CN117076642A

CN117076642A - Question interaction method and device, computer equipment and storage medium

Info

Publication number: CN117076642A
Application number: CN202311114609.7A
Authority: CN
Inventors: 刘思涛; 王洁; 刘玲玲; 冯美婷; 李日霞; 陈明; 孟祥仁; 张震; 黄金源; 邵玮
Original assignee: Beijing Youzhuju Network Technology Co Ltd
Current assignee: Beijing Youzhuju Network Technology Co Ltd
Priority date: 2023-08-31
Filing date: 2023-08-31
Publication date: 2023-11-17

Abstract

The disclosure provides a question interaction method, a question interaction device, computer equipment and a storage medium, wherein the method comprises the following steps: responding to a question request initiated in the process of playing the learning video, and acquiring the video playing progress; determining target video content for problem recommendation according to the video playing progress; displaying target text content corresponding to the target video content and recommending problems; responding to the editing operation aiming at the target text content, and updating the displayed recommendation problem; and the recommendation questions are used for displaying corresponding answer results after being triggered.

Description

Question interaction method and device, computer equipment and storage medium

Technical Field

The disclosure relates to the technical field of artificial intelligence, in particular to a question interaction method, a question interaction device, computer equipment and a storage medium.

Background

When a user learns through a learning video, questions may be given about learning contents taught in the learning video, such as questions to be answered about teaching contents of a teacher in a courseware. In this case, if the user wants to solve the learning problem generated in the video learning, the user needs to summarize the learning problem by himself, search the question by using a search function or the like, screen the solution of the obtained problem, and return to continue playing the learning video for learning.

In the above case, it is difficult for the user to summarize questions to be asked from the content shown in the learning video, and it may take a long time to think about the summarized questions. Therefore, this approach is cumbersome and inefficient for the user.

Disclosure of Invention

The embodiment of the disclosure at least provides a question interaction method, a question interaction device, computer equipment and a storage medium.

In a first aspect, an embodiment of the present disclosure provides a question interaction method, including: responding to a question request initiated in the process of playing the learning video, and acquiring the video playing progress; determining target video content for problem recommendation according to the video playing progress; displaying target text content corresponding to the target video content and recommending problems; responding to the editing operation aiming at the target text content, and updating the displayed recommendation problem; and the recommendation questions are used for displaying corresponding answer results after being triggered.

In an alternative embodiment, determining target video content for problem recommendation according to the video playing progress includes: according to the video playing progress, taking the video content in a preset time range before and after the video playing progress as the target video content; or determining a currently learned target title or target knowledge point according to the video playing progress, and taking video content associated with the target title or target knowledge point as the target video content.

In an alternative embodiment, the target text content is determined according to the following steps: extracting first text content from the target video content, and converting audio content of the target video content into second text content; and integrating the first text content and the second text content to obtain target text content.

In an alternative embodiment, the recommendation question is determined according to the following steps: selecting candidate questions with the correlation degree between the candidate questions and the target text content or the edited target text content meeting preset conditions from a learning question library; and selecting the at least one recommended problem from the candidate problems according to the authorized acquired user learning data and/or the historical consumption data corresponding to the candidate problems.

In an alternative embodiment, the method further comprises: in response to reaching a problem recommendation opportunity in the process of playing the learning video, displaying at least one recommendation problem corresponding to the current video content; and the problem recommendation time is determined based on the video playing progress corresponding to each problem associated with the learning video, the historical consumption data of each problem and the real-time learning data of the current learning user.

In an optional implementation manner, the displaying the target text content and the recommendation problem corresponding to the target video content includes: displaying an artificial intelligence question-answering window in a video playing page, and displaying the target text content and the recommendation problem in the artificial intelligence question-answering window; and the target text content is in an editable state, or the display area of the target text content displays editing indication information, and the target text content enters the editable state after the editing indication information is triggered.

In an alternative embodiment, the artificial intelligence question-answering window displays a question information input area; the method further comprises the steps of: and responding to the triggering operation of the questioning information input area, receiving and displaying the questioning information input in the input area, and displaying the target text content at the adjacent position of the input area.

In an optional implementation manner, after displaying the target text content corresponding to the target video content, the method further includes: receiving questioning information input by a user; under the condition that the questioning intention corresponding to the questioning information is the learning intention, selecting and displaying a recommended question matched with the questioning information from a learning question library; and when the questioning intention corresponding to the questioning information is a non-learning intention or no recommended questions matched with the questioning information exist in the learning question library, displaying an artificial intelligent answer result corresponding to the questioning information.

In a second aspect, an embodiment of the present disclosure further provides a question interaction device, including: the acquisition module is used for responding to the inquiry request initiated in the process of playing the learning video and acquiring the video playing progress; the determining module is used for determining target video content for problem recommendation according to the video playing progress; the first display module is used for displaying the target text content and the recommendation problem corresponding to the target video content; the second display module is used for responding to the editing operation aiming at the target text content and updating the displayed recommendation problem; and the recommendation questions are used for displaying corresponding answer results after being triggered.

In an alternative embodiment, the determining module is configured to, when determining the target video content for problem recommendation according to the video playing progress: according to the video playing progress, taking the video content in a preset time range before and after the video playing progress as the target video content; or determining a currently learned target title or target knowledge point according to the video playing progress, and taking video content associated with the target title or target knowledge point as the target video content.

In an alternative embodiment, the apparatus further comprises a processing module configured to: in response to reaching a problem recommendation opportunity in the process of playing the learning video, displaying at least one recommendation problem corresponding to the current video content; and the problem recommendation time is determined based on the video playing progress corresponding to each problem associated with the learning video, the historical consumption data of each problem and the real-time learning data of the current learning user.

In an optional implementation manner, when the first display module displays the target text content and the recommendation problem corresponding to the target video content, the first display module is configured to: displaying an artificial intelligence question-answering window in a video playing page, and displaying the target text content and the recommendation problem in the artificial intelligence question-answering window; and the target text content is in an editable state, or the display area of the target text content displays editing indication information, and the target text content enters the editable state after the editing indication information is triggered.

In an alternative embodiment, the artificial intelligence question-answering window displays a question information input area; the first display module is further configured to: and responding to the triggering operation of the questioning information input area, receiving and displaying the questioning information input in the input area, and displaying the target text content at the adjacent position of the input area.

In an alternative embodiment, after displaying the target text content corresponding to the target video content, the first display module is further configured to: receiving questioning information input by a user; under the condition that the questioning intention corresponding to the questioning information is the learning intention, selecting and displaying a recommended question matched with the questioning information from a learning question library; and when the questioning intention corresponding to the questioning information is a non-learning intention or no recommended questions matched with the questioning information exist in the learning question library, displaying an artificial intelligent answer result corresponding to the questioning information.

In a third aspect, embodiments of the present disclosure further provide a computer device, comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory in communication via the bus when the computer device is running, the machine-readable instructions when executed by the processor performing the steps of the first aspect, or any of the alternative embodiments of the first aspect.

In a fourth aspect, the presently disclosed embodiments also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the first aspect, or any of the alternative embodiments of the first aspect, described above.

According to the questioning interaction method, the questioning interaction device, the computer equipment and the storage medium, in the process of playing the learning video by the user, target video content for recommending the questions can be determined according to the video playing progress, and after the target text content and the recommended questions corresponding to the target video content are displayed, answer results corresponding to the recommended questions after editing operation is performed on the recommended questions are displayed to the user.

By adopting the scheme of the embodiment of the disclosure, on one hand, the recommendation questions and the answer result display can be provided according to the current video playing progress of the learning video, and the user is not required to actively search in a page skip mode, so that the operation is more convenient. On the other hand, the target video content used for problem recommendation in the learning video can be automatically determined, and the associated recommendation problem under the target video content is determined, so that the problem possibly appearing in the learning video content which is concerned by the user at present can be directly displayed without the need for the user to conduct thinking summary of the problem. On the other hand, for the target text content displayed under the determined target video content, the content range of the question desired by the user can be redefined according to the editing operation of the user, and the recommendation problem matched and displayed is correspondingly updated according to the redefined content range, so that the user can purposefully learn a specific content part in the video to question through simple operation; in addition, after the user selects any one of the recommended questions, the answer result of the selected recommended question can be provided for the user in time, so that the questioning of the user in a learning scene is greatly facilitated, the efficiency of solving the related questions for the user can be improved, and the learning efficiency of the user is improved.

In addition, in an implementation manner, in the video playing process, the embodiment of the disclosure can automatically display the recommended questions under the current playing progress to the user under the condition that the question recommending time is met, so that the user is guided to ask questions and display answer results, and the user can be better helped to understand related contents in the video learning process.

The foregoing objects, features and advantages of the disclosure will be more readily apparent from the following detailed description of the preferred embodiments taken in conjunction with the accompanying drawings.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for the embodiments are briefly described below, which are incorporated in and constitute a part of the specification, these drawings showing embodiments consistent with the present disclosure and together with the description serve to illustrate the technical solutions of the present disclosure. It is to be understood that the following drawings illustrate only certain embodiments of the present disclosure and are therefore not to be considered limiting of its scope, for the person of ordinary skill in the art may admit to other equally relevant drawings without inventive effort.

FIG. 1 illustrates a flow chart of a method of question interaction provided by an embodiment of the present disclosure;

FIG. 2 is a schematic diagram of a video playback page provided by an embodiment of the present disclosure;

FIG. 3 is a schematic diagram illustrating the presentation of target text content and recommended questions in an artificial intelligence question-answering window according to one embodiment of the present disclosure;

fig. 4 is a schematic diagram showing answer results corresponding to a recommendation question triggered by selection according to an embodiment of the present disclosure;

FIG. 5 illustrates a schematic diagram of a question information entry area presented in an artificial intelligence dialog window provided by an embodiment of the disclosure;

FIG. 6 is a schematic diagram of a recommendation problem presented for question information entered by a user according to an embodiment of the present disclosure;

FIG. 7 is a schematic diagram showing at least one recommendation problem corresponding to current video content when playing a learning video according to an embodiment of the present disclosure;

FIG. 8 illustrates a schematic diagram of a question interaction device provided by an embodiment of the present disclosure;

FIG. 9 illustrates a schematic diagram of a computer device provided by an embodiment of the present disclosure;

Detailed Description

For the purposes of making the objects, technical solutions and advantages of the embodiments of the present disclosure more apparent, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is apparent that the described embodiments are only some embodiments of the present disclosure, but not all embodiments. The components of the embodiments of the present disclosure, which are generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present disclosure provided in the accompanying drawings is not intended to limit the scope of the disclosure, as claimed, but is merely representative of selected embodiments of the disclosure. All other embodiments, which can be made by those skilled in the art based on the embodiments of this disclosure without making any inventive effort, are intended to be within the scope of this disclosure.

According to research, a user may have a question about learning content in the learning video in the process of playing the learning video, and in order to solve the question, the user needs to summarize the problem and search for questions according to the content in the learning video, and then can use the solution after summarizing the search results to return to continuously play the learning video for learning. In the process, on one hand, sometimes, the user uses the watched learning video to summarize the problems in an internal mode, and may take a long time to think about the summarizing problems, on the other hand, the searching question-answering path is longer, and the operation is complex. The user initiatively performs summarization and summarization, and the method is complex in operation and low in efficiency in a mode that the doubt can be solved by using different search functions.

Based on the above, the present disclosure provides a question interaction method, in the process of playing a learning video by a user, target video content for performing question recommendation can be determined according to video playing progress, and after target text content and a recommended question corresponding to the target video content are displayed, answer results corresponding to the recommended question after editing operation is performed on the recommended question are displayed to the user.

The present invention is directed to a method for manufacturing a semiconductor device, and a semiconductor device manufactured by the method.

It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.

It will be appreciated that prior to using the technical solutions disclosed in the embodiments of the present disclosure, the user should be informed and authorized of the type, usage range, usage scenario, etc. of the personal information related to the present disclosure in an appropriate manner according to the relevant legal regulations.

For the convenience of understanding the present embodiment, a detailed description will be first provided of a question interaction method disclosed in the embodiments of the present disclosure, where an execution body of the question interaction method provided in the embodiments of the present disclosure is generally a computer device with a certain computing capability. The questioning interaction method provided by the embodiment of the present disclosure is described below by taking an execution subject as a terminal device. In the embodiment of the present disclosure, the question interaction method may be specifically applied to a learning application, or applied as an auxiliary function to a video playing application capable of browsing learning videos, where these applications may exist as separate application software, an application platform, or may also exist in the form of an applet, and the embodiment of the present disclosure is not limited thereto.

Referring to fig. 1, a flowchart of a question interaction method provided by an embodiment of the disclosure is shown, where the method includes S101 to S104, where:

s101: responding to a question request initiated in the process of playing the learning video, and acquiring the video playing progress;

s102: determining target video content for problem recommendation according to the video playing progress;

s103: displaying target text content corresponding to the target video content and recommending problems;

S104: responding to the editing operation aiming at the target text content, and updating the displayed recommendation problem; and the recommendation questions are used for displaying corresponding answer results after being triggered.

For S101, a learning video will be described first. The learning video can be a recorded teaching video or a courseware video created by continuously playing courseware, etc. When the learning video is played, the learning video can be played through a video playing page. For example, referring to fig. 2, a schematic diagram of a video playing page according to an embodiment of the disclosure is shown, where a frame of video frame image during learning video playing is specifically shown in the video playing page. In addition, other controls when the user browses the video, such as a play control for adjusting the video progress, a media control for adjusting the volume, the brightness, etc., may be provided in the video play page, which is not illustrated one by one in the embodiments of the present disclosure.

In order to provide the recommendation problem matched with the learning video played in real time for the user, the video playing progress can be obtained in real time in the process of playing the learning video. For example, the video playback progress may be represented by a playback time point in the learning video. For example, when the current playing is to the 10 th minute position in the learning video, the obtained video playing progress may be represented by "10:00", for example.

In one possible case, the user may actively initiate a question and acquire the video playing progress when receiving the request to initiate the question. In order to enable the user to actively initiate the question, referring to fig. 2, a question button is specifically shown in the video playing page, and the question button is specifically marked by "unintelligible" text information. In addition, an artificial intelligence logo, specifically identified by a avatar, is also shown in fig. 2. In the process of playing the learning video, the learning video and the learning video can be displayed simultaneously, and one of the learning video and the learning video can be displayed. And responding to the triggering operation of the questioning button or the artificial intelligence identifier, the user can be considered to actively initiate questioning and acquire the current video playing progress of the learning video.

Here, the question button is specifically used for asking questions of the current video content, that is, questions under learning intention; and after the artificial intelligence identification is triggered, a question of non-learning intention can be specifically made, and the following description of the embodiment can be specifically referred to. In addition, the artificial intelligent identification can be continuously displayed in a display page of the learning video; for the question button, there is no need for continuous presentation, such as presentation only when there are recommended questions in the current learning video segment.

For the above S102, according to the video playing progress obtained in the above step, the target video content for problem recommendation may be first determined. Here, since the acquired video playing progress specifically indicates a point in time, at which the portion corresponding to the complete semantic information in the learning video should be a video segment.

Therefore, in a possible case, when determining the target video content for problem recommendation according to the video playing progress, the video content located in the preset time range before and after the video playing progress can be used as the target video content according to the video playing progress. For example, when the target video content is acquired, a video of 1 minute before the video playing progress and 30 seconds after the video playing progress is taken as the target video content for making a problem recommendation. Following the above example, upon determining that the video playback progress is "10:00", the time period to which the determined target video content belongs may then be determined to be 9:00-10:30. In this way, the manner of acquiring the target video content by the video playing progress is simpler, and since the target video content can be determined quickly, the recommendation problem corresponding to the target video content can be determined quickly in response.

In another possible scenario, since the learning content is usually described in segments in the learning video in a stepwise manner, for example, a certain conceptual knowledge is first described, and then problems are described. Thus, at a certain video playing schedule, there will be a complete piece of content in the learning video, such as being in the process of explaining the title. Therefore, in order to enable the acquired target video content to be a video segment with complete semantics, a target title or a target knowledge point which is currently learned according to the video playing progress can be selected, and the video content associated with the target title or the target knowledge point is used as the target video content.

Taking the above example as an example, if it is determined that the video playing progress is 10:00 in the learning video and it is determined that the x-th title is being explained at the video playing progress, the target title is determined as the x-th title, and then the complete video segment for explaining the title, such as the process of explaining the title from 9:30 to 10:30, is determined as the target video content in the learning video. In another possible example case, if the video content of the current video playing progress indicator is not a topic explanation, but an explanation of a knowledge point, the target video content may be intercepted from the learning video in a similar manner.

For S103, for the determined target video content, in the embodiment of the present disclosure, the corresponding target text content and the recommendation problem are specifically selected and displayed. The displayed target text content is used for prompting the user to select specific content in the learning video, the selected content is specifically used for determining a recommendation problem, and the determined recommendation problem can assist the user in asking questions of the target video content.

A specific manner of determining the target text content and recommending the problem is described below.

First, a specific manner of determining target text content from target video content will be described. For a user, when selecting a video segment corresponding to a target video content, there are two possible situations, namely, a question is given to an explanation part under the target video content, for example, a question given to a teacher aiming at a target knowledge point or an analysis content given to a target topic; but rather, the content presented under the target video content, such as the formula derivation process presented in courseware in the learning video. Both of these situations may also occur simultaneously.

Therefore, in determining the target text content, it is specifically possible to refer to the two possible cases described above, extract the first text content from the target video content, and convert the audio content of the target video content into the second text content. Here, the first text content extracted from the target video content includes the content in the displayed courseware described above, and the second text content obtained by means of audio conversion includes the text result of the speech conversion of the teacher in the lecture described above. And integrating the first text content and the second text content to obtain target text content.

Next, a specific manner of determining a recommendation problem according to the target video content will be described. In the embodiment of the disclosure, for the selected target video content, the corresponding target text content may be first determined according to the above manner, and then the recommendation problem may be determined according to the target text content.

Specifically, candidate questions with the correlation degree between the candidate questions and the target text content meeting a preset condition can be selected from a learning question library; and selecting the at least one recommended problem from the candidate problems according to the authorized acquired user learning data and/or the historical consumption data corresponding to the candidate problems.

Here, various candidate recommended questions are collected and collated in advance in the learning question library, and these candidate recommended questions may include some questions provided by teaching users who provide target learning materials, question questions of other learning users who are collated and the like. Candidate questions in the learning problem library may be updated in real-time, such as by supplementary recording of questions sent by the user in real-time in the learning problem library.

In one possible case, when the candidate questions meeting the preset conditions are determined through the relevance, the candidate questions can be determined through semantic relevance, such as determining the semantic relevance between the candidate questions and the target text content; alternatively, the relevance may be expressed in the candidate question, and it may be considered that the more keywords in the target text content included in the candidate question, the higher the relevance, the more suitable it is to be selected as the recommendation question.

In another possible case, this correlation can also be embodied in the matching relationship. For example, when the problem is stored in the learning problem library, the problem may be stored specifically by a tag determined under the content of the target text, for example, by a knowledge point or the like. Therefore, in the case of determining the target text content, at least one candidate question which is determined to match the target knowledge point information can be selected from the learning question library according to the target knowledge point information corresponding to the target text content.

For the determined candidate questions, the at least one recommended question may be specifically selected from the candidate questions according to authorized acquired user learning data and/or historical consumption data corresponding to each candidate question.

Here, since there may be more candidate questions, if all the candidate questions are selected to be displayed, the display information redundancy will occur. Thus, for the candidate questions obtained, a screening may be specifically performed to select at least one recommended question therefrom. When selecting the recommended questions, the authorized user learning data and/or the historical consumption data corresponding to each candidate question may be referred to. Here, the authorized acquired user learning data may specifically include learning progress of the user, feedback of historical recommended questions, browsing duration of the current learning page, and the like, where the learning data may reflect the level capability of the user, so that recommended questions that conform to the actual level capability of the user learning may be screened out of candidate questions. For example, when it is determined that the user's horizontal ability is low according to the user learning data, the recommendation problem is correspondingly selected to have simpler and easier logic or to explain more basic knowledge points.

The historical consumption data corresponding to the candidate problem may specifically include click rate corresponding to the candidate problem, recommendation conditions of different users for the candidate problem, and the like, and these consumption data may reflect attributes of the candidate problem, such as whether the candidate problem is a problem that needs to be solved in learning, or whether the candidate problem is a problem that a plurality of users recommend learning. Furthermore, the recommendation degree of students on the candidate questions at different levels can be reflected, and recommendation questions more suitable for the learning level of the user can be arranged by combining the authorized acquired user learning data.

In the case that the target text content and the corresponding recommendation problem are determined first by using the target video content according to the above manner, both can be presented.

Specifically, when target text content and a recommendation problem corresponding to target video content are displayed, an artificial intelligence question-answering window can be displayed on a video playing page, and the target text content and the recommendation problem are displayed in the artificial intelligence question-answering window.

Exemplary, referring to fig. 3, a schematic diagram is provided for displaying target text content and recommending questions in an artificial intelligence question-answering window according to an embodiment of the present disclosure. The target text content is displayed above the recommendation problem, and the recommendation problem is asked by you: the text information of the' is guided and displayed, and the two recommendation problems obtained through screening are specifically displayed.

For S104, the target text content displayed in the step is in an editable state. Or displaying editing indication information in the display area of the target text content, wherein the target text content enters an editable state after the editing indication information is triggered. Illustratively, in fig. 3, the editing indication information "modification" is specifically shown, and after the editing indication information is triggered, the displayed target text content can be edited, and the editing operation includes, but is not limited to, deleting fields, adding fields, changing field order, and the like. In the modification, the modification may be selected in the area where the target text content is displayed, or another editing interface for the target text content may be evoked to perform text modification, which is not limited in the embodiment of the present disclosure.

If the editing operation of the target text content is triggered, the corresponding displayed candidate questions may also change as the target text content is updated. Specifically, in the case where the update of the target text content occurs, candidate questions having a correlation with the edited target text content satisfying the preset condition may be obtained from the learning question library, and in a similar manner to the above embodiment, the at least one recommended question is selected from among the candidate questions according to the authorized obtained user learning data and/or the historical consumption data corresponding to each of the candidate questions.

Taking the example that the editing operation includes the deletion operation as an example, for the target text content before the editing operation, in the example in fig. 3, for example, the explanation of several special equations in the logarithm is included, and the explanation of the logarithm in the actual application is included, so that the recommended questions correspondingly presented include the questions of the special equations and the questions of the actual application of the logarithm. If the content portion corresponding to the explanation of the logarithm in the actual application is deleted in the deletion operation, the content related to the actual application does not exist in the updated target text content, and the determined candidate questions and the recommendation questions obtained by screening will not be shown in fig. 3, "what is the conclusion in the actual application? ".

Selecting such editing of the target text content and determining a recommendation problem for the edited target text content may facilitate the user to further limit the range of desired questions from the identified target text content. Specifically, the original target text content is directly displayed to the user, so that the operation difficulty of the user for organizing language repeated video content by himself can be reduced, the correspondingly displayed recommendation problem can help the user to roughly know the problem which can be learned under the target text content, and the editing function is provided, so that the user can select part of the content which is required to be asked from the target text content in a targeted manner, and the learning efficiency is improved.

The recommendation questions corresponding to the target text content described in the above embodiment, or the recommendation questions displayed after editing the target text content, may be specifically used to display corresponding answer results after being triggered.

Exemplary, referring to fig. 4, a schematic diagram showing answer results corresponding to a recommendation question triggered by selection is provided in an embodiment of the present disclosure. For the plurality of recommended questions presented under the corresponding example of fig. 3, if the user selects the second "what the conclusions have in practical application", the second recommended question is presented on the right side of the artificial intelligence question-answering window in a manner that the user sends the recommended question, and the corresponding answer result is presented on the left side of the artificial intelligence question-answering window in a manner that the user replies.

In another possible case, for the displayed target text content, the displayed text information can also be used as a reference, so that the user can ask questions by looking at the text information.

In a specific implementation, a question information input area is further arranged in the artificial intelligence question and answer window, specifically, the question information input in the input area can be received and displayed in response to a trigger operation for the question information input area, and the target text content can be displayed in the adjacent position of the input area.

Exemplary, referring to fig. 5, a schematic diagram of a question information input area shown in an artificial intelligence dialog window is provided according to an embodiment of the disclosure. For users, the content in the target text displayed in the artificial intelligence question-answering window can be referred to, the question questions to be asked are determined by themselves, the question information is input in the question information input area through the modes of text, voice input and the like, and the question is asked by triggering a 'send' button.

For the question information input by the user, if the question intention corresponding to the question information is a learning intention, a recommended question matched with the question information is selected from a learning question library and displayed.

Here, for the question information input by the user, the matched recommended questions are selected from the learning question library, so that answer information related to the recommended questions in the learning question library can be displayed quickly, and the efficiency is higher; and the recommended questions stored in the learning question library can be generally regarded as standard questions, namely questions which are more rigorous in terms of expression and are easier to understand, and are therefore preferably displayed, so that a user can determine whether the recommended questions are questions which the user intends to ask.

Exemplary, referring to fig. 6, a schematic diagram of a recommended problem is shown for question information input by a user according to an embodiment of the disclosure. For the question information input by the user in fig. 5 how to get this conclusion, how to derive log_a (1) =0, the relevant presentation will be made above the question information input area. The above embodiment can easily determine that the recommended questions have more definite question purposes and more strict terms than the question information originally input by the user, and is helpful for the user to judge whether the question information accords with the question intention of the user.

In another possible scenario, the question information entered by the user may also indicate a non-learning intent, or there are no recommended questions in the learning question bank that match the question information. For example, merely asking if there are other revisable videos, or for other subject questions associated with knowledge points, etc. In this case, the question answering function under the artificial intelligence function may be called, and the corresponding artificial intelligence answering result is directly generated for the question information through the artificial intelligence model, so as to provide answering information for the user.

In the above embodiment, the recommendation problem is fed back to the user specifically for the active operation of the user, and in another possible scenario, the recommendation problem may be actively shown to the user, for example, in a pop-up window or the like during the process of watching the learning video.

In specific implementation, at least one recommendation problem corresponding to the current video content can be displayed in response to reaching a problem recommendation opportunity in the process of playing the learning video; and the problem recommendation time is determined based on the video playing progress corresponding to each problem associated with the learning video, the historical consumption data of each problem and the real-time learning data of the current learning user.

Here, according to the above description, a plurality of knowledge points and video segments of the topic specification are included in the learning video, and at least one recommendation problem under each video segment can be determined. In one possible scenario, the corresponding recommendation questions may be presented as each video segment is about to end. Or, the recommendation and the question can be displayed on the similar playing time nodes by referring to the time when a plurality of users select to ask the related recommendation questions.

In addition, for each question, corresponding historical consumption data can be determined, including the number of times the question is presented, the number of times the answer corresponding to the question is selected to be checked after the question is presented, and the like. In one possible scenario, if a question is presented multiple times, but the number of choices to view the corresponding answer is small, it is indicated that the question is not suitable for being presented by recommendation, and thus does not meet the question recommendation opportunity. In another possible case, if a question is presented multiple times, the corresponding answer is also presented multiple times, which indicates that the question and the answer are required to be presented under the learning video, so that the question recommendation opportunity can be considered to be met.

In addition, the historical consumption data may also include a length of time to view the question, and/or answers to the question. In one possible case, if the viewing duration is shorter, it is indicated that the user does not actually have a consumption requirement for the question or the associated answer, for example, the user may simply touch by mistake, or the answer under the question is incomplete, for example, a specific answering step is omitted, and only the answer part is included. In this case too, it is not appropriate to recommend the problem.

The real-time learning data of the current learning user for the learning video may specifically include the number of times that the current learning user has selected to trigger the problem recommendation under the learning video displayed at this time, the grasping degree of the currently displayed knowledge point or question, the grasping degree of the difficulty level corresponding to the knowledge point or question, and so on. In one possible case, if the number of times that the current learning user has triggered the problem recommendation by itself is large, the method is not suitable for actively recommending the problem to the user, so that frequent interference is caused to normal learning of the user. According to the mastering condition of the current learning user on the related knowledge points or the related questions or the related difficulty levels, whether the current learning user possibly has question and problem solving requirements under the displayed learning video can be judged, so that whether the problem recommending time is met or not is judged.

Exemplary, referring to fig. 7, a schematic diagram showing at least one recommendation problem corresponding to a current video content when playing a learning video is provided in an embodiment of the present disclosure. In fig. 7, a question pop-up window is shown in the lower right corner of the video, in which the recommended questions are shown in question form, i.e. "why log_a (1) =0? "recommendation questions, shown as" how do you know how to prove log_a (1) =0? "and interaction with the user is achieved through two different interaction buttons.

If the user selects the trigger "know" button, it is considered that the user does not need to answer the associated recommendation questions; if the user selects the trigger "not know" button, it is indicated that the user fails to understand the associated recommended questions, and then the artificial intelligence question-answering window may be displayed and the associated recommended questions may be displayed in the manner described in the above embodiments.

According to the questioning interaction method provided by the embodiment, in the process that the user watches the learning video, the recommended problems can be actively displayed to the user, the recommended problems can be displayed in response to the operation of the user, the coverage scene is wider, and the questioning requirement of the user can be fully met. In addition, for the recommendation problem, no matter whether the recommendation problem is learning intention or not, answer information can be provided to solve the problem of user confusion, so that the user can be timely confused in the process of watching learning video.

It will be appreciated by those skilled in the art that in the above-described method of the specific embodiments, the written order of steps is not meant to imply a strict order of execution but rather should be construed according to the function and possibly inherent logic of the steps.

Based on the same inventive concept, the embodiment of the disclosure further provides a question interaction device corresponding to the question interaction method, and since the principle of solving the problem by the device in the embodiment of the disclosure is similar to that of the question interaction method in the embodiment of the disclosure, the implementation of the device can refer to the implementation of the method, and the repetition is omitted.

Referring to fig. 8, an architecture diagram of a question interaction device according to an embodiment of the disclosure is shown, where the device includes:

an obtaining module 81, configured to obtain a video playing progress in response to a question request initiated during a process of playing a learning video;

a determining module 82, configured to determine target video content for problem recommendation according to the video playing progress;

the first display module 83 is configured to display target text content and a recommendation problem corresponding to the target video content;

a second presentation module 84 for updating the presented recommendation questions in response to the editing operation for the target text content; and the recommendation questions are used for displaying corresponding answer results after being triggered.

In an alternative embodiment, the determining module 82 is configured to, when determining the target video content for problem recommendation according to the video playing progress: according to the video playing progress, taking the video content in a preset time range before and after the video playing progress as the target video content; or determining a currently learned target title or target knowledge point according to the video playing progress, and taking video content associated with the target title or target knowledge point as the target video content.

In an alternative embodiment, the apparatus further comprises a processing module 85 for: in response to reaching a problem recommendation opportunity in the process of playing the learning video, displaying at least one recommendation problem corresponding to the current video content; and the problem recommendation time is determined based on the video playing progress corresponding to each problem associated with the learning video, the historical consumption data of each problem and the real-time learning data of the current learning user.

In an alternative embodiment, when the first display module 83 displays the target text content and the recommendation problem corresponding to the target video content, the first display module is configured to: displaying an artificial intelligence question-answering window in a video playing page, and displaying the target text content and the recommendation problem in the artificial intelligence question-answering window; and the target text content is in an editable state, or the display area of the target text content displays editing indication information, and the target text content enters the editable state after the editing indication information is triggered.

In an alternative embodiment, the artificial intelligence question-answering window displays a question information input area; the first display module 83 is further configured to: and responding to the triggering operation of the questioning information input area, receiving and displaying the questioning information input in the input area, and displaying the target text content at the adjacent position of the input area.

In an alternative embodiment, the first display module 83 is further configured to, after displaying the target text content corresponding to the target video content: receiving questioning information input by a user; under the condition that the questioning intention corresponding to the questioning information is the learning intention, selecting and displaying a recommended question matched with the questioning information from a learning question library; and when the questioning intention corresponding to the questioning information is a non-learning intention or no recommended questions matched with the questioning information exist in the learning question library, displaying an artificial intelligent answer result corresponding to the questioning information.

The process flow of each module in the apparatus and the interaction flow between the modules may be described with reference to the related descriptions in the above method embodiments, which are not described in detail herein.

The embodiment of the disclosure further provides a computer device, as shown in fig. 9, which is a schematic structural diagram of the computer device provided by the embodiment of the disclosure, including:

a processor 10 and a memory 20; the memory 20 stores machine readable instructions executable by the processor 10, the processor 10 being configured to execute the machine readable instructions stored in the memory 20, the machine readable instructions when executed by the processor 10, the processor 10 performing the steps of:

responding to a question request initiated in the process of playing the learning video, and acquiring the video playing progress; determining target video content for problem recommendation according to the video playing progress; displaying target text content corresponding to the target video content and recommending problems; responding to the editing operation aiming at the target text content, and updating the displayed recommendation problem; and the recommendation questions are used for displaying corresponding answer results after being triggered.

The memory 20 includes a memory 210 and an external memory 220; the memory 210 is also referred to as an internal memory, and is used for temporarily storing operation data in the processor 10 and data exchanged with the external memory 220 such as a hard disk, and the processor 10 exchanges data with the external memory 220 via the memory 210.

The specific execution process of the above instruction may refer to the steps of the question interaction method described in the embodiments of the present disclosure, which are not described herein.

The disclosed embodiments also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the question interaction method described in the method embodiments above. Wherein the storage medium may be a volatile or nonvolatile computer readable storage medium.

The embodiments of the present disclosure further provide a computer program product, where the computer program product carries program code, where instructions included in the program code may be used to perform the steps of the question interaction method described in the foregoing method embodiments, and specifically reference may be made to the foregoing method embodiments, which are not described herein in detail.

Wherein the above-mentioned computer program product may be realized in particular by means of hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied as a computer storage medium, and in another alternative embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK), or the like.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described system and apparatus may refer to corresponding procedures in the foregoing method embodiments, which are not described herein again. In the several embodiments provided in the present disclosure, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and there may be other manners of division in actual implementation, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present disclosure may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer readable storage medium executable by a processor. Based on such understanding, the technical solution of the present disclosure may be embodied in essence or a part contributing to the prior art or a part of the technical solution, or in the form of a software product stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiments of the present disclosure. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

Finally, it should be noted that: the foregoing examples are merely specific embodiments of the present disclosure, and are not intended to limit the scope of the disclosure, but the present disclosure is not limited thereto, and those skilled in the art will appreciate that while the foregoing examples are described in detail, it is not limited to the disclosure: any person skilled in the art, within the technical scope of the disclosure of the present disclosure, may modify or easily conceive changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features thereof; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the disclosure, and are intended to be included within the scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.

Claims

1. A method of question interaction, comprising:

responding to a question request initiated in the process of playing the learning video, and acquiring the video playing progress;

determining target video content for problem recommendation according to the video playing progress;

displaying target text content corresponding to the target video content and recommending problems;

responding to the editing operation aiming at the target text content, and updating the displayed recommendation problem; and the recommendation questions are used for displaying corresponding answer results after being triggered.

2. The method of claim 1, wherein determining target video content for problem recommendation based on the video playback progress comprises:

according to the video playing progress, taking the video content in a preset time range before and after the video playing progress as the target video content; or,

and determining a currently learned target title or target knowledge point according to the video playing progress, and taking video content associated with the target title or target knowledge point as the target video content.

3. The method according to claim 1 or 2, wherein the target text content is determined according to the steps of:

Extracting first text content from the target video content, and converting audio content of the target video content into second text content;

and integrating the first text content and the second text content to obtain target text content.

4. The method of claim 1, wherein the recommendation question is determined according to the steps of:

selecting candidate questions with the correlation degree between the candidate questions and the target text content or the edited target text content meeting preset conditions from a learning question library;

and selecting at least one recommended problem from the candidate problems according to the authorized acquired user learning data and/or the historical consumption data corresponding to the candidate problems.

5. The method according to claim 1, wherein the method further comprises:

in response to reaching a problem recommendation opportunity in the process of playing the learning video, displaying at least one recommendation problem corresponding to the current video content; and the problem recommendation time is determined based on the video playing progress corresponding to each problem associated with the learning video, the historical consumption data of each problem and the real-time learning data of the current learning user.

6. The method of claim 1, wherein the presenting the target text content and the recommendation question corresponding to the target video content comprises:

displaying an artificial intelligence question-answering window in a video playing page, and displaying the target text content and the recommendation problem in the artificial intelligence question-answering window;

and the target text content is in an editable state, or the display area of the target text content displays editing indication information, and the target text content enters the editable state after the editing indication information is triggered.

7. The method of claim 6, wherein the artificial intelligence question-answering window presents a question information input area;

the method further comprises the steps of:

and responding to the triggering operation of the questioning information input area, receiving and displaying the questioning information input in the input area, and displaying the target text content at the adjacent position of the input area.

8. The method of claim 1, further comprising, after presenting the target text content corresponding to the target video content:

receiving questioning information input by a user;

Under the condition that the questioning intention corresponding to the questioning information is the learning intention, selecting and displaying a recommended question matched with the questioning information from a learning question library;

and when the questioning intention corresponding to the questioning information is a non-learning intention or no recommended questions matched with the questioning information exist in the learning question library, displaying an artificial intelligent answer result corresponding to the questioning information.

9. A question interaction device, comprising:

the acquisition module is used for responding to the inquiry request initiated in the process of playing the learning video and acquiring the video playing progress;

the determining module is used for determining target video content for problem recommendation according to the video playing progress;

the first display module is used for displaying the target text content and the recommendation problem corresponding to the target video content;

the second display module is used for responding to the editing operation aiming at the target text content and updating the displayed recommendation problem; and the recommendation questions are used for displaying corresponding answer results after being triggered.

10. A computer device, comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory in communication via the bus when the computer device is running, the machine-readable instructions when executed by the processor performing the steps of the question interaction method of any of claims 1 to 8.

11. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when executed by a processor, performs the steps of the question interaction method of any of claims 1 to 8.