Video conference data processing method and device, equipment, medium and product

Abstract

The invention provides a video conference data processing method and device, equipment, a medium and a product, and the method comprises the steps: displaying a conference summary interface in a video conference page of a first user after a first video conference is finished; wherein conference members of the first video conference comprise the first user and the second user; in the conference summary interface, presenting question and answer information in the first video conference; wherein the question and answer information comprises a plurality of question and answer pairs composed of question texts and answer texts; in response to a trigger operation of a first user for target question and answer information in the question and answer information, displaying a conference recording interface in a video conference page; and in the conference recording interface, presenting a conference recording text of the first video conference, and presenting the conference recording text corresponding to the target question and answer information in a set presentation mode. The method can improve the efficiency of combing and summarizing the video conference content by the user.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, electronic device, computer-readable storage medium, and computer program product for processing video conference data. Background Art

[0002] With the continuous development of computer technology, video conferencing has emerged. Video conferencing refers to a conference method in which users transmit video and audio signals in real time through the network and communication equipment to communicate. Users can communicate through video conferencing in different conference scenarios.

[0003] In the related art, after a video conference ends, a record of the video conference can be generated, and the user can view the record to review the content of the video conference. However, some video conferences have a lot of content and information, and the above method can only provide the original record of the video conference. For the video conference content that the user is concerned about, the user needs to conduct a secondary sorting and summary based on the record text, and the processing efficiency of the video conference data is poor. Summary of the invention

[0004] The present application provides a method for processing video conference data. The method can improve the efficiency of users in combing and summarizing video conference content. The present application also provides a device, an electronic device, a computer-readable storage medium, and a computer program product corresponding to the above method.

[0005] In a first aspect, the present application provides a method for processing video conference data, the method comprising:

[0006] After the first video conference ends, a conference summary interface is displayed on the first user's video conference page; wherein the conference members of the first video conference include the first user and the second user;

[0007] In the conference summary interface, question and answer information in the first video conference is presented; wherein the question and answer information includes a plurality of question and answer pairs consisting of question texts and answer texts;

[0008] In response to a triggering operation by the first user on target question and answer information in the question and answer information, displaying a conference record interface in the video conference page;

[0009] In the conference record interface, the conference record text of the first video conference is presented, and the conference record text corresponding to the target question and answer information is presented in a set presentation mode.

[0010] In some possible implementations, the first video conference includes a plurality of video conference sections; and the question and answer information in the first video conference is presented in the conference summary interface, including:

[0011] In the conference summary interface, the question and answer information in the first video conference is presented in the form of a question and answer information group; wherein one question and answer information group includes the question and answer information in one video conference chapter.

[0012] In some possible implementations, the method further includes:

[0013] Receive a feedback operation from the first user regarding the question and answer information; wherein the feedback operation includes at least one of the following operations: an operation representing a first type of evaluation regarding the question and answer information, an operation representing a second type of evaluation regarding the question and answer information, and an operation indicating a reason for generating the second type of evaluation regarding the question and answer information.

[0014] In some possible implementations, presenting the meeting record text corresponding to the target question and answer information in a set presentation mode includes:

[0015] Determining time information when the target question and answer information appears in the first video conference;

[0016] Determining, from the conference record text of the first video conference according to the time information, the conference record text corresponding to the target question and answer information;

[0017] The meeting record text corresponding to the target question and answer information is presented in a set presentation mode.

[0018] In some possible implementations, one of the question texts includes a first sub-question text and a second sub-question text, and the second sub-question text is used to follow up on an answer text corresponding to the first sub-question text.

[0019] In some possible implementations, the question and answer information is determined in the following manner:

[0020] Extracting a question text and an answer text corresponding to the question text from the conference record text of the first video conference to form a question-answer pair;

[0021] Question and answer information is determined according to the question and answer pair.

[0022] In some possible implementations, the question and answer information group is determined in the following manner:

[0023] Dividing the first video conference into a plurality of video conference chapters according to a conference scenario of the first video conference;

[0024] For each video conference chapter among the multiple video conference chapters, the following steps are performed: from the meeting record text of the video conference chapter, a question text and an answer text corresponding to the question text are extracted to form a question-answer pair; based on the question-answer pair, a question-answer information group of the video conference chapter is determined.

[0025] In some possible implementations, the method further includes:

[0026] In the meeting summary interface, meeting summary information related to the second user is presented.

[0027] In some possible implementations, the first video conference is related to a target topic, and the conference summary information related to the second user represents: the degree of adaptation of the second user to the target topic in the first video conference.

[0028] In some possible implementations, the method further includes:

[0029] In the meeting summary interface, multiple label controls are presented; wherein one label control corresponds to one meeting summary dimension;

[0030] In response to a trigger operation by the first user on at least one target label control among the multiple label controls, target meeting summary information of a meeting summary dimension corresponding to the at least one target label control is presented; wherein the target meeting summary information is at least part of the meeting summary information.

[0031] In some possible implementations, the method further includes:

[0032] In the video conference page of the first user, a participant information interface and a conference evaluation interface are displayed side by side with the conference summary interface; wherein the participant information interface is used to present the participant information of the second user, and the conference evaluation interface is used by the first user to fill in the conference evaluation of the second user in the first video conference.

[0033] In a second aspect, the present application provides a device for processing video conference data, the device comprising:

[0034] A display module, configured to display a conference summary interface on a first user's video conference page after the first video conference ends; wherein the conference members of the first video conference include the first user and the second user;

[0035] A presentation module, configured to present, in the conference summary interface, the question and answer information in the first video conference; wherein the question and answer information includes a plurality of question and answer pairs consisting of a question text and an answer text;

[0036] The display module is further configured to display a conference record interface in the video conference page in response to a trigger operation by the first user on target question and answer information in the question and answer information;

[0037] The presentation module is also used to present the meeting record text of the first video conference in the meeting record interface, and to present the meeting record text corresponding to the target question and answer information in a set presentation mode.

[0038] In some possible implementations, the first video conference includes a plurality of video conference sections; and the presentation module is specifically configured to:

[0039] In the conference summary interface, the question and answer information in the first video conference is presented in the form of a question and answer information group; wherein one question and answer information group includes the question and answer information in one video conference chapter.

[0040] In some possible implementations, the device further includes an interaction module, and the interaction module is configured to:

[0041] Receive a feedback operation from the first user regarding the question and answer information; wherein the feedback operation includes at least one of the following operations: an operation representing a first type of evaluation regarding the question and answer information, an operation representing a second type of evaluation regarding the question and answer information, and an operation indicating a reason for generating the second type of evaluation regarding the question and answer information.

[0042] In some possible implementations, the presentation module is specifically used to:

[0043] Determining time information when the target question and answer information appears in the first video conference;

[0044] Determining, from the conference record text of the first video conference according to the time information, the conference record text corresponding to the target question and answer information;

[0045] The meeting record text corresponding to the target question and answer information is presented in a set presentation mode.

[0046] In some possible implementations, one of the question texts includes a first sub-question text and a second sub-question text, and the second sub-question text is used to follow up on an answer text corresponding to the first sub-question text.

[0047] In some possible implementations, the question and answer information is determined in the following manner:

[0048] Extracting a question text and an answer text corresponding to the question text from the conference record text of the first video conference to form a question-answer pair;

[0049] Question and answer information is determined according to the question and answer pair.

[0050] In some possible implementations, the question and answer information group is determined in the following manner:

[0051] Dividing the first video conference into a plurality of video conference chapters according to a conference scenario of the first video conference;

[0052] For each video conference chapter among the multiple video conference chapters, the following steps are performed: from the meeting record text of the video conference chapter, a question text and an answer text corresponding to the question text are extracted to form a question-answer pair; based on the question-answer pair, a question-answer information group of the video conference chapter is determined.

[0053] In some possible implementations, the presentation module is further configured to:

[0054] In the meeting summary interface, meeting summary information related to the second user is presented.

[0055] In some possible implementations, the first video conference is related to a target topic, and the conference summary information related to the second user represents: the degree of adaptation of the second user to the target topic in the first video conference.

[0056] In some possible implementations, the presentation module is further configured to:

[0057] In the meeting summary interface, multiple label controls are presented; wherein one label control corresponds to one meeting summary dimension;

[0058] In response to a trigger operation by the first user on at least one target label control among the multiple label controls, target meeting summary information of a meeting summary dimension corresponding to the at least one target label control is presented; wherein the target meeting summary information is at least part of the meeting summary information.

[0059] In some possible implementations, the presentation module is further configured to:

[0060] In the video conference page of the first user, a participant information interface and a conference evaluation interface are displayed side by side with the conference summary interface; wherein the participant information interface is used to present the participant information of the second user, and the conference evaluation interface is used by the first user to fill in the conference evaluation of the second user in the first video conference.

[0061] In a third aspect, the present application provides an electronic device, the electronic device comprising a processor and a memory. The processor and the memory communicate with each other. The processor is used to execute instructions stored in the memory, so that the electronic device executes the method for processing video conference data in the first aspect or any implementation of the first aspect.

[0062] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, wherein the instructions instruct an electronic device to execute the method for processing video conference data described in the first aspect or any one of the implementations of the first aspect.

[0063] In a fifth aspect, the present application provides a computer program product comprising instructions, which, when executed on an electronic device, enables the electronic device to execute the method for processing video conference data as described in the first aspect or any one of the implementations of the first aspect.

[0064] Based on the implementations provided in the above aspects, this application can also be further combined to provide more implementations.

[0065] It can be seen from the above technical solutions that this application has the following advantages:

[0066] The present application provides a method for processing video conference data. After a first video conference ends, the method displays a conference summary interface on a first user's video conference page, wherein conference members of the first video conference include a first user and a second user. In the conference summary interface, question and answer information in the first video conference is presented, wherein the question and answer information includes a plurality of question and answer pairs consisting of question texts and answer texts. In response to a trigger operation of the first user on target question and answer information in the question and answer information, a meeting record interface is displayed on the video conference page, wherein the meeting record text of the first video conference is presented in the meeting record interface, and the meeting record text corresponding to the target question and answer information is presented in a set presentation mode.

[0067] In this method, after the video conference is over, question and answer information is extracted from the video conference content and provided to the user in the form of question and answer pairs. In this way, the user can intuitively and clearly view the content related to questions and answers in the video conference, and in a video conference with a question and answer scenario (for example, a video conference for an interview), the efficiency of the user in sorting out and summarizing the content of the video conference is improved. In addition, for the target question and answer information that the user is concerned about, the user can directly jump to the corresponding conference record text by triggering the target question and answer information, which is convenient for the user to compare and view the question and answer information and the conference record text, thereby improving the processing efficiency of the video conference data. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to more clearly illustrate the technical method of the embodiments of the present application, the drawings required for use in the embodiments are briefly introduced below.

[0069] Figure 1 A schematic diagram of a video conference page provided in an embodiment of the present application;

[0070] Figure 2 A flowchart of a method for processing video conference data provided in an embodiment of the present application;

[0071] FIG. 3A to FIG. 3F A schematic diagram of a video conference page provided in an embodiment of the present application;

[0072] Figure 4 A schematic diagram of the structure of a device for processing video conference data provided in an embodiment of the present application;

[0073] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0074] The terms "first" and "second" in the embodiments of the present application are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features.

[0075] First, some technical terms and application scenarios involved in the embodiments of this application are introduced.

[0076] With the continuous development of computer technology, video conferencing has emerged. Video conferencing refers to a conference method in which users transmit video signals and audio signals in real time through the network and communication equipment to communicate. Specifically, users (such as conference members) can conduct video conferences with other users (such as other conference members) through video conferencing systems.

[0077] Users can communicate via video conferencing in different conference scenarios. In some examples, the conference scenario can be a question-and-answer scenario, such as a question-and-answer scenario in which an interviewer and a candidate conduct an interview via video conferencing, or a question-and-answer scenario in which an interviewer and an interviewee conduct an interview via video conferencing.

[0078] See also Figure 1 A schematic diagram of a video conference page is shown, where the video conference page 10 can be a page displayed by the client of a first user (e.g., an interviewer). In a video conference in a question-and-answer scenario, the video conference page 10 can be used to present relevant information with other participants in the video conference (e.g., a second user), as well as for the first user to record information in a question-and-answer scenario.

[0079] like Figure 1 As shown, the participant information interface 101 of the video conference page 10 can be used to present the relevant information of the second user. The meeting evaluation interface 102 of the video conference page 10 can be an editable area, and the first user can record the meeting situation in the editable area to form a meeting evaluation. In this way, in a video conference in which the first user and the second user are in a question-and-answer scenario, the first user (for example, an interviewer) can quickly understand the relevant information of the second user through the video conference page, and record the meeting process to achieve an efficient video conference.

[0080] In the related art, after a video conference ends, a record of the video conference can be generated, and the user can view the record to review the content of the video conference. However, in the video conference in the above-mentioned question-and-answer scenario, the content of the video conference is relatively large, the amount of information is large, and there is a large amount of question-and-answer content. It is difficult for users to quickly and effectively sort out and summarize the video conference by only viewing the record. Moreover, usually, the first user also needs to fill in the meeting evaluation after the video conference ends. In the above-mentioned method of only providing the original record of the video conference, it is difficult for the first user to quickly extract the content for filling in the meeting evaluation (such as the quality of the second user's answers to questions during the video conference, etc.) from the record text.

[0081] In view of this, the present application provides a method for processing video conference data. After the first video conference ends, the method displays a meeting summary interface in the video conference page of the first user, wherein the conference members of the first video conference include the first user and the second user. In the meeting summary interface, question and answer information in the first video conference is presented, wherein the question and answer information includes multiple question and answer pairs consisting of question text and answer text. In response to the first user's trigger operation on target question and answer information in the question and answer information, a meeting record interface is displayed in the video conference page, and in the meeting record interface, the meeting record text of the first video conference is presented, and the meeting record text corresponding to the target question and answer information is presented in a set presentation mode.

[0082] In this method, after the video conference is over, question and answer information is extracted from the video conference content and provided to the user in the form of question and answer pairs. In this way, the user can intuitively and clearly view the content related to questions and answers in the video conference, and in a video conference with a question and answer scenario (for example, a video conference for an interview), the efficiency of the user in sorting out and summarizing the content of the video conference is improved. In addition, for the target question and answer information that the user is concerned about, the user can directly jump to the corresponding conference record text by triggering the target question and answer information, which is convenient for the user to compare and view the question and answer information and the conference record text, thereby improving the processing efficiency of the video conference data.

[0083] To facilitate understanding of the technical solution provided by the embodiments of the present application, the following will be described in conjunction with the accompanying drawings. Figure 2 A flow chart of a method for processing video conference data is shown, the method specifically comprising:

[0084] S201: After the first video conference ends, a conference summary interface is displayed on the video conference page of the first user.

[0085] The first video conference can be understood as any video conference that has ended. The first video conference can have different conference scenes. For example, the first video conference can be a video conference in a question-and-answer scene. In other words, the method for processing video conference data provided in the embodiment of the present application is a method for processing video conference data of a ended video conference after the video conference ends.

[0086] The video conferencing page can be understood as a page provided by the video conferencing service. In some embodiments, the video conferencing service is an independent software system. In this case, the user can deploy a video conferencing client on a terminal (such as a mobile terminal, a personal computer, etc.), open the video conferencing client, and a video conferencing page is presented. In other embodiments, the video conferencing service can be used as a functional module of other systems (such as a business platform). In this case, the functional module that provides the video conferencing service in other systems is opened, and a video conferencing page is presented. In some other embodiments, the video conferencing service can also be run as a website (website, WEB) application. In this case, the video conferencing service is opened through a browser, and a video conferencing page is presented.

[0087] In the embodiment of the present application, the conference members of the first video conference include a first user and a second user. The video conference page of the first user can be understood as a video conference page presented to the first user, that is, a video conference page presented in the terminal of the first user.

[0088] When the conference scene of the first video conference is a question-and-answer scene, the first user is usually the questioner and the second user is usually the answerer. That is to say, in the question-and-answer process of the first video conference, the first user usually asks questions and the second user answers them. For example, in a video conference for an interview, the first user can be the interviewer and the second user can be the candidate. In a video conference for an interview, the first user can be the interviewer and the second user can be the interviewee. Considering various types of question-and-answer scenes such as group interviews and group interviews, the second user can also include multiple users.

[0089] The meeting summary interface can be understood as an area in the video conference page. In the embodiment of the present application, considering that the first user has the need to summarize and review the first video conference, for example, when the conference scene of the first video conference is a question-and-answer scene, the first user (such as an interviewer) has the need to summarize and review the first video conference in order to evaluate the performance of the second user (such as a candidate) in the first video conference. Therefore, after the first video conference ends, the meeting summary interface is displayed to the first user in the video conference page, so as to provide the first user with relevant summary content of the first video conference in the meeting summary interface.

[0090] S202: In the conference summary interface, present the question and answer information of the first video conference.

[0091] There may be a large amount of question and answer content in the first video conference, and the question and answer content may be scattered in different time periods of the first video conference. In traditional video conference services, only the conference record text is provided after the video conference ends, and it is difficult for the first user to quickly find the question and answer content scattered in various time periods of the video conference from the conference record text. Therefore, in an embodiment of the present application, question and answer information is extracted from the first video conference, and the question and answer information in the first video conference is presented to the first user.

[0092] The question-and-answer information may include multiple question-and-answer pairs consisting of question texts and answer texts. That is, the question-and-answer information is provided in the form of "question-and-answer pairs". In this way, the scattered question-and-answer contents in the first video conference are merged to form question-and-answer information in the form of question-and-answer pairs, so that the first user can quickly review the question-and-answer contents in the first video conference by viewing the question-and-answer information.

[0093] In specific implementation, the question and answer information can be determined in the following manner: extract the question text and the answer text corresponding to the question text from the conference record text of the first video conference to form a question and answer pair, and determine the question and answer information based on the question and answer pair.

[0094] The process of extracting the question text can be understood as the process of identifying the question sentence from the conference record text, that is, by identifying the question sentence in the conference record text, a question sentence is determined as a question text. Then the conference record text associated with the question text, such as the conference record text whose content similarity with the question text meets the similarity threshold, the conference record text adjacent to the position of the question text in the conference record text, etc., is determined as the answer text of the question text to form a question-answer pair. In this way, the question and answer content in the first video conference is focused on, and the question and answer information is extracted from the conference record text.

[0095] In some possible implementations, the first video conference may include multiple video conference chapters, and one video conference chapter may correspond to one conference sub-topic. That is, according to the conference content of the first video conference, the first video conference is divided into multiple video conference chapters, and the conference contents of different video conference chapters represent different conference sub-topics. For example, in the first video conference used for an interview, multiple video conference chapters may be divided into video conference chapter A and video conference chapter B, and the conference sub-topic of video conference chapter A is "self-introduction", and the conference sub-topic of video conference chapter B is "career planning", that is, in video conference chapter A, the first user and the second user ask and answer questions about the content related to "self-introduction", and in video conference chapter B, the first user and the second user ask and answer questions about the content related to "career planning".

[0096] In the case where the first video conference includes multiple video conference chapters, the question and answer information in the first video conference is presented in the conference summary interface in the form of a question and answer information group, wherein one question and answer information group includes the question and answer information in one video conference chapter.

[0097] That is to say, the question and answer information in a video conference chapter is grouped together, and the question and answer information of the first video conference is presented in groups. For example, in the conference summary interface, the name of video conference chapter A is presented first, and then the question and answer information in video conference chapter A is presented. Then, the name of video conference chapter B is presented, and then the question and answer information in video conference chapter B is presented. In this way, the conference structure of the first video conference is presented to the first user intuitively and clearly, and the question and answer information belonging to the same video conference chapter is presented uniformly, so that the first user can quickly view the question and answer content in the video conference chapter that he is concerned about in the first video conference.

[0098] In specific implementation, the question and answer information group can be determined in the following manner: according to the conference scene of the first video conference, the first video conference is divided into multiple video conference chapters, and for each of the multiple video conference chapters, the following steps are performed: from the meeting record text of the video conference chapter, the question text and the answer text corresponding to the question text are extracted to form a question and answer pair, and based on the question and answer pair, the question and answer information group of the video conference chapter is determined.

[0099] That is to say, taking into account that different meeting scenarios may have different meeting processes (for example, in a video conference used for interviews, the meeting process may include self-introduction, project manager, professional ability assessment, code assessment, career planning, candidate questions, etc.), the first video conference is divided into multiple video conference chapters based on the meeting scenario of the first video conference, and then for each video conference chapter, the question text and answer text are extracted separately to form a question and answer information group in the video conference chapter.

[0100] In some embodiments, a question text includes a first sub-question text and a second sub-question text, and the second sub-question text is used to ask a follow-up question to the answer text corresponding to the first sub-question text. In other words, follow-up questions will be combined with the main question into a question text and presented together in the question and answer information, further optimizing the structure of the question and answer information.

[0101] The embodiments of the present application do not limit the manner of determining whether the second sub-question text is used to ask a follow-up question to the answer text corresponding to the first sub-question text. In some embodiments, by calculating the similarity between the second sub-question text and the answer text corresponding to the first sub-question text, the second sub-question text whose similarity satisfies a set condition (for example, the similarity is greater than a set threshold) is determined as the second sub-question text used to ask a follow-up question to the answer text corresponding to the first sub-question text. In other embodiments, a pre-trained follow-up question determination model may also be used to input the second sub-question text into the follow-up question determination model, receive the determination result output by the follow-up question determination model, and characterize the second sub-question text belonging to the follow-up question type as the second sub-question text used to ask a follow-up question to the answer text corresponding to the first sub-question text.

[0102] Furthermore, the embodiment of the present application also supports the first user to provide feedback on the question and answer information. Specifically, the first user's feedback operation on the question and answer information is received. The feedback operation includes at least one of the following operations: an operation representing a first type of evaluation on the question and answer information, an operation representing a second type of evaluation on the question and answer information, and an operation indicating the reason for generating the second type of evaluation on the question and answer information.

[0103] For example, the first type of evaluation may be a positive evaluation, and the second type of evaluation may be a negative evaluation.

[0104] In other words, the first user can evaluate the question and answer information extracted from the first video conference. In some possible implementations, the conference summary interface provides feedback controls, such as thumbs-up controls and thumbs-down controls. The first user can trigger the thumbs-up control to generate a feedback operation representing a first type of evaluation of the question and answer information, and can also trigger the thumbs-down control to generate a feedback operation representing a second type of evaluation of the question and answer information. When the first user triggers the thumbs-down control, a feedback pop-up window may also be presented. The first user may enter the reason for generating the second type of evaluation of the question and answer information in the feedback pop-up window, such as the question text is divided too finely or too roughly, the answer text does not accurately and comprehensively summarize the second user's speech in the first video conference, etc.

[0105] In addition, considering that there may be a lot of question and answer information in the first video conference and considering the aesthetics of the conference summary interface, only part of the question and answer information may be presented on the conference summary interface, and an expand all control may be provided. The first user may view all the question and answer information on the conference summary interface by triggering the expand all control.

[0106] S203: In response to the first user's triggering operation on the target question and answer information in the question and answer information, displaying a conference record interface in the video conference page.

[0107] The target question and answer information may be any question and answer information in the question and answer information in the first video conference, and the trigger operation may be understood as an operation of selecting the question and answer information in the first video conference. In other words, the first user may select any question and answer information in the question and answer information in the first video conference.

[0108] In the embodiment of the present application, in response to the trigger operation of the first user on the target question and answer information, the video conference page jumps from the conference summary interface to the conference record interface. In this way, a jump method between the conference summary interface and the conference record interface is provided, so that the first user can quickly jump from the question and answer information to the conference record text, and conveniently jump between the summary contents under different dimensions of the first video conference.

[0109] S104: In the conference record interface, present the conference record text of the first video conference, and present the conference record text corresponding to the target question and answer information in a set presentation mode.

[0110] The conference record interface is used to present the conference record text. In the embodiment of the present application, the conference record interface can present the conference record text of the first video conference, for example, present the conference record text in the chronological order of the first video conference.

[0111] Since the meeting record interface is displayed by jumping to the trigger operation of the first user on the target question and answer information, the meeting record text corresponding to the target question and answer information is presented in the set presentation mode in the presented meeting record text.

[0112] The setting presentation mode can be understood as a presentation mode different from the presentation of other meeting record texts in the meeting record interface, for example, the setting presentation mode can be a highlight presentation. The meeting record text corresponding to the target question and answer information can be understood as the source of the target question and answer information in the meeting record text.

[0113] Specifically, determine the time information when the target question and answer information appears in the first video conference, and determine the meeting record text corresponding to the target question and answer information from the meeting record text of the first video conference based on the time information, so as to set the presentation method and present the meeting record text corresponding to the target question and answer information.

[0114] For example, the time information at which the target question and answer information appears in the first video conference is 10 minutes and 20 seconds. From the conference record text of the first video conference, the conference record text at 10 minutes and 20 seconds is determined as the conference record text corresponding to the target question and answer information. In this way, the time information is used as an intermediary between the question and answer information and the conference record text to achieve the positioning of the target question and answer information in the conference record text, so that the first user can further trace back the first video conference through the conference record text, or the first user can also jump to the corresponding conference record text for confirmation when he has questions about the target question and answer information.

[0115] Furthermore, a return control may be provided in the meeting record interface. The first user may trigger the return control to redisplay the meeting summary interface in the video conference page. Furthermore, the content presented in the meeting summary interface may be the same as the content before the first user triggered the target question and answer information.

[0116] In this method, after the video conference is over, question and answer information is extracted from the video conference content and provided to the user in the form of question and answer pairs. In this way, the user can intuitively and clearly view the content related to questions and answers in the video conference, and in a video conference with a question and answer scenario (for example, a video conference for an interview), the efficiency of the user in sorting out and summarizing the content of the video conference is improved. In addition, for the target question and answer information that the user is concerned about, the user can directly jump to the corresponding conference record text by triggering the target question and answer information, which is convenient for the user to compare and view the question and answer information and the conference record text, thereby improving the processing efficiency of the video conference data.

[0117] The foregoing describes a method for processing video conference data provided in an embodiment of the present application. In an embodiment of the present application, a meeting summary interface is provided in the video conference page of the first user, and question and answer information in the first video conference is presented to the first user through the meeting summary interface, so that the first user can trace back the question and answer content in the first video conference without searching in the meeting record text.

[0118] In some embodiments, when the conference scenario of the first video conference is a question-and-answer scenario, since the first user is usually the questioner and the second user is usually the answerer, after the first video conference, the first user can evaluate the second user based on the second user's answer performance in the first video conference.

[0119] Taking the first video conference used for an interview as an example, the first user can be the interviewer and the second user can be the candidate. After the first video conference, the first user can evaluate the interview performance of the second user based on the second user's answers in the first video conference.

[0120] In traditional video conferencing services, the first user needs to look through the second user's answer text from the conference record text and evaluate the second user's answer performance, which is time-consuming and labor-intensive. In an embodiment of the present application, the conference summary information related to the second user can also be presented in the conference summary interface.

[0121] That is, based on the answer performance of the second user in the first video conference, the conference summary information for the second user is generated. In specific implementation, the answer performance in the first video conference is summarized using a language model to generate conference summary information related to the second user. The language model has natural language processing capabilities and can be used to process natural language tasks. For example, the language model can be a deep learning model trained using text data.

[0122] In some embodiments, the meeting summary information related to the second user is generated based on prompt learning. Among them, the prompt word can be used to guide the language model to perform specific output in a generative task (such as a text generation task, a question-answering task, and a dialogue task). By configuring the prompt word, the language model is helped to understand the background and requirements of the task, so that the language model can handle different types of natural language processing tasks without retraining the language model, thereby increasing the scalability and flexibility of the language model.

[0123] In the embodiment of the present application, the prompt word may include the text of the meeting record of the first video conference and information indicating that the language model analyzes the part of the text related to the second user in the meeting record text and evaluates the answer text of the second user. In this way, the prompt word is sent to the language model, and the language model can evaluate the answer performance of the second user based on the prompt ability of the prompt word, combined with the question of the first user and the answer of the second user in the meeting record text, and return the meeting summary information related to the second user.

[0124] In some embodiments, the first video conference is related to a target topic, and the conference summary information related to the second user may represent: the degree of adaptation of the second user to the target topic in the first video conference.

[0125] The target topic can be understood as the conference topic of the first video conference. For example, in the first video conference for interviews, the target topic can be understood as the interview position, that is, the first video conference interviews for a certain position. For another example, in the first video conference for interviews, the target topic can be understood as the topic of the interview, that is, the first video conference interviews for a certain topic.

[0126] Since the meeting summary information related to the second user represents the degree of adaptation of the second user to the target topic in the first video conference, the first user can quickly understand whether the second user is adapted to the target topic by viewing the meeting summary information related to the second user in the meeting summary interface, for example, whether the second user is competent for a certain position, or whether the second user is close to the interview topic.

[0127] In the first video conference used for the interview, the conference summary information related to the second user may specifically include the second user's advantages in the position, reasons for job hunting, future career plans, etc.

[0128] Furthermore, in traditional video conferencing services, in addition to providing the text of the meeting record, meeting minutes can also be provided. Among them, the meeting minutes can be understood as a meeting summary generated after analyzing the overall content of the video conference. However, in actual video conferences, universal meeting minutes often cannot meet the personalized needs of users. For example, in video conferences used for interviews, different positions and different evaluation habits allow different interviewers to evaluate candidates from different dimensions.

[0129] Therefore, in an embodiment of the present application, a multi-dimensional meeting summary function is introduced. Specifically, in the meeting summary interface, multiple label controls are presented, and in response to a trigger operation of the first user on at least one target label control among the multiple label controls, target meeting summary information of the meeting summary dimension corresponding to the at least one target label control is presented.

[0130] Among them, a label control corresponds to a meeting summary dimension, and the target meeting summary information is at least part of the meeting summary information. That is to say, the embodiment of the present application provides the first user with target meeting summary information under different meeting summary dimensions. The first user can select the meeting summary dimension required by him / her based on actual needs by triggering the target label control. In this way, the first user can view the meeting summary information under the meeting summary dimension corresponding to the selected target label control, thereby improving the flexibility of the meeting summary and meeting the personalized needs of different users.

[0131] In specific implementation, similarly, the language model can also be used to generate meeting summary information of different meeting summary dimensions. The prompt word can include the meeting record text of the first video conference, multiple meeting summary dimensions, and information indicating that the language model generates meeting summary information of multiple meeting summary dimensions for the meeting record text. In this way, the prompt word is sent to the language model, and the language model can return meeting summary information of different meeting summary dimensions based on the prompt ability of the prompt word, combined with the meeting record text and multiple meeting summary dimensions.

[0132] In some embodiments, when the conference scene of the first video conference is a question-and-answer scene, considering that the first user usually needs to evaluate the conference for the second user, in the embodiment of the present application, the participant information interface and the conference evaluation interface can also be displayed side by side with the conference summary interface on the video conference page of the first user. Among them, the participant information interface is used to present the participant information of the second user, and the conference evaluation interface is used by the first user to fill in the conference evaluation of the second user in the first video conference.

[0133] In this way, by displaying the participant information interface, the meeting summary interface, and the meeting evaluation interface side by side, when the first user fills in the second user's meeting evaluation in the first video conference, he can directly refer to the second user's participant information in the participant information interface and the question and answer information and meeting summary information related to the second user in the meeting summary interface. For example, in the first video conference for an interview, the first user can directly refer to the second user's resume in the participant information interface and the question and answer information in the meeting summary interface and the second user's interview summary information, which is convenient for the first user to review the interview content while writing the interview evaluation without switching between multiple interfaces.

[0134] The following describes the method for processing video conference data provided by the embodiment of the present application in conjunction with a specific scenario. FIG. 3A to FIG. 3F A schematic diagram of a video conference page is shown in FIG. Figure 3A In the example, after the first video conference ends, the video conference page 30 displays the participant information interface 301 and the conference summary interface 302. The first video conference is a video conference in a question-and-answer scenario, and the video conference page 30 is a video conference page presented in the terminal of the first user. The participant information interface 301 presents relevant information of the second user, and the conference summary interface 302 includes conference summary information 3021 and question-and-answer information 3022 related to the second user.

[0135] The conference summary information 3021 related to the second user represents the degree of adaptation of the second user to the target topic in the first video conference, that is, the conference summary information 3021 related to the second user summarizes the performance of the second user in the first video conference in combination with the speech of the second user in the first video conference. The question and answer information 3022 presents the question and answer information in the first video conference in the form of a question and answer information group. For example, the question and answer information group can be divided into the question and answer information in the "Planning" video conference section and the question and answer information in the "Knowledge" video conference section.

[0136] exist Figure 3BIn the conference summary interface 302, the first user can trigger a feedback operation for the question and answer information 3022 in the conference summary interface 302. Specifically, the area presenting the question and answer information 3022 provides feedback controls, such as a thumbs-up control and a thumbs-down control. The first user can trigger the thumbs-up control to indicate a first type of evaluation for the question and answer information 3022, or the first user can trigger the thumbs-down control to indicate a second type of evaluation for the question and answer information 3022. After the first user triggers the thumbs-down control, the first user can also enter a reason for generating the second type of evaluation for the question and answer information 3022 (not shown in the figure).

[0137] exist Figure 3C In the video conference page 30, the first user can place the focus (for example, the mouse) on any target question and answer information in the question and answer information 3022. At this time, the area presenting the target question and answer information provides a jump control 3024. In response to the first user's trigger operation on the target question and answer information (for example, a trigger operation on the jump control 3024), the user can jump to the meeting record interface in the video conference page 30.

[0138] like Figure 3D As shown, in response to the trigger operation of the first user on the target question and answer information, a meeting record interface 303 is displayed in the video conference page 30. The meeting record interface 303 presents the meeting record text of the first video conference, and the meeting record text 3031 corresponding to the target question and answer information is presented in a set presentation mode (for example, highlighted).

[0139] exist Figure 3E In the conference summary interface 302, a plurality of label controls 3025 are also provided, and a label control 3025 corresponds to a conference summary dimension, such as "first dimension", "second dimension", "third dimension", etc. The first user can select a target label control from the plurality of label controls 3025 ( Figure 3E In the figure, in response to the first user's triggering operation on the target label control, the target meeting summary information 3021 of the meeting summary dimension corresponding to the target label control is presented, that is, the target meeting summary information related to the "first dimension" and the "second dimension".

[0140] exist Figure 3F In the video conference page 30, the conference information interface 301, the conference summary interface 302 and the conference evaluation interface 303 are displayed in parallel. In this way, the first user can fill in the conference evaluation in the conference evaluation interface 303 by combining the relevant information of the second user in the conference information interface 301 and the conference summary information and question and answer information in the conference summary interface 302, without switching back and forth between different interfaces.

[0141] Combination of the above Figure 1Figure 3 provides a detailed introduction to the method for processing video conference data provided in the embodiment of the present application. The following will introduce the apparatus and device provided in the embodiment of the present application in conjunction with the accompanying drawings.

[0142] See also Figure 4 The schematic diagram of the structure of the apparatus for processing video conference data shown in FIG. 40 includes:

[0143] Display module 401 is used to display a conference summary interface in the video conference page of the first user after the first video conference ends; wherein the conference members of the first video conference include the first user and the second user;

[0144] A presentation module 402 is used to present the question and answer information in the first video conference in the conference summary interface; wherein the question and answer information includes a plurality of question and answer pairs consisting of question texts and answer texts;

[0145] The display module 401 is further configured to display a conference record interface in the video conference page in response to a trigger operation by the first user on a target question and answer information in the question and answer information;

[0146] The presentation module 402 is further configured to present the meeting record text of the first video conference in the meeting record interface, and present the meeting record text corresponding to the target question and answer information in a set presentation mode.

[0147] In some possible implementations, the first video conference includes a plurality of video conference sections; and the presentation module 402 is specifically configured to:

[0148] In the conference summary interface, the question and answer information in the first video conference is presented in the form of a question and answer information group; wherein one question and answer information group includes the question and answer information in one video conference chapter.

[0149] In some possible implementations, the device further includes an interaction module, and the interaction module is configured to:

[0150] Receive a feedback operation from the first user regarding the question and answer information; wherein the feedback operation includes at least one of the following operations: an operation representing a first type of evaluation regarding the question and answer information, an operation representing a second type of evaluation regarding the question and answer information, and an operation indicating a reason for generating the second type of evaluation regarding the question and answer information.

[0151] In some possible implementations, the presenting module 402 is specifically configured to:

[0152] Determining time information when the target question and answer information appears in the first video conference;

[0153] Determining, from the conference record text of the first video conference according to the time information, the conference record text corresponding to the target question and answer information;

[0154] The meeting record text corresponding to the target question and answer information is presented in a set presentation mode.

[0155] In some possible implementations, one of the question texts includes a first sub-question text and a second sub-question text, and the second sub-question text is used to follow up on an answer text corresponding to the first sub-question text.

[0156] In some possible implementations, the question and answer information is determined in the following manner:

[0157] Extracting a question text and an answer text corresponding to the question text from the conference record text of the first video conference to form a question-answer pair;

[0158] Question and answer information is determined according to the question and answer pair.

[0159] In some possible implementations, the question and answer information group is determined in the following manner:

[0160] Dividing the first video conference into a plurality of video conference chapters according to a conference scenario of the first video conference;

[0161] For each video conference chapter among the multiple video conference chapters, the following steps are performed: from the meeting record text of the video conference chapter, a question text and an answer text corresponding to the question text are extracted to form a question-answer pair; based on the question-answer pair, a question-answer information group of the video conference chapter is determined.

[0162] In some possible implementations, the presenting module 402 is further configured to:

[0163] In the meeting summary interface, meeting summary information related to the second user is presented.

[0164] In some possible implementations, the first video conference is related to a target topic, and the conference summary information related to the second user represents: the degree of adaptation of the second user to the target topic in the first video conference.

[0165] In some possible implementations, the presenting module 402 is further configured to:

[0166] In the meeting summary interface, multiple label controls are presented; wherein one label control corresponds to one meeting summary dimension;

[0167] In response to a trigger operation by the first user on at least one target label control among the multiple label controls, target meeting summary information of a meeting summary dimension corresponding to the at least one target label control is presented; wherein the target meeting summary information is at least part of the meeting summary information.

[0168] In some possible implementations, the presenting module 402 is further configured to:

[0169] In the video conference page of the first user, a participant information interface and a conference evaluation interface are displayed side by side with the conference summary interface; wherein the participant information interface is used to present the participant information of the second user, and the conference evaluation interface is used by the first user to fill in the conference evaluation of the second user in the first video conference.

[0170] The video conference data processing device 40 according to the embodiment of the present application may correspond to the method described in the embodiment of the present application, and the above and other operations and / or functions of each module / unit of the video conference data processing device 40 are respectively to implement Figure 1 For the sake of brevity, the corresponding processes of each method in the illustrated embodiment are not described in detail here.

[0171] The present application also provides an electronic device. The electronic device is specifically used to implement Figure 4 The functions of the apparatus 40 for processing video conference data in the illustrated embodiment.

[0172] Figure 5 A schematic diagram of the structure of an electronic device 500 is provided. Figure 5 As shown, the electronic device 500 includes a bus 501, a processor 502, a communication interface 503 and a memory 504. The processor 502, the memory 504 and the communication interface 503 communicate with each other via the bus 501.

[0173] The bus 501 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0174] The processor 502 may be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0175] The communication interface 503 is used for communicating with the outside. For example, the communication interface 503 can be used for communicating with a terminal.

[0176] The memory 504 may include a volatile memory, such as a random access memory (RAM). The memory 504 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0177] The memory 504 stores executable codes, and the processor 502 executes the executable codes to perform the aforementioned video conference data processing method.

[0178] Specifically, in implementing Figure 4 In the case of the embodiment shown, and Figure 4 When each module or unit of the video conference data processing device 40 described in the embodiment is implemented by software, the execution Figure 4 The software or program code required for the functions of each module / unit in the video conference system may be partially or completely stored in the memory 504. The processor 502 executes the program code corresponding to each unit stored in the memory 504 to execute the aforementioned video conference data processing method.

[0179] The embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that can be stored by the computing device or a data storage device such as a data center that contains one or more available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid-state hard disk). The computer-readable storage medium includes instructions that instruct the computing device to execute the above-mentioned method for processing video conference data applied to the processing device 40 for video conference data.

[0180] The embodiment of the present application further provides a computer program product, which includes one or more computer instructions. When the computer instructions are loaded and executed on a computing device, the process or function described in the embodiment of the present application is generated in whole or in part.

[0181] The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer or data center to another website, computer or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0182] When the computer program product is executed by a computer, the computer executes any of the aforementioned methods for processing video conference data. The computer program product may be a software installation package, and when any of the aforementioned methods for processing video conference data is required, the computer program product may be downloaded and executed on a computer.

[0183] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to each embodiment of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0184] The units involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the unit / module does not, in some cases, constitute a limitation on the unit itself.

[0185] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0186] In the context of the present application embodiment, machine-readable medium can be a tangible medium that can contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable medium can include but is not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the above. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0187] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the various embodiments can be referred to each other. For the system or device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0188] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0189] It should also 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 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 device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0190] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0191] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for processing video conference data, characterized in that: The method comprises: After the first video conference ends, a conference summary interface is displayed on the first user's video conference page; wherein the conference members of the first video conference include the first user and the second user; In the conference summary interface, question and answer information in the first video conference is presented; wherein the question and answer information includes a plurality of question and answer pairs consisting of question texts and answer texts; In response to a triggering operation by the first user on target question and answer information in the question and answer information, displaying a conference record interface in the video conference page; In the conference record interface, the conference record text of the first video conference is presented, and the conference record text corresponding to the target question and answer information is presented in a set presentation mode.

2. The method according to claim 1, characterized in that: The first video conference includes a plurality of video conference chapters; and the question and answer information in the first video conference is presented in the conference summary interface, including: In the conference summary interface, the question and answer information in the first video conference is presented in the form of a question and answer information group; wherein one question and answer information group includes the question and answer information in one video conference chapter.

3. The method according to claim 1, characterized in that The method further comprises: Receive a feedback operation from the first user regarding the question and answer information; wherein the feedback operation includes at least one of the following operations: an operation representing a first type of evaluation regarding the question and answer information, an operation representing a second type of evaluation regarding the question and answer information, and an operation indicating a reason for generating the second type of evaluation regarding the question and answer information.

4. The method according to claim 1, characterized in that The presenting of the meeting record text corresponding to the target question and answer information in a set presentation mode includes: Determining time information when the target question and answer information appears in the first video conference; Determining, from the conference record text of the first video conference according to the time information, the conference record text corresponding to the target question and answer information; The meeting record text corresponding to the target question and answer information is presented in a set presentation mode.

5. The method according to claim 1, characterized in that The question text includes a first sub-question text and a second sub-question text, and the second sub-question text is used to follow up on the answer text corresponding to the first sub-question text.

6. The method according to claim 1, characterized in that The question and answer information is determined in the following manner: Extracting a question text and an answer text corresponding to the question text from the conference record text of the first video conference to form a question-answer pair; Question and answer information is determined according to the question and answer pair.

7. The method according to claim 2, characterized in that: The question and answer information group is determined in the following manner: Dividing the first video conference into a plurality of video conference chapters according to a conference scenario of the first video conference; For each video conference chapter among the multiple video conference chapters, the following steps are performed: from the meeting record text of the video conference chapter, a question text and an answer text corresponding to the question text are extracted to form a question-answer pair; based on the question-answer pair, a question-answer information group of the video conference chapter is determined.

8. The method according to claim 1, characterized in that: The method further comprises: In the meeting summary interface, meeting summary information related to the second user is presented.

9. The method according to claim 8, characterized in that The first video conference is related to a target topic, and the conference summary information related to the second user represents: the degree of adaptation of the second user to the target topic in the first video conference.

10. The method according to claim 8, characterized in that The method further comprises: In the meeting summary interface, multiple label controls are presented; wherein one label control corresponds to one meeting summary dimension; In response to a trigger operation by the first user on at least one target label control among the multiple label controls, target meeting summary information of a meeting summary dimension corresponding to the at least one target label control is presented; wherein the target meeting summary information is at least part of the meeting summary information.

11. The method according to any one of claims 1 to 10, characterized in that: The method further comprises: In the video conference page of the first user, a participant information interface and a conference evaluation interface are displayed side by side with the conference summary interface; wherein the participant information interface is used to present the participant information of the second user, and the conference evaluation interface is used by the first user to fill in the conference evaluation of the second user in the first video conference.

12. A device for processing video conference data, characterized in that: The device comprises: A display module, configured to display a conference summary interface on a first user's video conference page after the first video conference ends; wherein the conference members of the first video conference include the first user and the second user; A presentation module, configured to present, in the conference summary interface, the question and answer information in the first video conference; wherein the question and answer information includes a plurality of question and answer pairs consisting of a question text and an answer text; The display module is further configured to display a conference record interface in the video conference page in response to a trigger operation by the first user on target question and answer information in the question and answer information; The presentation module is also used to present the meeting record text of the first video conference in the meeting record interface, and to present the meeting record text corresponding to the target question and answer information in a set presentation mode.

13. An electronic device, characterized in that: The electronic device comprises a processor and a memory; The processor is configured to execute instructions stored in the memory, so that the electronic device performs the method according to any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that: The method comprises instructions, wherein the instructions instruct an electronic device to execute the method according to any one of claims 1 to 11.

15. A computer program product, characterized in that The computer program product comprises computer readable instructions for implementing the method according to any one of claims 1 to 11.

Images