A question and answer interaction method and device, computer equipment and storage medium

Abstract

This disclosure provides a question-and-answer interaction method, apparatus, computer device, and storage medium. The method includes: displaying a learning page containing target learning materials; the learning page containing at least one piece of text content; determining target text content for question recommendation in response to meeting question recommendation criteria; displaying an artificial intelligence dialogue window on the learning page based on the target text content; the artificial intelligence dialogue window containing at least one first recommended question matching the learning intent determined based on the target text content; and displaying a first answer result in the artificial intelligence dialogue window in response to a triggering operation on the target first recommended question.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and more specifically, to a question-and-answer interaction method, apparatus, computer device, and storage medium. Background Technology

[0002] When users read learning materials, they may encounter questions during the learning process, such as not understanding certain content. In such cases, to resolve these learning problems, users need to summarize the information themselves, then use search functions to ask questions, filter for answers, and only return to continue reading the learning materials after finding the solutions. Summarizing the problems can be difficult in some situations and may take a considerable amount of time. Therefore, this method is cumbersome and inefficient for users. Summary of the Invention

[0003] This disclosure provides at least one question-and-answer interaction method, apparatus, computer device, and storage medium.

[0004] In a first aspect, embodiments of this disclosure provide a question-and-answer interaction method, comprising: displaying a learning page of target learning materials; the learning page containing at least one piece of text content; in response to meeting question recommendation conditions, determining target text content for question recommendation; displaying an artificial intelligence dialogue window on the learning page based on the target text content; the artificial intelligence dialogue window containing at least one first recommended question determined based on the target text content and matching the learning intention; and displaying a first answer result in the artificial intelligence dialogue window in response to a triggering operation for the target first recommended question.

[0005] In one optional implementation, after displaying the AI ​​dialogue window, the method further includes: in response to receiving a question input by a first user in the AI ​​dialogue window, determining the question intent corresponding to the question information; if the question intent is determined to be a learning intent, selecting a second recommended question matching the question information from a learning question library, and displaying the second recommended question in the AI ​​dialogue window; the second recommended question is used to display a second answer result after being triggered.

[0006] In an optional implementation, the method further includes: if it is determined that the questioning intent is not a learning intent, or if there is no recommended question matching the questioning information in the learning question library, then displaying the AI ​​answer result corresponding to the questioning information.

[0007] In one optional implementation, satisfying the question recommendation criteria includes: receiving a question triggering operation on the learning page, wherein the question triggering operation includes: a triggering operation for an AI icon displayed on the learning page, or a selection operation for text content displayed on the learning page; or, satisfying the question recommendation criteria includes: determining the current timing for question recommendation; the timing for question recommendation is determined based on the first user's real-time learning data for the target learning material and the question consumption data corresponding to the text content displayed on the learning page.

[0008] In one optional implementation, determining the target text content in response to a selection operation on the text content displayed on the learning page includes: in response to the selection operation, determining the target segment text content triggered by the selection operation, and using the target segment text content as the target text content; or, in response to the selection operation, displaying a boundary locator; and determining the target text content based on the positioning position of the boundary locator after it has been dragged.

[0009] In one optional implementation, the at least one first recommended question is determined according to the following steps: selecting candidate questions that match the target text content from a learning question library; selecting the at least one recommended question from each of the candidate questions based on the learning data of the first user obtained with authorization, and / or the consumption data corresponding to each of the candidate questions.

[0010] In one optional implementation, selecting candidate questions that match the target text content from a learning question base includes: determining at least one target knowledge point based on the target text content; and selecting candidate questions that match the target knowledge point information from the learning question base.

[0011] Secondly, embodiments of this disclosure also provide a question-and-answer interaction device, comprising: a first display module for displaying a learning page of target learning materials; the learning page containing at least one piece of text content; a determination module for determining target text content for question recommendation in response to meeting question recommendation conditions; a second display module for displaying an artificial intelligence dialogue window on the learning page based on the target text content; the artificial intelligence dialogue window containing at least one first recommended question determined based on the target text content and matching the learning intention; and a third display module for displaying a first answer result in the artificial intelligence dialogue window in response to a triggering operation for the target first recommended question.

[0012] In one optional implementation, after displaying the AI ​​dialogue window, the second display module is further configured to: in response to receiving a question input by a first user in the AI ​​dialogue window, determine the question intent corresponding to the question information; if the question intent is determined to be a learning intent, select a second recommended question matching the question information from a learning question library, and display the second recommended question in the AI ​​dialogue window; the second recommended question is used to display a second answer result after being triggered.

[0013] In one optional implementation, the second display module is further configured to: if it is determined that the questioning intent is not a learning intent, or if there is no recommended question matching the questioning information in the learning question library, then display the artificial intelligence answer result corresponding to the questioning information.

[0014] In one optional implementation, satisfying the question recommendation criteria includes: receiving a question triggering operation on the learning page, wherein the question triggering operation includes: a triggering operation for an AI icon displayed on the learning page, or a selection operation for text content displayed on the learning page; or, satisfying the question recommendation criteria includes: determining the current timing for question recommendation; the timing for question recommendation is determined based on the first user's real-time learning data for the target learning material and the question consumption data corresponding to the text content displayed on the learning page.

[0015] In one optional implementation, in response to a selection operation on the text content displayed on the learning page, when determining the target text content, in response to the selection operation, the target segment text content triggered by the selection operation is determined, and the target segment text content is used as the target text content; or, in response to the selection operation, a boundary locator is displayed; and the target text content is determined based on the positioning position of the boundary locator after it has been dragged.

[0016] In one optional implementation, the at least one first recommended question is determined according to the following steps: selecting candidate questions that match the target text content from a learning question library; selecting the at least one recommended question from each of the candidate questions based on the learning data of the first user obtained with authorization, and / or the consumption data corresponding to each of the candidate questions.

[0017] In one optional implementation, when selecting candidate questions that match the target text content from the learning question base, at least one target knowledge point is determined based on the target text content; and candidate questions that match the target knowledge point information are selected from the learning question base.

[0018] Thirdly, embodiments of this disclosure also provide a computer device, including: a processor, a memory, and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor communicates with the memory via the bus, and when the machine-readable instructions are executed by the processor, the steps of the first aspect above, or any optional implementation of the first aspect, are performed.

[0019] Fourthly, embodiments of this disclosure also provide a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the first aspect or any optional implementation thereof.

[0020] This disclosure provides a question-and-answer interaction method, apparatus, computer device, and storage medium. When a user is reading learning materials, the system can display a learning page of the target learning materials to the user. The system can also directly determine the target text content for question recommendation and display an artificial intelligence dialogue window on the learning page. This allows the user to directly view at least one first recommended question that matches the target text content in the artificial intelligence dialogue window. For the selected target first recommended question, the corresponding first answer result can also be displayed in the artificial intelligence dialogue window.

[0021] This allows for the display of recommended questions and corresponding answers to target learning materials directly on the current learning page, eliminating the need to navigate to different pages to ask questions, thus making the process more convenient. Furthermore, in question-asking scenarios, the system automatically identifies the target text content within the learning materials for question recommendation. For this target text content, it determines at least one primary recommended question that matches the user's learning intent and displays it in the AI ​​dialogue window on the learning page. This directly shows potential questions from the user's currently focused material, without requiring the user to think about and summarize the questions. Each of these recommended questions has a corresponding answer; after the user selects any recommended question, the system promptly provides the answer, greatly facilitating question-asking in learning scenarios and improving the efficiency of resolving related problems, thereby enhancing the user's learning efficiency.

[0022] To make the above-mentioned objects, features and advantages of this disclosure more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0023] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the embodiments will be briefly described below. These drawings are incorporated in and constitute a part of this specification. They illustrate embodiments conforming to this disclosure and, together with the specification, serve to explain the technical solutions of this disclosure. It should be understood that the following drawings only show some embodiments of this disclosure and should not be considered as limiting the scope. Those skilled in the art can obtain other related drawings based on these drawings without creative effort.

[0024] Figure 1 A flowchart of a question-and-answer interaction method provided in an embodiment of this disclosure is shown;

[0025] Figure 2 A schematic diagram of a learning page provided in an embodiment of this disclosure is shown;

[0026] Figure 3 This illustration shows a schematic diagram of displaying an artificial intelligence icon on a learning page, according to an embodiment of the present disclosure.

[0027] Figure 4a This illustration shows a schematic diagram of selecting text content on a learning page according to an embodiment of the present disclosure;

[0028] Figure 4b This illustration shows another schematic diagram of selecting text content on a learning page, provided by an embodiment of this disclosure;

[0029] Figure 5a This illustration shows a schematic diagram illustrating a first recommendation problem provided by an embodiment of the present disclosure;

[0030] Figure 5b This illustration shows another schematic diagram illustrating the first recommendation problem provided by an embodiment of this disclosure;

[0031] Figure 6 This illustration shows a schematic diagram of an AI dialogue window after selecting a first recommended question, as provided in an embodiment of this disclosure.

[0032] Figure 7 This illustration shows a schematic diagram of follow-up recommended questions displayed after the first answer result is shown, provided by an embodiment of the present disclosure.

[0033] Figure 8 A schematic diagram of an artificial intelligence dialogue window provided in an embodiment of this disclosure is shown;

[0034] Figure 9 A schematic diagram of a question-and-answer interaction device provided in an embodiment of this disclosure is shown;

[0035] Figure 10A schematic diagram of a computer device provided in an embodiment of this disclosure is shown. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. The components of the embodiments of this disclosure described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this disclosure provided in the accompanying drawings is not intended to limit the scope of the claimed disclosure, but merely represents selected embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without inventive effort are within the scope of protection of this disclosure.

[0037] Research has found that when users encounter difficulties understanding content in learning materials, they need to summarize the questions about these challenging parts themselves, then search for answers to these questions online, and finally summarize the answers from the search results before returning to the learning materials. This process is problematic because, on the one hand, summarizing questions can be difficult and time-consuming; on the other hand, the search process is lengthy and cumbersome. This method of users actively summarizing and using different search functions to resolve their doubts is tedious and inefficient.

[0038] Based on this, this disclosure provides a question-and-answer interaction method. When a user is reading learning materials, the learning page of the target learning materials can be displayed to the user. The target text content for question recommendation can be determined directly on the learning page, and an artificial intelligence dialogue window can be displayed so that the user can directly view at least one first recommended question that matches the target text content in the artificial intelligence dialogue window. For the selected target first recommended question, the corresponding first answer result can also be displayed in the artificial intelligence dialogue window.

[0039] The solution adopted in this embodiment offers several advantages. First, it allows for direct question recommendations and corresponding answer displays for target learning materials on the current learning page, eliminating the need for page redirection and dedicated searching, thus enhancing convenience. Second, it automatically identifies the target text content within the learning materials for question recommendations, determines at least one first recommended question matching the user's learning intent, and displays it in the AI ​​dialogue window of the learning page. This directly presents potential questions from the user's currently viewed materials without requiring the user to think about and summarize the questions. Third, all recommended questions are matched with corresponding answer results. After the user selects any recommended question, the answer is promptly provided, greatly facilitating questioning in learning scenarios and improving the efficiency of resolving related issues, thereby enhancing the user's learning efficiency.

[0040] The deficiencies of the above solutions and the proposed solutions are the result of the inventors' practical experience and careful research. Therefore, the discovery process of the above problems and the solutions proposed in this disclosure below should be considered as the inventors' contributions to this disclosure.

[0041] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0042] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0043] To facilitate understanding of this embodiment, a question-and-answer interaction method disclosed in this disclosure will first be described in detail. The execution subject of the question-and-answer interaction method provided in this disclosure is generally a computer device with a certain computing power. The following description uses a terminal device as the execution subject to illustrate the question-and-answer interaction method provided in this disclosure. In this disclosure, the question-and-answer interaction method can be specifically applied to learning applications, or used as an auxiliary function in reading applications that allow viewing learning materials. These applications can exist as standalone application software, application platforms, or in the form of mini-programs; no limitations are made in this disclosure.

[0044] See Figure 1 The diagram shows a flowchart of a question-and-answer interaction method provided in an embodiment of this disclosure. The method includes steps S101 to S104, wherein:

[0045] S101: A learning page displaying the target learning materials; the learning page contains at least one piece of text content;

[0046] S102: In response to meeting the question recommendation criteria, determine the target text content for question recommendation;

[0047] S103: Based on the target text content, display an AI dialogue window on the learning page; the AI ​​dialogue window contains at least one first recommendation question that matches the learning intention based on the target text content;

[0048] S104: In response to the triggered operation for the target first recommended question, display the first answer result in the AI ​​dialogue window.

[0049] Regarding S101 above, the learning page is specifically used to display the target learning materials. The target learning materials can be in the form of text documents, image documents, etc. The learning page can display at least a piece of text content, such as the text content in the document directly displayed on the learning page, or related text content displayed in association with the target learning materials, such as questions related to the currently displayed answers, etc. There are no limitations here.

[0050] Taking the terminal device as the user equipment as an example, see Figure 2 The diagram shown is a schematic representation of a learning page provided in an embodiment of this disclosure. The learning page specifically displays explanations for a given topic, which can be used as the text content provided in this application.

[0051] Regarding S102 above, if the problem recommendation conditions are met, the target text content for problem recommendation can be determined.

[0052] Here, there are several criteria for meeting the recommended conditions, which will be explained one by one below.

[0053] (a) A question is triggered on the learning page.

[0054] In this context, the recommended conditions for the problem are considered met specifically when a user performs a particular action. Furthermore, the actions a user can perform can be varied; two examples are provided below:

[0055] (a1) Triggering operation for the artificial intelligence icon displayed on the learning page.

[0056] For example, see Figure 3The diagram illustrates an embodiment of this disclosure of displaying an artificial intelligence (AI) icon on a learning page. In one possible scenario, if a user has questions while viewing target learning materials, they can trigger the AI ​​icon displayed on the learning page to utilize AI functionality to answer those questions. Here, the AI ​​function can act as a "learning assistant," being activated when the user needs answers and continuously displayed as an icon on the learning page when not triggered.

[0057] (a2) Selecting text content displayed on the learning page.

[0058] For example, see Figure 4a The diagram illustrates a scenario where text content is selected on a learning page according to an embodiment of this disclosure. In one possible scenario, the user may only have questions about a portion of the target learning materials displayed on the learning page, such as questions about concepts, derivations, or answers within the target learning materials.

[0059] Therefore, in this embodiment of the disclosure, a function for selecting text content is also provided to the user. Specifically, in response to a selection operation, the target segment of text content triggered by the selection operation can be determined and used as the target text content. For example, the text content may contain pre-marked parts, such as concept explanations marked with underlines; pre-marked text content can be selected by a click-triggered operation and used as the target text content. For example, in response to a triggered operation on the aforementioned concept explanation marked with underlines, the concept explanation part can be used as the target text content; while for parts of the text content that are not pre-marked with underlines, the target segment of text content can be freely selected from the text content by long-pressing or other operations and used as the target text content. For example, in Figure 4a In the code, a long press on the line of text indicated by "③" will select that line as the target text segment. Whether a line or a paragraph is selected as the target text segment can be preset; for example, it can be identified as a line of text by default, or changed to a paragraph based on user settings. To clearly indicate that a line of text has been selected, [the code is missing here]. Figure 4a The selected text portion will be marked with an opaque background color.

[0060] In another possible scenario, the user can be provided with the ability to select a specific text range. Specifically, in response to the selection operation, a boundary locator can be displayed; the target text content is determined based on the position of the boundary locator after it has been dragged. Here, the selection operation can specifically be a long-press dash operation, after which a boundary locator will be displayed on the text content. See [link to documentation] for details. Figure 4b The diagram shown illustrates another method for selecting text content on a learning page, as provided in this embodiment of the present disclosure. In this diagram, only the process for the last two inferences in the solution section is selected. The selected content is marked with boundary locators at both ends, and the selected target text content will display an opaque background color.

[0061] Here, after receiving the user's selection of the displayed text content, it can be considered that the above scenario is met, that is, the user has questions about the selected text content, or needs to explore and explain it in more detail, so it can also be considered that the question recommendation conditions are met.

[0062] (b) Determine the timing for recommending a problem that meets the current criteria.

[0063] In this scenario, the system will proactively determine whether to recommend questions and initiate such recommendations without relying on user actions. Specifically, questions can be recommended based on the current real-time situation. For example, if many users have asked questions and viewed answers in the text content displayed on the current learning page, or if learning data obtained with user authorization indicates that the user needs more answers to challenging knowledge points, and the currently displayed learning page happens to show a challenging knowledge point, then it is appropriate to recommend a question to the user.

[0064] Therefore, in practice, the timing of question recommendation is determined based on the first user's real-time learning data regarding the target learning materials and the question consumption data corresponding to the text content displayed on the learning page. Here, the first user specifically refers to the user corresponding to the terminal device.

[0065] The following is a detailed explanation. First, regarding the question consumption data corresponding to the text content displayed on the learning page, for each displayed text content, we can first determine the question consumption data associated with it. Specifically, this includes the number of times the question associated with the text content is displayed, and the number of times the corresponding answer is selected to be viewed after the question is displayed. In one possible scenario, if a question is displayed multiple times, but the number of times the corresponding answer is selected to be viewed is low, it indicates that the question is not suitable for recommendation and therefore does not meet the timing for question recommendation. In another possible scenario, if a question is displayed multiple times, and the corresponding answer is also selected and displayed multiple times, it indicates that there is a demand for displaying the question and answer under that text content, and therefore it can be considered to meet the timing for question recommendation.

[0066] Additionally, question consumption data can also include the viewing time of questions and / or answers to those questions. In one possible scenario, a short viewing time indicates that the user does not actually have a need to consume the question or related answers; for example, it might be a mistaken click, or the answer to the question might be incomplete, omitting specific solution steps and only containing the answer portion. In this case, it is not appropriate to recommend the question.

[0067] For the first user's real-time learning data regarding the target learning materials, this can specifically include the number of times the first user has triggered question recommendations under the currently displayed target learning materials, their level of mastery of the currently displayed knowledge points, and their level of mastery of the corresponding difficulty level of those knowledge points. In one possible scenario, if the first user has already triggered question recommendations a large number of times, it is not appropriate to proactively recommend questions to the user, as this would frequently disrupt their normal learning. However, based on the first user's mastery of the relevant knowledge points and difficulty level, it can be determined whether the first user might have a need for questions and answers within the displayed text content, thus determining whether it is appropriate to recommend questions at this time.

[0068] In the above embodiments, when determining the target text content for question recommendation based on the user's selection operation, the target text content can be determined directly based on the user's selection operation, or when the timing for question recommendation is met, the displayed text content, or content related to the displayed text content (such as the entire question content, theme content, or chapter content corresponding to the displayed text content) can be directly used as the target text content.

[0069] Regarding S103 above, if the target text content for question recommendation is determined, an artificial intelligence dialogue window can be displayed on the learning page based on the target text content, so as to display at least one first recommended question that matches the learning intention determined based on the target text content in the artificial intelligence dialogue window.

[0070] Here, the learning intent indicates asking questions about the learning content. To easily distinguish the different recommended questions obtained in different embodiments, the recommended question determined in this embodiment is denoted as the first recommended question; in the embodiment below, where recommended questions are selected by the user through questioning in the AI ​​dialogue window, the obtained recommended question is denoted as the second recommended question.

[0071] Here, when the target text content can be determined, at least one first recommendation question can be determined in the following manner: select candidate questions that match the target text content from the learning question library; select the at least one recommendation question from each candidate question based on the learning data of the first user obtained with authorization, and / or the consumption data corresponding to each candidate question.

[0072] The candidate questions in the learning question bank described above can be updated in real time, for example, by adding user-submitted questions to the learning question bank. When storing questions in the learning question bank, they can be stored using tags defined under the target text content, such as by knowledge points. Therefore, given the target text content, based on the target knowledge point information corresponding to the target text content, at least one candidate question matching the target knowledge point information can be selected from the learning question bank.

[0073] Under relevant knowledge points, there may be many candidate questions. Displaying all of them would result in information redundancy. Therefore, the candidate questions can be filtered to select at least one recommended question. When selecting a recommended question, the learning data of the first user (obtained with authorization) and / or the consumption data corresponding to each candidate question can be referenced. The learning data of the first user (obtained with authorization) can specifically include the user's learning progress, feedback on historical recommended questions, and browsing time on the current learning page. This learning data reflects the user's skill level, allowing for the selection of recommended questions that match the user's actual learning ability. For example, if the user's skill level is determined to be low based on their learning data, the recommended question should have a simpler and easier-to-understand logic, or explain more basic knowledge points.

[0074] The consumption data corresponding to the candidate questions can specifically include the click-through rate of the candidate questions and the recommendation status of different users. This consumption data can reflect the attributes of the candidate questions themselves, such as whether they are necessary problems to solve in learning, or whether they are problems recommended by multiple users. Furthermore, it can also reflect the degree of recommendation of the candidate questions by students at different levels. Combined with the learning data of the first user obtained with authorization as described above, recommended questions that are more suitable for the first user's learning level can be compiled.

[0075] If at least one first recommended question is identified that matches the target text content, the first recommended question can be displayed in the AI ​​dialogue window.

[0076] In one possible scenario, if the conditions for recommending a question are met—specifically, through triggering an AI identifier or determining when the timing for recommending a question is right—the target text content for recommending the question can be identified, i.e., the text content associated with the learning page. In this case, the first recommended question can be displayed in a fixed area of ​​the learning page.

[0077] For example, regarding the text content displayed on the learning page in the above example, see... Figure 5a The diagram shown illustrates a method for displaying a first recommendation question according to an embodiment of this disclosure. Since the first recommendation question pertains to the displayed text content without specifying a particular part of the text, it can be displayed independently of the text content, instead showing the AI ​​dialogue window as a pop-up on the learning page.

[0078] exist Figure 5a The window that appears first displays several recommended questions. Specifically, based on the target text content, it displays the guiding words "For the analysis of this question, you can ask me:" and below the guiding words, it displays three different recommended questions.

[0079] In another possible scenario, if the selection of text content displayed on the learning page is specifically used to determine whether the question recommendation criteria are met, then when displaying the first recommended question, it can be displayed next to the selected text content to demonstrate the relationship between the two.

[0080] For example, with Figure 4a For example, see the corresponding implementation. Figure 5b The diagram shown is another illustration of the first recommendation problem provided by an embodiment of this disclosure, which differs from... Figure 5a The first recommended question is displayed in a fixed position on the right side of the learning page. Figure 5b The window is displayed in conjunction with the selected text content. In this case, to enable the window to be displayed in conjunction with the text, its display size usually needs to be adjusted. This results in a smaller display area, and consequently, the number of first recommended questions that can be displayed can be reduced to one or two. By displaying a "More questions" prompt, the user is encouraged to select and view more first recommended questions.

[0081] Here, for the two different scenarios of displaying the first recommended question, the displayed AI dialogue window not only shows the first recommended question, but may also include controls for the user to input question information. The method by which the user actively inputs question information will be described in detail in the following embodiments, and will not be elaborated upon here.

[0082] Regarding the above S104, for the above Figure 5a and Figure 5b The first recommended question displayed can also respond to a triggered action on the target first recommended question by showing the first answer result in the AI ​​dialogue window.

[0083] Based on the above Figure 5a For example, see the corresponding implementation. Figure 6 The diagram illustrates an AI dialogue window after selecting a target first recommended question, as provided in an embodiment of this disclosure. The selected first recommended question will be displayed as user-sent information on the right side of the AI ​​dialogue window. After setting the first recommended question as the target first recommended question, the AI ​​dialogue window will display its corresponding first matching answer.

[0084] In one possible scenario, after displaying the first answer matching the selected target primary recommended question in the AI ​​dialogue window, the user can be provided with follow-up recommended questions. These follow-up recommended questions can be determined based on the target primary recommended question and the displayed first answer, or alternatively, other primary recommended questions that were not selected as the target primary recommended question can be displayed. See also Figure 7 The diagram shown is a schematic of a follow-up question recommended after the first answer is displayed, provided by an embodiment of this disclosure. The follow-up question recommended is specifically displayed by the text information "You might also like to ask:".

[0085] In the above embodiments, the terminal device actively provides the first recommended question. According to the description of the above embodiments, the question-and-answer interaction method provided in this disclosure also specifically provides users with the function of actively asking questions. Therefore, after displaying the AI ​​dialogue window, it is also possible to determine the questioning intent corresponding to the question information received from the first user in the AI ​​dialogue window.

[0086] Here, the intention to ask a question may specifically include two types: one is a learning intention similar to that in the above embodiment, specifically asking questions about the text content being studied; the other is a non-learning intention, such as asking whether there are other available courseware.

[0087] In one scenario, if the determined question intent is a learning intent, a second recommended question matching the question information can be selected from the learning question database and displayed in the AI ​​dialogue window. This second recommended question is used to display a second answer result upon being triggered. Here, the learning question database pre-collects and organizes various candidate recommended questions. These candidate recommended questions may include questions provided by teaching users offering target learning materials, as well as collected and organized questions from other learning users.

[0088] In one possible scenario, the second recommended question can be dynamically determined based on the input question information. For example, in the example above, after entering "Why if" in the AI ​​dialogue window, the second recommended questions can be determined to include "Why if α⊥β, then m⊥n?" and "Why if m / / n, then α / / β?". When the AI ​​dialogue window is updated to "Why if α⊥β", the second recommended questions can be determined to include "Why if α⊥β, then m⊥n?" and "Why if α⊥β, then m is definitely not parallel to n?".

[0089] In another possible scenario, the user's question can only be received after the user enters the question and clicks send. In this case, the second recommended question is determined after the question is received.

[0090] For the user-inputted question, the learning question base can contain semantically similar second recommended questions. Since these second recommended questions in the learning question base are associated with matching second answer results, they are more suitable for selection, triggering, and displaying the answer result. Therefore, in this embodiment, for the received question, a matching second recommended question can be found from the learning question base based on the user's question intent, and then displayed. Similar to the scenario of displaying the first recommended question in the above embodiment, after the user selects any of the second recommended questions to trigger, the second answer result can be displayed in the artificial intelligence dialogue window.

[0091] For example, see Figure 8 The diagram shown is a schematic representation of an artificial intelligence dialogue window provided in an embodiment of this disclosure. For ease of explanation, the learning page is omitted, and only the artificial intelligence dialogue window is described. Figure 8In the AI ​​dialogue window shown in (a), the user inputs a question such as "Why do α and β intersect, and m and n may or may not intersect?". If the intention is determined to be learning, a second recommended question selected from the learning question database that matches the question is selected, for example, "Why do α and β intersect, and m and n may not intersect?". This is the same as the question intention, specifically reflected in the identical semantic content of the question. Here, the second recommended question is displayed above the text box used to receive the user's input question.

[0092] In response to the triggered action for the second recommended question, you can jump to display such as Figure 8 In the AI ​​dialogue window shown in (b), the selected second recommended question will be displayed on the right as the information sent by the user, while the corresponding second answer result will be displayed on the left.

[0093] In another possible scenario, if the intent to ask a question is not for learning purposes, then there will be no recommended questions matching the question in the learning question bank. Similarly, if the intent is for learning purposes, there will also be no recommended questions matching the question. Therefore, it's not possible to search for existing information in the learning question bank and display the stored second answer. In this case, the question-and-answer function under the artificial intelligence feature can be invoked to directly generate a corresponding AI answer for the question using an AI model, thus providing the user with a solution.

[0094] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0095] Based on the same inventive concept, this disclosure also provides a question-and-answer interaction device corresponding to the question-and-answer interaction method. Since the principle of the device in this disclosure for solving problems is similar to the question-and-answer interaction method described above in this disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0096] Reference Figure 9 The diagram shown is an architectural schematic of a question-and-answer interaction device provided in an embodiment of this disclosure. The device includes: a first display module 91, a determining module 92, a second display module 93, and a third display module 94, wherein:

[0097] The first display module 91 is used to display the learning page of the target learning materials; the learning page contains at least one piece of text content;

[0098] Module 92 is used to determine the target text content for making question recommendations in response to meeting the question recommendation conditions;

[0099] The second display module 93 is used to display an artificial intelligence dialogue window on the learning page according to the target text content; the artificial intelligence dialogue window includes at least one first recommended question that matches the learning intention based on the target text content;

[0100] The third display module 94 is used to display the first answer result in the artificial intelligence dialogue window in response to a trigger operation for the target first recommended question.

[0101] In one optional implementation, after displaying the AI ​​dialogue window, the second display module 93 is further configured to: in response to receiving a question input by a first user in the AI ​​dialogue window, determine the question intent corresponding to the question information; if the question intent is determined to be a learning intent, select a second recommended question matching the question information from a learning question library, and display the second recommended question in the AI ​​dialogue window; the second recommended question is used to display a second answer result after being triggered.

[0102] In an optional implementation, the second display module 93 is further configured to: if it is determined that the questioning intent is not a learning intent, or if there is no recommended question matching the questioning information in the learning question library, then display the artificial intelligence answer result corresponding to the questioning information.

[0103] In one optional implementation, satisfying the question recommendation criteria includes: receiving a question triggering operation on the learning page, wherein the question triggering operation includes: a triggering operation for an AI icon displayed on the learning page, or a selection operation for text content displayed on the learning page; or, satisfying the question recommendation criteria includes: determining the current timing for question recommendation; the timing for question recommendation is determined based on the first user's real-time learning data for the target learning material and the question consumption data corresponding to the text content displayed on the learning page.

[0104] In one optional implementation, in response to a selection operation on the text content displayed on the learning page, when determining the target text content, in response to the selection operation, the target segment text content triggered by the selection operation is determined, and the target segment text content is used as the target text content; or, in response to the selection operation, a boundary locator is displayed; and the target text content is determined based on the positioning position of the boundary locator after it has been dragged.

[0105] In one optional implementation, the at least one first recommended question is determined according to the following steps: selecting candidate questions that match the target text content from a learning question library; selecting the at least one recommended question from each of the candidate questions based on the learning data of the first user obtained with authorization, and / or the consumption data corresponding to each of the candidate questions.

[0106] In one optional implementation, when selecting candidate questions that match the target text content from the learning question base, at least one target knowledge point is determined based on the target text content; and candidate questions that match the target knowledge point information are selected from the learning question base.

[0107] The processing flow of each module in the device and the interaction flow between each module can be referred to the relevant descriptions in the above method embodiments, and will not be detailed here.

[0108] This disclosure also provides a computer device, such as... Figure 10 The diagram shown is a schematic representation of a computer device structure provided in an embodiment of this disclosure, including:

[0109] Processor 10 and memory 20; the memory 20 stores machine-readable instructions executable by processor 10, and processor 10 executes the machine-readable instructions stored in memory 20. When the machine-readable instructions are executed by processor 10, processor 10 performs the following steps:

[0110] A learning page displaying target learning materials is provided; the learning page contains at least one piece of text content; in response to meeting the question recommendation criteria, target text content for question recommendation is determined; based on the target text content, an artificial intelligence dialogue window is displayed on the learning page; the artificial intelligence dialogue window contains at least one first recommended question that matches the learning intent determined based on the target text content; in response to a trigger operation for the target first recommended question, a first answer result is displayed in the artificial intelligence dialogue window.

[0111] The aforementioned memory 20 includes a main memory 210 and an external memory 220; the main memory 210, also known as internal memory, is used to temporarily store the computational data in the processor 10, as well as the data exchanged with external memory 220 such as a hard disk. The processor 10 exchanges data with the external memory 220 through the main memory 210.

[0112] The specific execution process of the above instructions can be referred to the steps of the question-and-answer interaction method described in the embodiments of this disclosure, and will not be repeated here.

[0113] This disclosure also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the question-and-answer interaction method described in the above-described method embodiments. The storage medium may be a volatile or non-volatile computer-readable storage medium.

[0114] This disclosure also provides a computer program product carrying program code. The program code includes instructions that can be used to execute the steps of the question-and-answer interaction method described in the above method embodiments. For details, please refer to the above method embodiments, which will not be repeated here.

[0115] The aforementioned computer program product can be implemented through hardware, software, or a combination thereof. In one optional embodiment, the computer program product is specifically embodied in a computer storage medium; in another optional embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0116] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. In the several embodiments provided in this disclosure, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection may be through some communication interfaces; the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms.

[0117] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0118] In addition, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0119] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0120] Finally, it should be noted that the above-described embodiments are merely specific implementations of this disclosure, used to illustrate the technical solutions of this disclosure, and not to limit it. The protection scope of this disclosure is not limited thereto. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this disclosure. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this disclosure, and should all be covered within the protection scope of this disclosure. Therefore, the protection scope of this disclosure should be determined by the protection scope of the claims.

Claims

1. A question-and-answer interaction method, characterized in that, include: A learning page that displays the target learning materials; the learning page contains at least one piece of text content; In response to meeting the question recommendation criteria, the target text content in the learning page used for question recommendation is determined; Based on the target text content, an artificial intelligence dialogue window is displayed in a first area defined in the learning page; The AI ​​dialogue window contains at least one first recommendation question that matches the learning intent, determined based on the target text content; In response to a triggered action on the target's first recommended question, the first answer is displayed in the AI ​​dialogue window. The conditions for meeting the question recommendation criteria include: determining the current time when a question recommendation is appropriate; the question recommendation time is determined based on the real-time learning data of the first user for the target learning materials and the question consumption data corresponding to the text content displayed on the learning page.

2. The method according to claim 1, characterized in that, Following the display of the AI ​​dialogue window, it also includes: In response to receiving a question input by a first user in the AI ​​dialogue window, the intent of the question is determined. If the questioning intent is determined to be a learning intent, a second recommended question matching the questioning information is selected from the learning question library and displayed in the AI ​​dialogue window; the second recommended question is used to display a second answer result after being triggered.

3. The method according to claim 2, characterized in that, The method further includes: If it is determined that the intent of the question is not a learning intent, or if there is no recommended question matching the question information in the learning question database, then the AI ​​answer corresponding to the question information is displayed.

4. The method according to claim 1, characterized in that, The at least one first recommendation question is determined according to the following steps: Select candidate questions from the learning question bank that match the content of the target text; Based on the learning data of the first user obtained through authorization, and / or the consumption data corresponding to each of the candidate questions, at least one recommendation question is selected from the candidate questions.

5. The method according to claim 4, characterized in that, Candidate questions matching the target text content are selected from the learning question base, including: Based on the target text content, at least one target knowledge point is identified; Candidate questions that match the target knowledge point information are selected from the learning question bank.

6. A question-and-answer interactive device, characterized in that, include: The first display module is used to display the learning page of the target learning materials; the learning page contains at least one piece of text content; The determination module is used to determine the target text content in the learning page for recommending questions in response to meeting the question recommendation conditions; The second display module is used to display an artificial intelligence dialogue window in a first area determined in the learning page according to the target text content; The AI ​​dialogue window contains at least one first recommendation question that matches the learning intent, determined based on the target text content; The third display module is used to display the first answer result in the AI ​​dialogue window in response to a triggered operation on the target first recommended question. The conditions for meeting the question recommendation criteria include: determining the current time when a question recommendation is appropriate; the question recommendation time is determined based on the real-time learning data of the first user for the target learning materials and the question consumption data corresponding to the text content displayed on the learning page.

7. A computer device, characterized in that, include: The computer device includes a processor, a memory, and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor communicates with the memory via the bus, and the machine-readable instructions, when executed by the processor, perform the steps of the question-and-answer interaction method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the question-and-answer interaction method as described in any one of claims 1 to 5.

Images