first translator client can inform the translator who meets the language requirement information of the requirement, and send the conference entry verification information to the translator client of the translator who meets the language requirement information.

[0062] It should be noted that, in the case where the translator server is a server for directly providing language translation services in the architecture of the translator company, the translator server can directly join the target conference according to the received conference entry verification information to provide translation services. In addition, the translator server and the conference server can be the same server, such as the conference company and the translator company use the same cloud server together. In addition, the translator server and the conference server can also be different servers.

[0063] For example, refer to Figure 1 , the participant client 1 can apply to the conference server, make an appointment for the target conference, and join the target conference according to the participant entry verification information sent by the conference server. The participant clients 2-participant client n as conference participants can also receive the participant entry verification information sent by the participant client 1, and join the target conference through the participant entry verification information.

[0064] It can be understood that the above-mentioned client can be a mobile terminal, a personal computer, a tablet computer, a smart wearable device, etc., and the embodiments of the present application are not limited thereto.

[0065] Further references Figure 2, which shows a conference interface diagram provided by an embodiment of the present application. After joining the target conference, if participant 2 does not speak the same language, participant 2's conference client 2 can Figure 2 The translation demand control (interpreter reservation button) in the target conference interface shown calls out the interpreter reservation interface 10, and fills in the language demand (such as language b) and other demands in the interpreter reservation interface 10, wherein the meeting time, meeting field, participants, and meeting materials can be automatically filled in by the conference server, and the participant 2 can also modify the automatically filled in content. After filling in, the conference client can generate an entry verification information, and send the language demand information and the entry verification information in the interpreter reservation interface 10 to the interpreter server, and the interpreter server can assign the interpreter client 2 that meets the language demand information (language b) to provide translation services, and send the entry verification information to the interpreter client 2, so that the interpreter client 2 can join the target conference and provide translation through the entry verification information. It should be noted that if the participant 2 has the need to make an appointment for language b and language c at the same time, the conference server can generate the entry verification information corresponding to language b and the entry verification information corresponding to language c, so that the interpreter server assigns two interpreters to participate in the translation. In addition, the translator server can also send the language requirement information and membership verification information to the first translator client used to coordinate the reservation of translators, so that the user of the first translator client can then inform the translator 2 who meets the language requirement information of the requirement, and send the membership verification information to the translator client 2 of the translator 2 who meets the language requirement information.

[0066] In addition, participants can also make an appointment for interpreters in advance before the target meeting starts. Figure 3 , which shows another conference interface diagram provided by an embodiment of the present application. If a participant has made an appointment for a target conference, the participant can call out the interpreter appointment interface 10 through the translation demand control (interpreter appointment button) in the conference processing interface, and fill in the conference identification (ID, Identity document), language demand, other demands, meeting time, meeting field, participants, meeting materials and other information in the interpreter appointment interface 10. After filling in, the conference client can generate corresponding entry verification information, and send the language demand information and entry verification information in the interpreter appointment interface 10 to the interpreter server. The interpreter server can assign an interpreter client that meets the language demand information to provide translation services, and send the entry verification information to the interpreter client, so that the interpreter client can join the target conference and provide translation through the entry verification information.

[0067] In one implementation, the conference translation service provided by the interpreter company may include a simultaneous interpretation service, which refers to a translation method in which the interpreter interprets the conference content to the audience without interrupting the normal conference speech of the participants. In this form, when the interpreter joins the target conference established by the conference server through the conference verification information, the conference server can identify the interpreter identity and language of the interpreter client through the conference verification information, and establish another language channel independent of the conference channel in the target conference, and add the interpreter client to the language channel of the corresponding language, so that the target conference can normally collect and play the conference audio of the participants through the conference channel, and collect and play the interpreter's translation audio through the language channel, wherein the interpreter client can normally listen to the conference audio through the conference channel and perform simultaneous interpretation, and the translated audio after simultaneous interpretation is played only through the language channel, and the participants connected to the language channel (such as the participants who have made an appointment with the interpreter or other participants with translation needs) can listen to the translated audio in real time to achieve conference simultaneous interpretation.

[0068] In another implementation, the conference translation service provided by the translator company may include a machine translation service, which is also called automatic translation, and is the process of converting a natural language (source language) into another natural language (target language) using computer resources. It is a branch of computational linguistics, one of the goals of artificial intelligence, and has important scientific research value. As trade internationalization continues to deepen, no matter what field, etc., machine translation plays an increasingly important role. The present application embodiment can also integrate machine translation into the processing link of audio and video conferences, specifically, the service provider providing translation services can also be a machine translation service end, and the machine translation service end can join the target conference established by the conference service end based on the entry verification information, and collect the audio of the participants, provide machine translation services to automatically and accurately obtain the corresponding language service information, and the machine translation service end can provide the language service information in the target conference in the form of text or audio, etc., for the use of participants.

[0069] As machine translation is more widely and deeply applied in production and life, the requirements for domain machine translation are becoming more and more common. For example, the demand for machine translation in the medical field, the news field, the automotive field, etc. A common example is the translation demand for cross-border medical audio and video conferences, which requires the accuracy of the medical translation system and the professionalism of the text. To build machine translation services in these professional fields, it is necessary to train the machine translation model used by the machine translation service with bilingual data in the fundamental field.

[0070] In one embodiment of the present application, there may be different symbols for the same language. For example, the simplified Chinese "我爱中国" and the traditional Chinese "我愛中國" are different symbol expressions of the same text meaning in the same language. In some cases, literary works in simplified Chinese and those in traditional Chinese adopt the same grammatical expression. For example, novels written by modern writers can be considered the same without generating corpora. In other cases, literary works in simplified Chinese and those in traditional Chinese adopt the same grammatical expression. For example, for a traditional Chinese literary work written by an ancient author and a text translated into modern times, it is difficult to directly determine that they are the same because of the inconsistent grammatical expressions between them. In this case, it may be necessary to generate corpora. For example, for the traditional Chinese ancient poem "蒹葭蒼蒼,白露為霜" and its simplified Chinese modern translation "芦苇密密又苍苍,晶莹露水结成霜", due to the differences in word usage and grammatical expressions, it may be necessary to match them based on characteristic data such as the title, author, and chapter name of the ancient poem, and thus output corpus pairs. Another example is that for the traditional Chinese ancient poem "蒹葭蒼蒼,白露為霜" and its English translation "The young shoots of reeds are grey, The white dew looks like frost", it may be necessary to perform weighted calculations on the mapping relationships between the ancient poem titles, the similarities between the titles, the mapping relationships between the authors, the matching degrees between the authors, the similarities between the abstracts, and / or the similarities between the contents of specific parts to obtain literary work pairs containing different languages, and only then can the bilingual sentence group (sentence pair, corpus pair) of this ancient poem be obtained. Similarly, the bilingual sentence group (sentence pair, corpus pair) of the simplified Chinese poem "芦苇密密又苍苍,晶莹露水结成霜" and its English translation "The young shoots of reeds are grey, The white dew looks like frost" can be obtained.

[0071] It can be seen from the above embodiments that for a variety of symbol systems that may exist in a language, for example, Chinese includes symbol systems such as simplified Chinese, traditional Chinese, and Cantonese Chinese. For literary works completed using these symbol systems, there may be a large gap in the way they are expressed. Therefore, it may be necessary to generate literary work pairs through literary work alignment to obtain corpus pairs. In this case, in the professional field audio and video conference of the embodiment of the present application, in order to achieve a higher level of translation, different symbol systems of the same language can be considered as different languages. By analogy, for various languages ​​and each language's own multiple symbol systems, the corpus generation method in the embodiment of the present disclosure can be used to generate corpus pairs. Therefore, regardless of the size of the gap between various languages ​​or language symbol systems, the corpus generation method according to the embodiment of the present disclosure can be used to generate corpus pairs. In other words, as long as the characteristic data of literary works in different languages ​​or different symbol systems of the same language can be extracted and matched with literary works in different languages, pairs of literary works in different languages ​​can be obtained, and then corpus pairs in different languages ​​can be obtained. The corpus pairs can be used to train the machine translation model used by the machine translation service. During the training process, the machine translation model learns the translation experience of symbol systems in various languages ​​through the extracted corpus. This enables the machine translation service to provide efficiency and accuracy far superior to manual translation when participating in conference translation.

[0072] In other implementations, conference translation services may also include: text translation, sign language translation for the deaf and mute, and translation of multimedia media used in the conference. In the text translation scenario, the translator can translate the content of the conference into text and send the translated text to the participants through an independent transmission channel. In the multimedia translation scenario, the translator can translate the multimedia media used in the conference and send the translated multimedia media to the participants through an independent transmission channel. In the sign language translation scenario, refer to Figure 2 Assuming that interpreter 2 performs sign language interpretation, an interpreter window 20 corresponding to interpreter 2 can be set in the interface of the target conference. Interpreter window 20 can play the sign language image of interpreter 2 collected by the interpreter client corresponding to interpreter 2 to realize sign language translation.

[0073] Specifically, in addition to the conference translation scenario, the embodiments of the present application can also be applied to other scenarios:

[0074] In a conference scenario, since the architecture of the conference scenario is relatively simple, when participants have some relatively novel personalized needs, the conference scenario often cannot meet their personalized needs. In order to solve this problem, refer to Figure 4, the embodiment of the present application can connect the conference server to different personalized service providers, such as the translator server, the draughtsman server, the performance server, etc. The translator server can meet the personalized translation needs of the participants. When the participants have the need to draw, the draughtsman server can assign the corresponding draughtsman to join the meeting and provide drawing services. During the break of the meeting, when the participants hope to have actors perform to relieve fatigue, the performance server can assign the corresponding actors to join the meeting and provide performance services.

[0075] In this architecture, conference participants can make personalized auxiliary service reservations based on their personalized needs. At this time, the conference server can respond to the personalized reservation, match the personalized auxiliary service provider corresponding to the personalized needs, and generate assistant joining verification information and send it to the matched personalized auxiliary service provider, so that the personalized auxiliary service provider can send the assistant joining verification information to the assistant client that meets the personalized needs, so that the assistant client can join the conference and provide personalized auxiliary services through the assistant joining verification information. Figure 4 When a participant has a drawing requirement (requirement y), the conference server can send the drawing member joining verification information to the drawing member server, and the drawing member server can further send the drawing member joining verification information to the corresponding drawing member client to realize the provision of drawing service.

[0076] For example, refer to Figure 5 , which shows another conference interface diagram provided by an embodiment of the present application. When a participant has personalized needs, he can call out the personalized reservation interface 30 through the personalized needs control (personalized reservation button) and fill in the personalized needs in the personalized reservation interface 30. Assuming that the personalized auxiliary service provider assigns an assistant 2 to meet its personalized needs, an assistant window 40 corresponding to the assistant 2 can be set in the interface of the target conference, and the assistant window 40 is provided to the assistant 2 for use so that the personalized auxiliary service can be carried out normally. In the case where the assistant is an actor, the assistant can perform a performance through the assistant window 40; in the case where the assistant is a draftsman, the assistant can draw and display the drawing process in the assistant window 40; in the case where the assistant is a translator, the translator can be displayed in the assistant window 40.

[0077] The embodiment of the present application can also be applied to non-conference scenarios. In one implementation, the embodiment of the present application can also be applied to live broadcast scenarios. Figure 6 , which shows a system architecture diagram of another method for processing audio and video conferences provided in an embodiment of the present application, including: a live broadcast server, a personalized auxiliary service provider (drawing server, performance server, translator server).

[0078] Among them, the live broadcast service end can establish a target video live broadcast according to the request of the live broadcaster's client 1. For viewers who join the target video live broadcast, the live broadcast service end can obtain the video content collected by the client 1 and provide audio / video live broadcast services to the viewer's client. In addition, the live broadcast service end can also connect to different personalized service providers, such as the translator service end, the illustrator service end, the performance service end, etc.

[0079] In this architecture, the viewer's client or the live broadcaster's client can make personalized auxiliary service reservations based on personalized needs. At this time, the live broadcast service end can respond to the personalized reservation, match the personalized auxiliary service provider corresponding to the personalized needs, and generate assistant joining verification information and send it to the matched personalized auxiliary service provider, so that the personalized auxiliary service provider can send the assistant joining verification information to the assistant client that meets the personalized needs, so that the assistant client can join the meeting to provide personalized auxiliary services through the assistant joining verification information.

[0080] Specifically, in a live broadcast scenario, the client initiating the live broadcast and the client of the viewer may not speak the same language and may also need translation. In this case, the client can fill in the language requirement information in the interpreter reservation interface provided by the live broadcast server and initiate an interpreter reservation instruction to the live broadcast server. The live broadcast server can respond to the interpreter reservation instruction, generate membership verification information for the interpreter to join the target video live broadcast, and send the language requirement information and membership verification information to the interpreter server for the interpreter server to coordinate the reservation of the interpreter. Furthermore, when the client has made an appointment with the interpreter, the live broadcast server can also accept the membership verification information sent by the interpreter client, and after the membership verification information is verified, the interpreter client will be added to the target video live broadcast.

[0081] Reference Figure 7 , which shows a live broadcast interface diagram provided by an embodiment of the present application. After joining the target video live broadcast, if the viewer 2 does not speak the language, the client 2 of the viewer 2 can Figure 7 The translation requirement control (interpreter reservation button) in the target video live broadcast interface shown calls out the interpreter reservation interface 10, and fills in the language requirement (such as language b), other requirements, live broadcast time, live broadcast field, etc. in the interpreter reservation interface 10. After filling in, the live broadcast client can generate a membership verification information, and send the language requirement information and membership verification information in the interpreter reservation interface 10 to the interpreter server. The interpreter server can assign the interpreter client 2 that meets the language requirement information (language b) to provide translation services, and send the membership verification information to the interpreter client 2, so that the interpreter client 2 can join the target video live broadcast and provide translation through the membership verification information.

[0082] In an embodiment of the present application, a conference service end that provides conference services is connected to a service provider that provides language services, so that participants participating in a target conference can submit language requirement information to the conference service end. The conference service end generates entry verification information for adding the service provider that provides language services to the target conference based on the language requirement information, and sends the entry verification information to the service provider that meets the language requirement information, so that the service provider joins the target conference to provide language services through the entry verification information. In an embodiment of the present application, the service provider and the participants are in the same conference, and participants who listen to the language service do not need to frequently switch between translation content and conference content, thereby reducing user operations and improving user experience.

[0083] Reference Figure 8 , which shows a flowchart of the steps of a method for processing an audio and video conference provided by an embodiment of the present application, including:

[0084] Step 101: Receive language requirement information for a target conference.

[0085] Audio and video conferencing is an important scenario for cross-border corporate / group communication. The need for translation in meetings has become a rigid demand. In the case of language barriers, the first participant can fill in the language requirement information in the interpreter reservation interface provided by the conference server, and the first participant will send the language requirement information for the target meeting to the conference server.

[0086] Among them, the language demand information reflects the first participant's demand for the required translators and some basic information of the target meeting. For example, the language demand information may include language requirements, other requirements, meeting time, meeting field, participants, meeting materials, etc.

[0087] Step 102: Generate conference entry verification information for the target conference according to the language requirement information.

[0088] After receiving the language requirement information, the conference server can generate conference entry verification information for the target conference. The conference entry verification information can be implemented in various forms:

[0089] In one implementation form, the membership verification information may be the membership code corresponding to the target conference, which is encoded by a preset encoding method, and the preset position of the membership code may be encoded with information used to reflect the translated language in the language demand information. The service provider may copy the membership code and paste it on the conference joining page provided by the conference service end. The service provider may verify whether the pasted membership code is the same as the membership code of the target conference generated previously. If they are the same, the field at the preset position of the membership code is further identified. If a result reflecting the translated language is identified, the service provider is determined to be a translator, and the service provider is added to the target conference to provide translation services. It can be understood that the membership verification information may be understood as a membership password, such as a 9-digit password.

[0090] In another implementation form, the joining verification information may be a joining website address corresponding to the target conference. The preset position of the joining website address may be provided with a special parameter for reflecting the translation language in the language demand information. The service provider may submit a request to join the target conference to the conference server by clicking on the joining website address. The conference server may determine whether the joining website address carried in the request is the same as the joining website address of the target conference generated previously. If they are the same, the parameters at the preset position of the joining website address are further identified. If a result reflecting the translation language is identified, the service provider is determined to be a translator, and the service provider is added to the target conference to provide translation services.

[0091] Of course, the meeting entry verification information may be a combination of a website address and a password. After the translator opens the meeting page through a terminal, he or she enters the password to join the corresponding meeting.

[0092] In another implementation form, the entry verification information can also be in the form of graphic codes, such as a QR code. The translator client can parse the address of the target conference and the translation language reflecting the translator's identity by scanning the graphic code, and send this information to the conference server for verification and joining.

[0093] Step 103: Send the membership verification information to a service provider that meets the language requirement information.

[0094] In an embodiment of the present application, the conference service end may determine whether the service provider is a service provider that meets the language requirement information by determining whether the information on the language service that the service provider can provide matches the language requirement information.

[0095] For example, if the language service that a service provider can provide is Japanese translation service, and the language demand information is also about finding Japanese translation service, then the service provider is a service provider that meets the language demand information.

[0096] Step 104: Receive an access request from the service provider to the target conference, wherein the access request carries the conference entry verification information.

[0097] Step 105: connect the service provider to the target conference according to the conference entry verification information.

[0098] Step 106: Receive language service information provided by the service provider for the target conference.

[0099] In an embodiment of the present application, the conference entry verification information carries a correspondence with the target conference and a language requirement for reflecting the identity of the translator. The conference server can obtain the above information by parsing the conference entry verification information. The conference server can verify whether the conference entry verification information is the same as the previously generated conference entry verification information of the target conference. If they are the same, it is further identified whether the conference entry verification information carries a language requirement reflecting the identity of the translator. If so, it is determined that the service provider is a translator, and the service provider is added to the target conference to provide translation services.

[0100] In an embodiment of the present application, the entry verification information carries a correspondence with the target conference and a language requirement for reflecting the identity of the translator. The conference server can obtain the above information by parsing the entry verification information. The conference server can verify whether the entry verification information is the same as the entry verification information of the target conference generated previously. If they are the same, it is further identified whether the entry verification information carries a language requirement reflecting the identity of the translator. If so, it is determined that the translator client is a translator, and the translator client is added to the target conference to provide translation services.

[0101] Optionally, the method further includes:

[0102] Step A1: Allocate a first transmission channel to the service provider.

[0103] Step A2: Allocate a second transmission channel for audio and video transmission of the target conference.

[0104] The first transmission channel and the second transmission channel are independent of each other.

[0105] In an embodiment of the present application, in order to prevent the language service information from interfering with the normal collection of conference data by participants, the language service information provided by the service provider and the conference data provided by the participants can be transmitted separately, that is, the language service information is transmitted through an independent first transmission channel, and the audio and video conference data is transmitted through an independent second transmission channel.

[0106] Language service information and conference data may include audio data, image data, text data, video data, etc. When the conference data and language service information are audio data, the first transmission channel and the second transmission channel may be audio channels, and the volume of different audio channels may be freely adjusted; when the conference data and language service information are video data, text data, and image data, the first transmission channel and the second transmission channel may be transmission channels corresponding to the data type.

[0107] It should be noted that, in some cases, the language service information and conference data can also use the same transmission channel. For example, when the language service information and conference data are audio, the playback volume of the translated audio can be increased and the playback volume of the conference data can be reduced so that the participants can focus on listening to the translated audio. In addition, a corresponding first transmission channel can be established for each service provider, and multiple service providers of the same language can also share a first transmission channel of the corresponding language.

[0108] Step 106 may specifically include:

[0109] Step A3: receiving language service information provided by the service provider for the target conference through the first transmission channel.

[0110] The service provider can collect conference data by accessing the second transmission channel, generate language service information based on the conference data, and transmit the language service information through the first transmission channel. Participants who do not have translation needs can collect conference data through the second transmission channel, and will not receive language service information and will not be disturbed by the language service information. In one specific implementation, participants who have translation needs can receive language service information through the first transmission channel to provide translation services. In another specific implementation, participants who have translation needs can receive language service information through the first transmission channel, and receive conference data through the second transmission channel, so as to achieve the purpose of simultaneously receiving language service information and conference data for use.

[0111] Optionally, when the language requirement information includes multiple language requirements, a corresponding first transmission channel is allocated to the service provider of each language requirement, and the first transmission channels corresponding to different language requirements are independent of each other.

[0112] In the embodiment of the present application, when establishing the first transmission channel, the first transmission channel can be matched with the language requirement to achieve the purpose of distinguishing the first transmission channel according to the language.

[0113] For example, refer to Figure 2, assuming that the language requirement is the language, there are 3 participants in the target conference who have requested to reserve the interpreter 1 of language a, and 2 participants who have requested to reserve the interpreter 2 of language b, then the conference server can establish a first transmission channel corresponding to language a and a first transmission channel corresponding to language b, and generate the entry verification information of the corresponding language a and the entry verification information of the corresponding language b, and display the corresponding relationship between each language and the interpreter in the decoding of the target conference, so that the 3 participants who have reserved the language a can enter the first transmission channel of the corresponding language a by clicking the avatar of the interpreter 1; the 2 participants who have reserved the language b can enter the first transmission channel of the corresponding language b by clicking the avatar of the interpreter 2.

[0114] In addition, there can be multiple translators corresponding to one language. For example, when multiple translators join the target conference through the entry verification information, and the entry verification information corresponding to each translator corresponds to language a and is the same as each other, all these multiple translators can be added to the first transmission channel corresponding to language b to complete the translation of language b through multi-translator collaboration.

[0115] Optionally, when there are two or more service providers for the same language requirement, step A1 may specifically include:

[0116] Step A11: Allocate the same first transmission channel to the two or more service providers.

[0117] In an embodiment of the present application, when two or more service providers have the same language requirement, a first transmission channel corresponding to the same language requirement can be allocated to the two or more service providers. That is, assuming that three participants all have a language requirement for English, a first transmission channel corresponding to English can be allocated to these three participants.

[0118] Optionally, the method further includes:

[0119] Step A4: receiving a takeover request sent by a main service provider among the two or more service providers.

[0120] Reference Fig. 9 , which shows another target conference interface diagram provided by the embodiment of the present application, Fig. 9 The target conference interface provided by the conference server to the interpreter client is shown, wherein a takeover control (interpreter takeover button) may be provided in the target conference interface.

[0121] In actual applications, there may be a situation where a single translator is unable to provide translation services for a long time due to the long duration of the meeting. In this case, a takeover control can be provided in the display interface of the service provider, and the takeover control can be triggered by an translator of a major service provider, thereby sending a takeover request to the conference server to access the first transmission channel of the corresponding language, thereby realizing the translator's takeover and providing better translation quality.

[0122] Step A5: According to the takeover request, select one of the non-primary service providers as a new primary service provider to provide services for the target conference.

[0123] For example, refer to Fig. 9 , assuming Fig. 9 For the interface corresponding to interpreter 1, in the first transmission channel corresponding to language a, an interpreter x from a non-primary service provider has not taken a rest for a long time. At this time, interpreter 1 can trigger the takeover control (interpreter takeover button) and select the avatar of interpreter x in the pop-up selection box 50, thereby entering the first transmission channel of interpreter x for translation service. The conference server can notify interpreter x that "another interpreter has taken over for you, please take a rest", so that interpreter x can go offline and take a rest. In addition, the conference server will also notify other non-primary service providers other than those who sent the takeover request that the first transmission channel has been occupied, so that when multiple interpreters work alternately in the same channel, one interpreter can be in working state, and other interpreters are temporarily disabled to avoid interfering with translation.

[0124] In summary, in the embodiment of the present application, the conference service end that provides conference services is connected with the service provider that provides language services, so that participants participating in the target conference can submit language requirement information to the conference service end, and the conference service end generates entry verification information for adding the service provider that provides language services to the target conference based on the language requirement information, and sends the entry verification information to the service provider that meets the language requirement information, so that the service provider joins the target conference to provide language services through the entry verification information. In the embodiment of the present application, the service provider and the participants are in the same conference, and the participants who listen to the language service do not need to frequently switch between translation content and conference content, thereby reducing user operations and improving user experience.

[0125] Reference Fig.10 , which shows a flowchart of the steps of a method for processing an audio and video conference provided by an embodiment of the present application, applied to a conference server, including:

[0126] Step 201: receiving language requirement information for a target conference.

[0127] In the embodiments of this application, refer to Figure 1The conference server can provide audio / video conference services to the participants. The participants can fill in the conference reservation information in the conference processing interface provided by the conference server and initiate a conference reservation instruction to the conference server. The conference server can respond to the conference reservation instruction and establish the target conference requested by the participant.

[0128] The language demand information reflects the first participant's demand for the required interpreters and some basic information of the target meeting. For example, the language demand information may include language requirements, other requirements, meeting time, meeting field, participants, meeting materials, etc.

[0129] Step 202: Generate conference entry verification information for the target conference according to the language requirement information.

[0130] In the embodiment of the present application, the translator's translator client needs to join the target conference to provide the translation service required by the participant corresponding to the first participant. Specifically, the translator client can join the target conference through the conference verification information. The conference verification information is used to verify the translator identity of the translator client when joining the target conference.

[0131] Step 203: Send the membership verification information and the language requirement information to the translator server.

[0132] This step is for the translator server to send the membership verification information to the first translator client according to the language requirement information.

[0133] The interpreter server can receive the language requirement information and conference verification information sent by the conference client, and coordinate the reservation of interpreters based on the language requirement information.

[0134] In one case, after receiving the conference entry verification information and language requirement information, the translator server can assign a first translator client that meets the language requirement information and send the conference entry verification information directly to the first translator client, so that the first translator client can join the target conference through the conference entry verification information and provide translation services.

[0135] In another case, the translator server can send the language requirement information and the membership verification information to the first translator client used to coordinate the reservation of translators, so that the user of the first translator client can then inform the translator who meets the language requirement information of the requirement, and send the membership verification information to the second translator client of the translator who meets the language requirement information.

[0136] Further references Fig.11, which shows an implementation architecture diagram of a processing method for an audio and video conference provided by an embodiment of the present application, wherein steps s1-s4 are the process of the participant booking the target conference, specifically, the conference service end can provide a conference booking service and an interpreter booking service, as well as a conference booking interface and an interpreter booking interface, and steps s1-s4 can be implemented based on the conference booking service and the conference booking interface, and in step s5, in inputting the language requirement information, the participant with the translation requirement can fill in the language requirement information through the interpreter booking interface. And through step s6, calling the interpreter booking service, further implementing step s7, calling the conference booking service's entry verification information generation interface, generating the entry verification information corresponding to the target conference, executing step s8, returning the entry verification information to the interpreter booking service. Further executing step s9, notifying the interpreter server of the entry verification information, so that the interpreter server can provide the interpreter's scheduling. After completing step s9, executing step s10, notifying the participant through the interpreter booking interface that "notification to the interpreter server is successful", and step s11, after displaying success, the participant can know that the interpreter's appointment is successful.

[0137] Step 204: receiving the membership verification information sent by at least one second translator client.

[0138] In an embodiment of the present application, the second translator client can be the same client as the first translator client, that is, after receiving the entry verification information and language requirement information, the translator server can assign the first translator client that meets the language requirement information, and send the entry verification information directly to the first translator client, so that the first translator client joins the target conference through the entry verification information.

[0139] In addition, the second interpreter client can be a different client from the first interpreter client, that is, the interpreter server can send the language requirement information and the conference entry verification information to the first interpreter client used to coordinate the reservation of interpreters, so that the user of the first interpreter client can inform the interpreter who meets the language requirement information of the requirement, and send the conference entry verification information to the second interpreter client of the interpreter who meets the language requirement information, so that the second interpreter client can join the target conference through the conference entry verification information.

[0140] Step 205: adding the second translator client to the target conference according to the conference entry verification information.

[0141] Step 206: Receive the language service information sent by the second translator client, and provide the language service information to at least one participant joining the target conference.

[0142] Optionally, in an implementation of the present application, the method further includes:

[0143] Step B1: Allocate a first transmission channel for the interpreter client in the target conference according to the conference entry verification information.

[0144] The first transmission channel is independent of the second transmission channel of the target conference; the second transmission channel is used to transmit conference data.

[0145] Optionally, step B1 may include:

[0146] Sub-step B11: determining the target language requirement according to the membership verification information.

[0147] Sub-step B12: In the target conference, allocating a target first transmission channel corresponding to the target language requirement to the translator client; wherein different language requirements correspond to different first transmission channels.

[0148] Optionally, step B1 may further include:

[0149] Sub-step B13: when the membership verification information sent by at least two second translator clients is the same, assigning the at least two second translator clients to the same first transmission channel.

[0150] For the specific description, please refer to the relevant description of the above steps A1-A3, which will not be repeated here.

[0151] Optionally, step B1 may further include:

[0152] Sub-step B14: providing a replacement control in the display interface provided to the second translator client.

[0153] Sub-step B15: upon receiving a takeover request sent by any second translator client, allocating the right to use the first transmission channel to the second translator client; the takeover request is sent by the second translator client upon receiving a touch operation on the takeover control.

[0154] For the specific description, please refer to the above steps B4-B5, which will not be repeated here.

[0155] Step 206 can be specifically implemented by the method of step B2:

[0156] Step B2: receiving language service information sent by the second interpreter client based on the first transmission channel, and providing the language service information to at least one participant joining the target conference.

[0157] Optionally, the method may further include:

[0158] Step B3: providing a channel usage control for the interpreter client in a display interface provided to the conference participant.

[0159] Step B4: upon receiving a use request from any conference participant, the language service information of the translator client is sent to the conference participant; the use request is sent by the conference participant upon receiving a touch operation on the takeover control.

[0160] For example, refer to Figure 2 , assuming that there are 3 participants in the target conference who have requested to reserve interpreter 1 for language a, and 2 participants who have requested to reserve interpreter 2 for language b, the conference server can establish a first transmission channel corresponding to language a and a first transmission channel corresponding to language b, and display a channel usage control for the first transmission channel corresponding to language a (the avatar of interpreter 1 corresponding to language a), and a channel usage control for the first transmission channel corresponding to language b (the avatar of interpreter 2 corresponding to language b), so that the 3 participants who have reserved language a can enter the first transmission channel corresponding to language a by clicking on the avatar of interpreter 1, and obtain the language service information transmitted by the first transmission channel of language a; the 2 participants who have reserved language b can enter the first transmission channel corresponding to language b by clicking on the avatar of interpreter 2, and obtain the language service information transmitted by the first transmission channel of language b.

[0161] In this way, participants can flexibly switch the channels they need to listen to as needed.

[0162] Optionally, the method may further include:

[0163] Step B5: providing a language requirement information sending control in the display interface provided to the first conference participant; the language requirement information is sent by the first conference participant when the requirement information sending control is touched.

[0164] Reference Figure 2 After joining the target conference, if participant 2 does not speak the same language, participant 2's party 2 can Figure 2 The translation requirement control (interpreter reservation button) in the target conference interface shown calls out the interpreter reservation interface 10, and fills in the language requirement (such as language b), other requirements, meeting time, meeting field, participants, meeting materials, etc. in the interpreter reservation interface 10. After filling in, the conference client can generate a language requirement information based on the filled content, and send the language requirement information after the participant 2 triggers the requirement information sending control (send button).

[0165] Optionally, the method may further include:

[0166] Step B6: receiving at least two pieces of translator identity information sent by the translator server according to the language requirement information, and providing the at least two pieces of translator identity information to the first conference participant.

[0167] Step B7, receiving the target translator identity information sent by the target conference participant; the target translator identity information is determined by the conference participant after receiving the selection operation for the target translator identity information.

[0168] Step B8: sending the target translator's identity information to the translator server.

[0169] In an embodiment of the present application, when the translator server receives the language requirement information provided by the participant and sent by the conference server, it can also select a group of translator clients that all meet the language requirement information as candidate translator clients, and send the translator identity information of these candidate translator clients to the conference server. In one case, before the target meeting starts, the conference server can provide the translator identity information of these candidate translator clients to the participant, and after the participant selects the target translator identity information, the target translator identity information is sent to the translator server, and the translator server can schedule the translator client corresponding to the target translator identity information to participate in the subsequent target meeting. In another case, after the target meeting starts and the participant joins the target meeting, the conference server can provide the translator identity information of these candidate translator clients to the participant through the interface of the target meeting, and after the participant selects the target translator identity information, the target translator identity information is sent to the translator server, and the translator server can schedule the translator client corresponding to the target translator identity information to participate in the target meeting.

[0170] Optionally, the method may further include:

[0171] Step B9, receiving price information corresponding to multiple translator identity information sent by the translator server, and sending the corresponding relationship between the price information and the translator identity information to the first participant for display.

[0172] In an embodiment of the present application, the translator providing translation services may receive remuneration from the conference participants. Specifically, the translator service end may establish corresponding price information for the translator identity information of different translators, and send the correspondence between the price information and the translator identity information to the conference service end, which will be forwarded by the conference service end to the first conference participant for display, so that the first conference participant can understand the service price of the translator to be booked.

[0173] Optionally, the method may further include:

[0174] Step B10: Obtain the duration of the translator client's participation in the target conference.

[0175] Step B11: after the target meeting is over, a translation bill is generated according to the duration, and the translation bill is sent to the participants.

[0176] In an embodiment of the present application, the compensation income obtained by the translator for providing translation services can be determined based on the length of time the translator provides translation services, that is, the conference service end generates a translation bill based on the length of time the translator client participates in the target conference, and sends the translation bill to the participants. The participants can pay directly to the translator service end according to the translation bill, so that the translator service end can send the paid amount to the corresponding translator. The participants can also pay the conference service end according to the translation bill, and the conference service end forwards the paid amount to the translator service end, so that the translator service end can send the received amount to the corresponding translator.

[0177] Specifically, in one case, the interpreter server can establish corresponding price information for the interpreter identity information of different interpreters, and the price information can be charging standards for different durations, such as XX for 1 hour, XX for 1-2 hours, and XX for more than 2 hours. The conference server can find the corresponding charging amount in the above charging standards according to the duration of the interpreter client participating in the target conference.

[0178] In another case, the interpreter server can establish corresponding price information for the interpreter identity information of different interpreters. The price information can be the unit time amount corresponding to each time unit (hour, minute). The conference server can count the number of time units included in the length of time the interpreter client participates in the target conference, and multiply the number of time units by the unit time amount to obtain the final charge amount.

[0179] The billing invoice may include specific details, such as the meeting start time, end time, meeting ID, interpreter information, and interpreter translation time (interpreter translation start time, end time, etc.).

[0180] In addition, the determination of the actual translation duration may include: the participants may specify a preset duration for the translation sound in the interpreter's channel to stop. This preset duration may be specified, such as 10 minutes, to confirm that the translation is over, and the recorded duration is the actual translation duration. In addition, the continuous time of the translation sound may be detected, starting from the appearance of the translation sound in the interpreter's channel, and the duration of the translation sound is recorded until the end of the meeting, and the actual translation duration is accumulated. If the translation sound is interrupted and the interruption time lasts for more than the preset duration, it can be considered that the interruption time is not counted in the actual translation time. If the interval is less than the preset duration, this period of time can be counted in the actual translation time.

[0181] Optionally, the method may further include:

[0182] Step B12: After the target conference is over, receiving translation quality evaluation information sent by the conference participants, and sending the translation quality evaluation information to the translator server.

[0183] In an embodiment of the present application, after the target conference ends, the participants can provide the conference server with translation quality evaluation information of the translator, and the conference server sends the translation quality evaluation information to the translator server so that the translator company can improve the quality of the translation service based on the translation quality evaluation information.

[0184] Optionally, before step 201, the method may further include:

[0185] Step B13: receiving a conference reservation instruction sent by the first conference participant for reserving a target conference.

[0186] Step B14: after the reservation is successful, generate reservation success information including the participant's entry verification information, and send the reservation success information to the first participant; the participant's entry verification information is used for at least one participant to join the target conference.

[0187] Reference Fig.11 , the conference server can provide conference reservation service and interpreter reservation service, as well as conference reservation interface and interpreter reservation interface. Steps s1 to s4 are the process of participants reserving the target conference. Steps s1 to s4 can be implemented based on the conference reservation service and conference reservation interface. Specifically, the participants can fill in the conference reservation information through the conference reservation interface, send the conference reservation instruction for reserving the target conference to the conference server, and execute s1 to reserve the target conference. After that, the conference server executes s2, calls the conference server entry verification information generation interface, calls the conference reservation service to generate the participant entry verification information, and executes s3, returns the reservation success information including the participant entry verification information to the conference reservation interface for display. Execute s4, display the reservation success information and the participant entry verification information through the conference reservation interface.

[0188] Step B15: providing a translation requirement control in the reservation success display interface provided to the first participant; the translation requirement control is used to send language requirement information for the target conference to the conference server.

[0189] Reference Figure 3If the participant has made an appointment for the target conference, the participant can call out the interpreter appointment interface 10 through the translation requirement control (interpreter appointment button) in the appointment success display interface, and fill in the conference ID (ID, Identity document), language requirements, other requirements, meeting time, meeting field, participants, meeting materials and other information in the interpreter appointment interface 10. After filling in, the conference client can generate corresponding entry verification information, and send the language requirement information and entry verification information in the interpreter appointment interface 10 to the interpreter server. The interpreter server can assign the interpreter client that meets the language requirement information to provide translation services, and send the entry verification information to the interpreter client, so that the interpreter client can join the target conference and provide translation through the entry verification information.

[0190] Optionally, the method further includes:

[0191] Step B16: During the target conference, receiving language requirement information for the target conference sent by the first participant.

[0192] Step B17: providing a translation requirement control in the conference interface provided to the first conference participant; the translation requirement control is used to send language requirement information for the target conference to the conference server.

[0193] Specifically, refer to Figure 2 , After joining the target conference, if participant 2 does not speak the same language, participant 2's party 2 can Figure 2 The translation requirement control (interpreter reservation button) in the target conference interface shown calls out the interpreter reservation interface 10, and fills in the language requirement (such as language b) and other requirements in the interpreter reservation interface 10, wherein the meeting time, meeting field, participants, and meeting materials can be automatically filled in by the conference server, and the participant 2 can also modify the automatically filled in content. After filling in, the conference client can generate a meeting verification information, and send the language requirement information and meeting verification information in the interpreter reservation interface 10 to the interpreter server.

[0194] In summary, in the embodiment of the present application, the conference server that provides conference services is connected to the interpreter server that provides interpreter reservation services, so that participants participating in the target conference can submit translation requirements to the conference server. The conference server generates entry verification information for joining the interpreter's interpreter client to the target conference based on the translation requirements, and sends the entry verification information to the interpreter server. The interpreter server can assign an interpreter who meets the translation requirements and send the entry verification information to the interpreter's interpreter client, so that the interpreter client joins the target conference to provide translation services through the entry verification information. In the embodiment of the present application, the interpreter and the participants are in the same conference, and the participants who listen to the translation service do not need to frequently switch between the translation content and the conference content, thereby improving the user experience.

[0195] Reference Fig.12 , showing a step flow chart of another embodiment of an audio and video conference processing method of the present application, which is applied to a translator server.

[0196] Step 301: receiving conference entry verification information and language requirement information sent by a conference server; the conference entry verification information is associated with a target conference.

[0197] Step 302: Determine a first translator client matching the language requirement information from at least one preset translator client.

[0198] Optionally, step 302 may specifically include:

[0199] Sub-step 3021: sending multiple translator identity information to the conference server according to the language requirement information.

[0200] Optionally, sub-step 3021 may include:

[0201] Sub-step 30211: According to the language requirement information, at least two translator clients matching the language requirement information are determined from a plurality of preset translator clients.

[0202] Sub-step 30212: Obtain translator identity information of each of multiple translator clients that match the language requirement information.

[0203] Sub-step 30213: sending the translator's identity information to the conference server.

[0204] In an embodiment of the present application, when the translator server receives the language requirement information provided by the participants and sent by the conference server, it can also select a group of translator clients that meet the language requirement information as candidate translator clients, and send the translator identity information of these candidate translator clients to the conference server. For example, if the language requirement information includes language b, the translator server can select the translator clients of language b from all translator clients as candidate translator clients, and determine the translator identity information of these candidate translator clients.

[0205] In one case, before the target conference starts, the conference server can provide the translator identity information of these candidate translator clients to the participants, and after the participants select the target translator identity information, the target translator identity information is sent to the translator server, and the translator server can schedule the translator client corresponding to the target translator identity information to participate in the subsequent target conference. In another case, after the target conference starts and the participants join the target conference, the conference server can provide the translator identity information of these candidate translator clients to the participants through the interface of the target conference, and after the participants select the target translator identity information, the target translator identity information is sent to the translator server, and the translator server can schedule the first translator client corresponding to the target translator identity information to participate in the target conference.

[0206] Sub-step 3022: receiving the target translator identity information sent by the conference server.

[0207] Sub-step 3023: determining the first translator client according to the target translator identity information.

[0208] Step 303: Send the conference entry verification information to a first translator client matching the language requirement information; the conference entry verification information is used for at least one of the translator clients to join the target conference.

[0209] The translator server can be a server in the translator company's architecture for providing translation service reservations. The translator server can receive language requirement information and conference entry verification information associated with a target conference sent by a conference client. In one case, the translator server can assign a translator client that meets the language requirement information and send the conference entry verification information directly to the translator client, so that the translator client can join the target conference through the conference entry verification information and provide translation services.

[0210] In another case, the translator server can send the language requirement information and the membership verification information to the first translator client used to coordinate the reservation of translators, so that the user of the first translator client can then inform the translator who meets the language requirement information of the requirement, and send the membership verification information to the translator client of the translator who meets the language requirement information.

[0211] Reference Figure 2 , which shows a conference interface diagram provided by an embodiment of the present application. After joining the target conference, if participant 2 does not speak the same language, participant 2 can Figure 2 The translation requirement control (interpreter reservation button) in the target conference interface shown calls out the interpreter reservation interface 10, and fills in the language requirement (such as language b), other requirements, meeting time, meeting field, participants, etc. in the interpreter reservation interface 10. The conference client can generate an entry verification information and send the language requirement information and entry verification information in the interpreter reservation interface 10 to the interpreter server.

[0212] Specifically, the translator server can assign the translator client 2 that meets the language requirement information (language b) from all translator clients to provide translation services, and send the conference verification information to the translator client 2, so that the translator client 2 can join the target conference and provide translation through the conference verification information. It should be noted that if participant 2 has the need to make reservations for language b and language c at the same time, the conference server can generate the corresponding language b and language c entry verification information, so that the translator server can assign two translators to participate in the translation.

[0213] In addition, the translator server can also send the language requirement information and membership verification information to the first translator client used to coordinate the reservation of translators, so that the user of the first translator client can then inform the translator 2 who meets the language requirement information of the requirement, and send the membership verification information to the translator client 2 of the translator 2 who meets the language requirement information.

[0214] Optionally, the method may further include:

[0215] Step C1: Obtain the meeting entry verification information for the target meeting.

[0216] Step C2: sending the conference entry verification information to the conference server; the conference entry verification information is used by the conference server to add the second interpreter client to the target conference according to the conference entry verification information.

[0217] Step C3: sending language service information to the conference server, so as to provide the language service information to at least one participant joining the target conference through the conference server.

[0218] In an embodiment of the present application, the interpreter server can be connected to the conference server through the entry verification information, and the interpreter server provides translation services, that is, the interpreter server collects the interpreter's language service information and sends the language service information to the conference server, so that the target conference can use the language service information to implement translation services.

[0219] Optionally, the method may further include:

[0220] Step C4: Displaying a takeover control in the display interface of the translator server.

[0221] Step C5: When a touch operation on the takeover control is received, a takeover request is sent to the conference server; the takeover request is used to notify the conference server to allocate the use right of the first transmission channel to the interpreter client.

[0222] Steps C4-C5 may refer to the above steps B14-B15 and will not be described in detail here.

[0223] Optionally, the method may further include:

[0224] Step C6: displaying a language requirement information sending control in the display interface of the conference participant;

[0225] Step C7: When a touch operation on the language requirement information sending control is received, the language requirement information is sent to the conference server.

[0226] Steps C6-C7 may refer to the above steps B5-B6 and will not be described in detail here.

[0227] Optionally, the method may further include:

[0228] Step C8: Use controls for the interpreter client display channel in the participant's display interface.

[0229] Step C9: upon receiving a touch operation on the channel usage control, sending a usage request to the conference server; the usage request is used to notify the translator client to send the language service information to the conference participant.

[0230] Steps C8-C9 can refer to the above steps B3-B4 and will not be repeated here.

[0231] In summary, in the embodiment of the present application, the conference service end that provides conference services is connected with the service provider that provides language services, so that participants participating in the target conference can submit language requirement information to the conference service end, and the conference service end generates entry verification information for adding the service provider that provides language services to the target conference based on the language requirement information, and sends the entry verification information to the service provider that meets the language requirement information, so that the service provider joins the target conference to provide language services through the entry verification information. In the embodiment of the present application, the service provider and the participants are in the same conference, and the participants who listen to the language service do not need to frequently switch between translation content and conference content, thereby reducing user operations and improving user experience.

[0232] Reference Fig.13, showing a step flow chart of an embodiment of a method for processing an audio and video conference of the present application, which is applied to a conference server.

[0233] Step 401: Receive auxiliary service demand information for a target conference.

[0234] Step 402: Generate assistant joining verification information for the target conference according to the auxiliary service demand information.

[0235] Step 403: Send the assistant membership verification information to the auxiliary service provider that meets the auxiliary service demand information.

[0236] Step 404: Receive an access request from the auxiliary service provider to the target conference, wherein the access request carries the assistant's conference entry verification information.

[0237] Step 405: connect the auxiliary service provider to the target conference according to the assistant joining verification information.

[0238] Step 406: Receive auxiliary service information provided by the auxiliary service provider for the target conference.

[0239] Optionally, the conference auxiliary service includes at least one of a translation service, a drawing service, and a performance service.

[0240] In a conference scenario, since the architecture of the conference scenario is relatively simple, when participants have some relatively novel personalized needs, the conference scenario often cannot meet their personalized needs. In order to solve this problem, refer to Figure 4 , the embodiment of the present application can connect the conference server to different personalized service providers, such as the translator server, the draughtsman server, the performance server, etc. The translator server can meet the personalized translation needs of the participants. When the participants have the need to draw, the draughtsman server can assign the corresponding draughtsman to join the meeting and provide drawing services. During the break of the meeting, when the participants hope to have actors perform to relieve fatigue, the performance server can assign the corresponding actors to join the meeting and provide performance services.

[0241] In this architecture, conference participants can make personalized auxiliary service reservations based on their personalized needs. At this time, the conference server can respond to the personalized reservation, match the personalized auxiliary service provider corresponding to the personalized needs, and generate assistant joining verification information and send it to the matched personalized auxiliary service provider, so that the personalized auxiliary service provider can send the assistant joining verification information to the assistant client that meets the personalized needs, so that the assistant client can join the conference and provide personalized auxiliary services through the assistant joining verification information. Figure 4When a participant has a drawing requirement (requirement y), the conference server can send the drawing member joining verification information to the drawing member server, and the drawing member server can further send the drawing member joining verification information to the corresponding drawing member client to realize the provision of drawing service.

[0242] For example, refer to Figure 5 , which shows another conference interface diagram provided by an embodiment of the present application. When a participant has personalized needs, he can call out the personalized reservation interface 30 through the personalized needs control (personalized reservation button) and fill in the personalized needs in the personalized reservation interface 30. Assuming that the personalized auxiliary service provider assigns an assistant 2 to meet its personalized needs, an assistant window 40 corresponding to the assistant 2 can be set in the interface of the target conference, and the assistant window 40 is provided to the assistant 2 for use so that the personalized auxiliary service can be carried out normally. In the case where the assistant is an actor, the assistant can perform a performance through the assistant window 40; in the case where the assistant is a draftsman, the assistant can draw and display the drawing process in the assistant window 40; in the case where the assistant is a translator, the translator can be displayed in the assistant window 40.

[0243] Optionally, after step 402, the method may further include:

[0244] Step 404: different transmission channels are established for different assistant membership verification information, and the different transmission channels are isolated from each other.

[0245] Step 405: When it is determined that the target assistant client joins the target conference through the target assistant joining verification information, provide the conference participant with a conference auxiliary service according to the target transmission channel corresponding to the target assistant joining verification information and the auxiliary data sent by the target assistant client.

[0246] The details of steps 404-405 may refer to the above steps B1-B2, which will not be described again here.

[0247] To summarize, in the embodiments of the present application, the conference server that provides conference services is connected with the server that provides personalized auxiliary services, so that participants participating in the target conference can submit personalized auxiliary service requirements to the conference server. The target server that matches the personalized auxiliary service requirements generates assistant joining verification information for joining the assistant client of the assistant to the target conference according to the personalized auxiliary service requirements, and sends the assistant joining verification information to the target server. The target server can assign an assistant that meets the personalized auxiliary service requirements, and send the assistant joining verification information to the assistant client of the assistant that matches the personalized auxiliary service requirements, so that the assistant client joins the target conference through the assistant joining verification information to provide personalized auxiliary services. In the embodiments of the present application, the assistant and the participants are in the same conference, and the participants who obtain personalized auxiliary services do not need to frequently switch between personalized auxiliary content and conference content, thereby improving the user experience.

[0248] The present application also provides another embodiment of a method for processing an audio or video conference, which is applied to a conference server, including:

[0249] Step 501: Receive language requirement information for a target conference.

[0250] Step 502: Generate assistant membership verification information according to the language requirement information.

[0251] Step 503: Send the membership verification information to a service provider that matches the language requirement information.

[0252] Step 504: different transmission channels are established for different assistant membership verification information, and the different transmission channels are isolated from each other.

[0253] Step 505: When it is determined that the service provider joins the target conference through the assistant joining verification information, the translation audio sent by the service provider is played for at least one participant joining the target conference through an independent audio channel.

[0254] In one implementation, the conference translation service provided by the interpreter company may include a simultaneous interpretation service, which refers to a translation method in which the interpreter interprets the conference content to the audience without interrupting the normal conference speech of the participants. In this form, when the interpreter joins the target conference established by the conference server through the conference verification information, the conference server can identify the interpreter identity and language of the interpreter client through the conference verification information, and establish another language channel independent of the conference channel in the target conference, and add the interpreter client to the language channel of the corresponding language, so that the target conference can normally collect and play the conference audio of the participants through the conference channel, and collect and play the interpreter's translation audio through the language channel, wherein the interpreter client can normally listen to the conference audio through the conference channel and perform simultaneous interpretation, and the translated audio after simultaneous interpretation is played only through the language channel, and the participants connected to the language channel (such as the participants who have made an appointment with the interpreter or other participants with translation needs) can listen to the translated audio in real time to achieve conference simultaneous interpretation.

[0255] To sum up, in the embodiment of the present application, the conference server that provides conference services is connected with the interpreter server that provides interpreter reservation services, so that participants participating in the target conference can submit translation requirements to the conference server. The conference server generates entry verification information for joining the interpreter's interpreter client to the target conference based on the translation requirements, and sends the entry verification information to the interpreter server. The interpreter server can assign an interpreter who meets the translation requirements and send the entry verification information to the interpreter's interpreter client, so that the interpreter client joins the target conference to provide translation services through the entry verification information. In the embodiment of the present application, the interpreter and the participants are in the same conference, and the participants who listen to the translation service do not need to frequently switch between the translation content and the conference content, thereby improving the user experience.

[0256] The present application also provides an embodiment of a method for simultaneous interpretation of live video broadcast, which is applied to a live broadcast server, including:

[0257] Step 601: receiving language requirement information for a target live video.

[0258] Step 602: Generate membership verification information for the target video live broadcast according to the language requirement information, and send the membership verification information to a service provider that matches the language requirement information.

[0259] Step 603: Receive the membership verification information sent by at least one service provider.

[0260] Step 604: Add the service provider to the target video live broadcast according to the membership verification information.

[0261] Step 605: Receive the language service information sent by the service provider, and provide the language service information to at least one viewer who joins the target video live broadcast.

[0262] The embodiment of the present application can also be applied to non-conference scenarios. In one implementation, the embodiment of the present application can also be applied to live broadcast scenarios. Figure 6 , which shows a system architecture diagram of another method for processing audio and video conferences provided in an embodiment of the present application, including: a live broadcast server and a translator server.

[0263] The live broadcast service end can establish a target video live broadcast according to the request of the live broadcaster's client 1. For viewers who join the target video live broadcast, the live broadcast service end can obtain the video content collected by the client 1 and provide audio / video live broadcast services to the viewer's client. In addition, the live broadcast service end can also connect to the translator service end.

[0264] Specifically, in a live broadcast scenario, the client initiating the live broadcast and the client of the viewer may not speak the same language and may also need translation. In this case, the client can fill in the language requirement information in the interpreter reservation interface provided by the live broadcast server and initiate an interpreter reservation instruction to the live broadcast server. The live broadcast server can respond to the interpreter reservation instruction, generate membership verification information for the interpreter to join the target video live broadcast, and send the language requirement information and membership verification information to the interpreter server for the interpreter server to coordinate the reservation of the interpreter. Furthermore, when the client has made an appointment with the interpreter, the live broadcast server can also accept the membership verification information sent by the interpreter client, and after verifying the membership verification information, add the interpreter client to the target video live broadcast to provide translation services.

[0265] To sum up, in the embodiment of the present application, the live broadcast service end providing the live broadcast service is connected with the interpreter service end providing the interpreter reservation service, so that the live broadcast participants participating in the target live broadcast can submit translation requirements to the live broadcast service end, and the live broadcast service end generates membership verification information for joining the interpreter's interpreter client to the target live broadcast according to the translation requirements, and sends the membership verification information to the interpreter server end. The interpreter server end can assign an interpreter who meets the translation requirements, and send the membership verification information to the interpreter's interpreter client, so that the interpreter client joins the target live broadcast to provide translation services through the membership verification information. In the embodiment of the present application, the interpreter and the live broadcast participants are in the same live broadcast, and the live broadcast participants listening to the translation service do not need to frequently switch between the translation content and the live broadcast content, thereby improving the user experience.

[0266] The present application also provides a flowchart of a method for processing live video broadcast, which is applied to a live broadcast server and includes:

[0267] Step 701: Receive auxiliary service demand information sent to the target video live broadcast.

[0268] Step 702: Generate assistant joining verification information for the target video live broadcast according to the auxiliary service demand information.

[0269] Step 703, determine the target service provider that matches the target assistant requirement information from the preset service providers, and send the target assistant joining verification information corresponding to the target assistant requirement information and the target assistant requirement information to the target service provider, so that the target service provider can send the target assistant joining verification information to the first assistant client according to the target assistant requirement information; the assistant joining verification information is used for at least one assistant client to join the target video live broadcast and provide the auxiliary service for at least one viewing client that joins the target video live broadcast.

[0270] The embodiment of the present application can also be applied to non-conference scenarios. In one implementation, the embodiment of the present application can also be applied to live broadcast scenarios. Figure 6 , which shows a system architecture diagram of another method for processing audio and video conferences provided in an embodiment of the present application, including: a live broadcast server, a personalized auxiliary service provider, and the personalized auxiliary service provider is such as at least one of a drawing server, a performance server, and a translator server.

[0271] Among them, the live broadcast service end can establish a target video live broadcast according to the request of the live broadcaster's client 1. For viewers who join the target video live broadcast, the live broadcast service end can obtain the video content collected by the client 1 and provide audio / video live broadcast services to the viewer's client. In addition, the live broadcast service end can also connect to personalized service providers, such as translator service end, illustrator service end, performance service end, etc.

[0272] In this architecture, the viewer's client or the live broadcaster's client can make personalized auxiliary service reservations based on personalized needs. At this time, the live broadcast service end can respond to the personalized reservation, match the personalized auxiliary service provider corresponding to the personalized needs, and generate assistant joining verification information and send it to the matched personalized auxiliary service provider, so that the personalized auxiliary service provider can send the assistant joining verification information to the assistant client that meets the personalized needs, so that the assistant client can join the meeting to provide personalized auxiliary services through the assistant joining verification information.

[0273] To summarize, in the embodiments of the present application, the live broadcast service end providing the live broadcast service is connected with the service end providing the personalized auxiliary service, so that the live broadcast participants participating in the target live broadcast can propose the personalized auxiliary service requirements to the live broadcast service end, and the target server end matching the personalized auxiliary service requirements generates the assistant joining verification information for joining the assistant client of the assistant to the target live broadcast according to the personalized auxiliary service requirements, and sends the assistant joining verification information to the target server end. The target server end can assign the assistant that meets the personalized auxiliary service requirements, and send the assistant joining verification information to the assistant client of the assistant that matches the personalized auxiliary service requirements, so that the assistant client joins the target live broadcast to provide personalized auxiliary services through the assistant joining verification information. In the embodiments of the present application, the assistant and the live broadcast participants are in the same live broadcast, and the live broadcast participants who obtain the personalized auxiliary services do not need to frequently switch between personalized auxiliary content and live broadcast content, thereby improving the user experience.

[0274] It should be noted that, for the method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present application are not limited by the described order of actions, because according to the embodiments of the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present application.

[0275] On the basis of the above embodiments, this embodiment further provides a device for processing audio and video conferences, which is applied to electronic devices such as terminal devices and server terminals.

[0276] Reference Fig.14 , shows a structural block diagram of an embodiment of an audio and video conference processing device of an embodiment of the present application, which may specifically include the following modules:

[0277] The first receiving module 801 is used to receive language requirement information for a target conference.

[0278] The first generating module 802 is configured to generate conference entry verification information for the target conference according to the language requirement information.

[0279] The first sending module 803 is used to send the membership verification information to a service provider that meets the language requirement information.

[0280] The second receiving module 804 is configured to receive an access request from the service provider to the target conference, wherein the access request carries the conference entry verification information.

[0281] The first joining module 805 is used to connect the service provider to the target conference according to the joining verification information.

[0282] The third receiving module 806 is configured to receive the language service information provided by the service provider for the target conference.

[0283] Optionally, the device further comprises:

[0284] A first channel module, used to allocate a first transmission channel to the service provider;

[0285] A second channel module, used to allocate a second transmission channel for audio and video transmission of the target conference;

[0286] The first transmission channel and the second transmission channel are independent of each other;

[0287] The third receiving module 806 includes:

[0288] The first channel transmission submodule is used to receive the language service information provided by the service provider for the target conference through the first transmission channel.

[0289] Optionally, when the language requirement information includes multiple language requirements, a corresponding first transmission channel is allocated to the service provider of each language requirement, and the first transmission channels corresponding to different language requirements are independent of each other.

[0290] Optionally, when there are two or more service providers for the same language requirement, the first channel module includes:

[0291] The common allocation submodule is used to allocate the same first transmission channel to the two or more service providers.

[0292] Optionally, the device further comprises:

[0293] A takeover receiving module, used to receive a takeover request sent by a main service provider among the two or more service providers;

[0294] The takeover execution module is used to select one of the non-primary service providers as a new primary service provider to provide services for the target conference according to the takeover request.

[0295] In summary, in the embodiment of the present application, the conference service end that provides conference services is connected with the service provider that provides language services, so that participants participating in the target conference can submit language requirement information to the conference service end, and the conference service end generates entry verification information for adding the service provider that provides language services to the target conference based on the language requirement information, and sends the entry verification information to the service provider that meets the language requirement information, so that the service provider joins the target conference to provide language services through the entry verification information. In the embodiment of the present application, the service provider and the participants are in the same conference, and the participants who listen to the language service do not need to frequently switch between translation content and conference content, thereby reducing user operations and improving user experience.

[0296] Optionally, the embodiment of the present application further provides a structural block diagram of an embodiment of a processing device for an audio and video conference, which is applied to a conference server and may specifically include the following modules:

[0297] The requirement receiving module 901 is used to receive language requirement information for a target conference;

[0298] A verification generation module 902, configured to generate conference entry verification information for the target conference according to the language requirement information;

[0299] Verification sending module 903, used to send the membership verification information and the language requirement information to the translator server;

[0300] The verification receiving module 904 is used to receive the membership verification information sent by at least one second translator client;

[0301] The translator joining module 905 is used to add the second translator client to the target conference according to the conference joining verification information;

[0302] The translation execution module 906 is configured to receive the language service information sent by the second translator client, and provide the language service information to at least one participant joining the target conference.

[0303] Optionally, the device further comprises:

[0304] A first allocation module is used to allocate a first transmission channel for the interpreter client in the target conference according to the conference entry verification information; the first transmission channel is independent of a second transmission channel of the target conference; the second transmission channel is used to transmit conference data;

[0305] Optionally, the first allocation module includes:

[0306] A language determination submodule, used to determine the target language requirement based on the membership verification information;

[0307] The first allocation submodule is used to allocate a target first transmission channel corresponding to the target language requirement to the translator client in the target conference; wherein different language requirements correspond to different first transmission channels.

[0308] The second allocation submodule is configured to allocate the at least two second translator clients to the same first transmission channel when the membership verification information sent by the at least two second translator clients is the same.

[0309] providing a submodule for providing a replacement control in a display interface provided to the second translator client;

[0310] The takeover submodule is used to allocate the use right of the first transmission channel to any second translator client when receiving a takeover request sent by any second translator client; the takeover request is sent by the second translator client when receiving a touch operation on the takeover control.

[0311] The translation execution module 906 includes:

[0312] A submodule is provided, configured to receive language service information sent by the second translator client based on the first transmission channel, and provide the language service information to at least one participant joining the target conference.

[0313] Optionally, the device further comprises:

[0314] A first providing module, configured to provide a channel use control for the interpreter client in a display interface provided to the conference participant;

[0315] The first trigger module is used to send the language service information of the translator client to any participant when receiving a use request sent by the participant; the use request is sent by the participant when receiving a touch operation on the replacement control.

[0316] Optionally, the device further comprises:

[0317] The second providing module is used to provide a language requirement information sending control in a display interface provided to the first conference participant; the language requirement information is sent by the first conference participant when the requirement information sending control is touched.

[0318] Optionally, the device further comprises:

[0319] A first identity receiving module, configured to receive at least two translator identity information sent by the translator server according to the language requirement information, and provide the at least two translator identity information to the first conference participant;

[0320] The second identity receiving module is used to receive the target translator identity information sent by the target conference participant; the target translator identity information is determined by the conference participant after receiving the target translator identity information selection operation;

[0321] The identity information module is used to send the target translator's identity information to the translator server.

[0322] Optionally, the device further comprises:

[0323] The price receiving module is used to receive the price information corresponding to the multiple interpreter identity information sent by the interpreter server, and send the corresponding relationship between the price information and the interpreter identity information to the first participant for display.

[0324] Optionally, the device further comprises:

[0325] A duration module, used to obtain the duration of the translator client participating in the target conference;

[0326] The billing module is used to generate a translation bill according to the duration after the target meeting ends, and send the translation bill to the participants.

[0327] Optionally, the device further comprises:

[0328] The evaluation receiving module is used to receive the translation quality evaluation information sent by the participant after the target conference ends, and send the translation quality evaluation information to the translator server.

[0329] Optionally, the device further comprises:

[0330] An instruction receiving module, used to receive a conference reservation instruction sent by the first conference participant for reserving a target conference;

[0331] The success information module is used to generate reservation success information containing participant entry verification information after the reservation is successful, and send the reservation success information to the first participant; the participant entry verification information is used for at least one participant to join the target conference.

[0332] Optionally, the device further comprises:

[0333] The third providing module is used to provide a translation requirement control in the reservation success display interface provided to the first participant; the translation requirement control is used to send language requirement information for the target conference to the conference server.

[0334] Optionally, the device further comprises:

[0335] The demand information module is used to receive language demand information for the target conference sent by the first participant during the process of the target conference.

[0336] Optionally, the device further comprises:

[0337] The fourth providing module is used to provide a translation requirement control in the conference interface provided to the first conference participant; the translation requirement control is used to send language requirement information for the target conference to the conference server.

[0338] In summary, in the embodiment of the present application, the conference server that provides conference services is connected to the interpreter server that provides interpreter reservation services, so that participants participating in the target conference can submit translation requirements to the conference server. The conference server generates entry verification information for joining the interpreter's interpreter client to the target conference based on the translation requirements, and sends the entry verification information to the interpreter server. The interpreter server can assign an interpreter who meets the translation requirements and send the entry verification information to the interpreter's interpreter client, so that the interpreter client joins the target conference to provide translation services through the entry verification information. In the embodiment of the present application, the interpreter and the participants are in the same conference, and the participants who listen to the translation service do not need to frequently switch between the translation content and the conference content, thereby improving the user experience.

[0339] Optionally, the embodiment of the present application further provides a structural block diagram of an embodiment of a processing device for an audio and video conference, which is applied to a translator server and may specifically include the following modules:

[0340] A fourth receiving module, configured to determine a first translator client matching the language requirement information from at least one preset translator client;

[0341] A determination module, configured to determine a first translator client matching the language requirement information from at least one preset translator client;

[0342] The second sending module is used to send the conference entry verification information to a first translator client matching the language requirement information; the conference entry verification information is used for at least one of the translator clients to join the target conference.

[0343] In summary, in the embodiment of the present application, the conference server that provides conference services is connected to the interpreter server that provides interpreter reservation services, so that participants participating in the target conference can submit translation requirements to the conference server. The conference server generates entry verification information for joining the interpreter's interpreter client to the target conference based on the translation requirements, and sends the entry verification information to the interpreter server. The interpreter server can assign an interpreter who meets the translation requirements and send the entry verification information to the interpreter's interpreter client, so that the interpreter client joins the target conference to provide translation services through the entry verification information. In the embodiment of the present application, the interpreter and the participants are in the same conference, and the participants who listen to the translation service do not need to frequently switch between the translation content and the conference content, thereby improving the user experience.

[0344] Optionally, the embodiment of the present application further provides a structural block diagram of an embodiment of a processing device for an audio and video conference, which is applied to a conference server and may specifically include the following modules:

[0345] A fifth receiving module, configured to receive auxiliary service demand information for a target conference;

[0346] A second generating module, configured to generate assistant joining verification information for the target conference according to the auxiliary service demand information;

[0347] A third sending module, used to send the assistant joining verification information to an auxiliary service provider that meets the auxiliary service requirement information;

[0348] An access request module, configured to receive an access request from the auxiliary service provider to the target conference, wherein the access request carries the assistant conference entry verification information;

[0349] An access module, configured to connect the auxiliary service provider to the target conference according to the assistant conference entry verification information;

[0350] The auxiliary service providing module is used to receive the auxiliary service information provided by the auxiliary service provider for the target conference.

[0351] In summary, in the embodiments of the present application, the conference server that provides conference services is connected with the server that provides personalized auxiliary services, so that participants participating in the target conference can submit personalized auxiliary service requirements to the conference server. The target server that matches the personalized auxiliary service requirements generates assistant joining verification information for joining the assistant client of the assistant to the target conference according to the personalized auxiliary service requirements, and sends the assistant joining verification information to the target server. The target server can assign an assistant that meets the personalized auxiliary service requirements, and send the assistant joining verification information to the assistant client of the assistant that matches the personalized auxiliary service requirements, so that the assistant client joins the target conference through the assistant joining verification information to provide personalized auxiliary services. In the embodiments of the present application, the assistant and the participants are in the same conference, and the participants who obtain personalized auxiliary services do not need to frequently switch between personalized auxiliary content and conference content, thereby improving the user experience.

[0352] The present application provides a method and device embodiment for processing an audio and video conference, which is applied to a conference server and may specifically include the following modules:

[0353] A sixth receiving module, configured to receive language requirement information for a target conference;

[0354] A third generating module, used to generate assistant joining verification information according to the language requirement information;

[0355] A fourth sending module, configured to send the membership verification information to a service provider matching the language requirement information;

[0356] A channel establishment module is used to establish different transmission channels for different assistant membership verification information, and the different transmission channels are isolated from each other.

[0357] The simultaneous interpretation module is used to play the translation audio sent by the service provider to at least one participant joining the target conference through an independent channel when it is determined that the service provider joins the target conference through the assistant joining verification information.

[0358] In summary, in the embodiment of the present application, the conference server that provides conference services is connected to the interpreter server that provides interpreter reservation services, so that participants participating in the target conference can submit translation requirements to the conference server. The conference server generates entry verification information for joining the interpreter's interpreter client to the target conference based on the translation requirements, and sends the entry verification information to the interpreter server. The interpreter server can assign an interpreter who meets the translation requirements and send the entry verification information to the interpreter's interpreter client, so that the interpreter client joins the target conference to provide translation services through the entry verification information. In the embodiment of the present application, the interpreter and the participants are in the same conference, and the participants who listen to the translation service do not need to frequently switch between the translation content and the conference content, thereby improving the user experience.

[0359] The present application provides a video live broadcast simultaneous interpretation device embodiment, which is applied to a live broadcast server and may specifically include the following modules:

[0360] A seventh receiving module, used for receiving language requirement information for a target video live broadcast;

[0361] A fifth sending module, configured to generate membership verification information for the target video live broadcast according to the language requirement information, and send the membership verification information to a service provider matching the language requirement information;

[0362] an eighth receiving module, configured to receive the membership verification information sent by at least one service provider;

[0363] A second joining module, configured to add the service provider to the target video live broadcast according to the joining verification information;

[0364] The ninth receiving module is used to receive the language service information sent by the service provider and provide the language service information to at least one viewer who joins the target video live broadcast.

[0365] In summary, in the embodiment of the present application, the live broadcast service end providing the live broadcast service is connected with the interpreter service end providing the interpreter reservation service, so that the live broadcast participants participating in the target live broadcast can submit translation requirements to the live broadcast service end, and the live broadcast service end generates membership verification information for joining the interpreter's interpreter client to the target live broadcast according to the translation requirements, and sends the membership verification information to the interpreter server end. The interpreter server end can assign an interpreter who meets the translation requirements, and send the membership verification information to the interpreter's interpreter client, so that the interpreter client joins the target live broadcast to provide translation services through the membership verification information. In the embodiment of the present application, the interpreter and the live broadcast participants are in the same live broadcast, and the live broadcast participants listening to the translation service do not need to frequently switch between the translation content and the live broadcast content, thereby improving the user experience.

[0366] The present application provides a structural block diagram of an embodiment of a video live broadcast processing device, which is applied to a live broadcast server and may specifically include the following modules:

[0367] A tenth receiving module, used for receiving auxiliary service demand information sent for the target video live broadcast;

[0368] A fourth generating module, configured to generate assistant joining verification information for the target video live broadcast according to the auxiliary service demand information;

[0369] The sixth sending module is used to determine a target service provider that matches the target assistant demand information from preset service providers, and send the target assistant joining verification information corresponding to the target assistant demand information and the target assistant demand information to the target service provider, so that the target service provider can send the target assistant joining verification information to the first assistant client according to the target assistant demand information; the assistant joining verification information is used for at least one assistant client to join the target video live broadcast and provide the auxiliary service for at least one viewing client that joins the target video live broadcast.

[0370] In summary, in the embodiments of the present application, the live broadcast service end providing the live broadcast service is connected with the service end providing the personalized auxiliary service, so that the live broadcast participants participating in the target live broadcast can propose the personalized auxiliary service requirements to the live broadcast service end, and the target server end matching the personalized auxiliary service requirements generates the assistant joining verification information for joining the assistant client of the assistant to the target live broadcast according to the personalized auxiliary service requirements, and sends the assistant joining verification information to the target server end. The target server end can assign the assistant who meets the personalized auxiliary service requirements, and send the assistant joining verification information to the assistant client of the assistant who matches the personalized auxiliary service requirements, so that the assistant client joins the target live broadcast to provide personalized auxiliary services through the assistant joining verification information. In the embodiments of the present application, the assistant and the live broadcast participants are in the same live broadcast, and the live broadcast participants who obtain the personalized auxiliary services do not need to frequently switch between personalized auxiliary content and live broadcast content, thereby improving the user experience.

[0371] The embodiment of the present application also provides a non-volatile readable storage medium, which stores one or more modules (programs). When the one or more modules are applied to a device, the device can execute instructions (instructions) of each method step in the embodiment of the present application.

[0372] The present application embodiment provides one or more machine-readable media on which instructions are stored, and when executed by one or more processors, an electronic device executes one or more of the methods described in the above embodiments. In the present application embodiment, the electronic device includes various types of devices such as terminal devices and server terminals (clusters).

[0373] The embodiments of the present disclosure may be implemented as a device that uses any appropriate hardware, firmware, software, or any combination thereof to perform desired configurations, and the device may include electronic devices such as terminal devices and server (cluster). Fig.16 An exemplary device 1800 that can be used to implement various embodiments described in the embodiments of the present application is schematically shown.

[0374] For one embodiment, Fig.16 An exemplary apparatus 1800 is shown having one or more processors 1802, a control module (chip set) 1804 coupled to at least one of the (one or more) processors 1802, a memory 1806 coupled to the control module 1804, a non-volatile memory (NVM) / storage device 1808 coupled to the control module 1804, one or more input / output devices 1810 coupled to the control module 1804, and a network interface 1812 coupled to the control module 1804.

[0375] Processor 702 may include one or more single-core or multi-core processors, and processor 1802 may include any combination of general-purpose processors or special-purpose processors (such as graphics processors, application processors, baseband processors, etc.). In some embodiments, device 1800 can be used as a terminal device, a server (cluster), and other devices described in the embodiments of the present application.

[0376] In some embodiments, the device 1800 may include one or more computer-readable media (e.g., memory 1806 or NVM / storage device 1808) having instructions 1814 and one or more processors 1802 configured to execute the instructions 1814 in combination with the one or more computer-readable media to implement the module to perform the actions described in the present disclosure.

[0377] For one embodiment, the control module 1804 may include any suitable interface controller to provide any suitable interface to at least one of the processor(s) 1802 and / or any suitable device or component in communication with the control module 1804 .

[0378] The control module 1804 may include a memory controller module to provide an interface to the memory 1806. The memory controller module may be a hardware module, a software module, and / or a firmware module.

[0379] The memory 1806 may be used, for example, to load and store data and / or instructions 1814 for the device 1800. For one embodiment, the memory 1806 may include any suitable volatile memory, such as a suitable DRAM. In some embodiments, the memory 1806 may include double data rate type four synchronous dynamic random access memory (DDR4 SDRAM).

[0380] For one embodiment, control module 1804 may include one or more input / output controllers to provide an interface to NVM / storage device 1808 and input / output device(s) 1810 .

[0381] For example, NVM / storage 1808 may be used to store data and / or instructions 1814. NVM / storage 1808 may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable non-volatile storage device(s) (e.g., one or more hard disk drives (HDDs), one or more compact disk (CD) drives, and / or one or more digital versatile disk (DVD) drives).

[0382] NVM / storage device 1808 may include storage resources that are physically part of the device on which apparatus 1800 is installed, or it may be accessible to the device without being part of the device. For example, NVM / storage device 1808 may be accessed via (one or more) input / output devices 1810 over a network.

[0383] (One or more) input / output devices 1810 may provide an interface for the apparatus 1800 to communicate with any other appropriate device, and the input / output device 1810 may include a communication component, an audio component, a sensor component, etc. The network interface 1812 may provide an interface for the apparatus 1800 to communicate through one or more networks, and the apparatus 1800 may wirelessly communicate with one or more components of a wireless network according to any of one or more wireless network standards and / or protocols, for example, accessing a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G, 5G, etc., or a combination thereof for wireless communication.

[0384] For one embodiment, at least one of the processor(s) 1802 may be packaged together with the logic of one or more controllers (e.g., a memory controller module) of the control module 1804. For one embodiment, at least one of the processor(s) 1802 may be packaged together with the logic of one or more controllers of the control module 1804 to form a system-in-package (SiP). For one embodiment, at least one of the processor(s) 1802 may be integrated on the same die with the logic of one or more controllers of the control module 1804. For one embodiment, at least one of the processor(s) 1802 may be integrated on the same die with the logic of one or more controllers of the control module 1804 to form a system-on-chip (SoC).

[0385] In various embodiments, the device 1800 may be, but is not limited to, a terminal device such as a server, a desktop computing device, or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet computer, a netbook, etc.). In various embodiments, the device 1800 may have more or fewer components and / or different architectures. For example, in some embodiments, the device 1800 includes one or more cameras, a keyboard, a liquid crystal display (LCD) screen (including a touch screen display), a non-volatile memory port, multiple antennas, a graphics chip, an application-specific integrated circuit (ASIC), and a speaker.

[0386] Among them, the main control chip can be used as a processor or control module in the detection device, sensor data, location information, etc. are stored in a memory or NVM / storage device, the sensor group can be used as an input / output device, and the communication interface may include a network interface.

[0387] As 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.

[0388] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0389] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0390] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0391] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0392] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0393] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0394] The above is a detailed introduction to the audio and video conference processing method, device, conference simultaneous interpretation method, device, video live broadcast simultaneous interpretation method, device, video live broadcast processing method, device, electronic device and storage medium provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for processing an audio and video conference, characterized in that: The method comprises: Receive information on language requirements for targeted conferences; Generating conference entry verification information for the target conference according to the language requirement information; Sending the membership verification information to at least two service providers that meet the language requirement information; receiving an access request from the service provider to the target conference, wherein the access request carries the conference entry verification information; connecting the service provider to the target conference according to the conference entry verification information; receiving language service information provided by the service provider for the target conference; The service provider includes: a translator server and a translator client; The access request is sent by the translator client after the translator server schedules the translator client that meets the language requirement information according to the membership verification information and sends the membership verification information to the translator client.

2. The method according to claim 1, characterized in that The method further comprises: Allocating a first transmission channel to the service provider; Allocating a second transmission channel for audio and video transmission of the target conference; The first transmission channel and the second transmission channel are independent of each other; Accordingly, the receiving of the language service information provided by the service provider for the target conference includes: The language service information provided by the service provider for the target conference is received through the first transmission channel.

3. The method according to claim 2, characterized in that In the case that the language requirement information includes multiple language requirements, a corresponding first transmission channel is allocated to the service provider of each language requirement, and the first transmission channels corresponding to different language requirements are independent of each other.

4. The method according to claim 2 or 3, characterized in that: In the case where there are two or more service providers for the same language requirement, allocating a first transmission channel to the service providers includes: The same first transmission channel is allocated to the two or more service providers.

5. The method according to claim 4, characterized in that The method further comprises: receiving a takeover request sent by a main service provider among the two or more service providers; According to the takeover request, a new primary service provider is selected from the non-primary service providers to provide services for the target conference.

6. A method for processing an audio and video conference, characterized in that: The method comprises: receiving auxiliary service demand information for a target conference; Generating assistant joining verification information for the target conference according to the auxiliary service demand information; Sending the assistant membership verification information to at least two auxiliary service providers that meet the auxiliary service requirement information; receiving an access request from the auxiliary service provider to the target conference, wherein the access request carries the assistant conference entry verification information; Connecting the auxiliary service provider to the target conference according to the assistant conference entry verification information; receiving auxiliary service information provided by the auxiliary service provider for the target conference; The auxiliary service provider includes: an auxiliary server and an assistant client; The access request is sent by the assistant client after the assistant server schedules the assistant client that meets the auxiliary service demand information according to the assistant joining verification information and sends the assistant joining verification information to the assistant client.

7. A processing device for audio and video conferencing, characterized in that: The device comprises: A first receiving module, configured to receive language requirement information for a target conference; A first generating module, configured to generate conference entry verification information for the target conference according to the language requirement information; A first sending module, configured to send the membership verification information to at least two service providers that meet the language requirement information; A second receiving module is used to receive an access request from the service provider to the target conference, wherein the access request carries the conference entry verification information; A first joining module, configured to connect the service provider to the target conference according to the joining verification information; A third receiving module, configured to receive language service information provided by the service provider for the target conference; The service provider includes: a translator server and a translator client; The access request is sent by the translator client after the translator server schedules the translator client that meets the language requirement information according to the membership verification information and sends the membership verification information to the translator client.

8. A processing device for audio and video conferencing, characterized in that: The device comprises: A fifth receiving module, configured to receive auxiliary service demand information for a target conference; A second generating module, configured to generate assistant joining verification information for the target conference according to the auxiliary service demand information; A third sending module, configured to send the assistant membership verification information to at least two auxiliary service providers that meet the auxiliary service requirement information; An access request module, configured to receive an access request from the auxiliary service provider to the target conference, wherein the access request carries the assistant conference entry verification information; An access module, configured to connect the auxiliary service provider to the target conference according to the assistant conference entry verification information; an auxiliary service providing module, configured to receive auxiliary service information provided by the auxiliary service provider for the target conference; The auxiliary service provider includes: an auxiliary server and an assistant client; The access request is sent by the assistant client after the assistant server schedules the assistant client that meets the auxiliary service demand information according to the assistant joining verification information and sends the assistant joining verification information to the assistant client.

9. An electronic device, characterized in that: include: processor; and A memory having executable codes stored thereon, which, when executed, cause the processor to perform the method according to one or more of claims 1-6.

10. One or more machine-readable media having executable codes stored thereon, which, when executed, cause a processor to perform the method according to one or more of claims 1-6.

Images