Information interaction method, apparatus, and computer-readable storage medium

Abstract

This disclosure relates to information interaction methods, apparatus, and computer-readable storage media, and relates to the terminal technology field. The information interaction method includes receiving a trigger operation from a user to a conversational function, displaying the interface of the conversational function in response to the trigger operation, and displaying conversational information on the interface of the conversational function corresponding to the user's actions prior to the trigger operation, the conversational information including candidate questions.

Description

[Technical Field]

[0001] [Cross - reference to Related Applications] This application claims priority based on Chinese Patent Application No. 202311127087.4 filed on September 1, 2023, and the disclosure content of the previous Chinese application is hereby incorporated into this application in its entirety.

[0002] [Technical Field] The present disclosure relates to the field of terminal technologies, and particularly to an information interaction method, apparatus, and computer - readable storage medium. [Background Art]

[0003] In related technologies, a user can ask questions through a chatbot to realize an automatic conversation function. For example, the user inputs and submits a question in an input box on the interface of the chatbot. After obtaining the question submitted by the user, the chatbot automatically generates an answer based on the question and displays the answer on the interface of the chatbot. [Summary of the Invention]

[0004] According to a first aspect of some embodiments of the present disclosure, an information interaction method is provided, and the method includes: Receiving a trigger operation for the user's conversation function; Displaying an interface of the conversation function in response to the trigger operation; Displaying conversation information corresponding to the content related to the action on the interface of the conversation function based on the user's action before the trigger operation, where the conversation information includes candidate questions.

[0005] In some embodiments, the interface for receiving the trigger operation of the conversation function and the interface corresponding to the action are the same interface.

[0006] In some embodiments, based on the user's actions prior to a trigger operation, conversational information corresponding to the actions is displayed in the conversational function interface. Using machine learning models to process information related to target behavior and generate conversational information, This includes displaying conversation information.

[0007] In some embodiments, the action includes exceeding a first threshold in the duration of viewing multimedia content.

[0008] In some embodiments, multimedia content meets the target criteria.

[0009] In some embodiments, the target condition is that the search or question data after viewing multimedia content exceeds a second threshold.

[0010] In some embodiments, post-viewing search or question data is positively correlated with the number of searches or questions conducted after viewing the multimedia content, and negatively correlated with the number of times the multimedia content was viewed.

[0011] In some embodiments, candidate questions are generated based on multimedia content.

[0012] In some embodiments, the conversation information further includes at least one of the following: descriptive text of the multimedia content generated based on the multimedia content, and answers to automatically generated questions.

[0013] In some embodiments, receiving a trigger operation for the user's conversation function is, The multimedia content playback interface includes receiving trigger operations for user conversation functions.

[0014] In some embodiments, multimedia content resides within a media stream.

[0015] In some embodiments, the action includes searching.

[0016] In some embodiments, candidate questions are generated based on the search terms used in the search.

[0017] In some embodiments, conversational information further includes at least one of multimedia content retrieved based on a search term and descriptive text generated based on the multimedia content.

[0018] In some embodiments, receiving a trigger operation for the user's conversation function is, This includes receiving trigger actions for user conversational features within the search results interface.

[0019] In some embodiments, the search results interface includes multimedia content retrieved based on the search terms, descriptive text generated based on the multimedia content, and trigger controls for conversational features.

[0020] In some embodiments, the trigger control for the conversational function includes suggested questions generated based on search terms, and based on the user's actions prior to the trigger operation, conversational information corresponding to the actions is displayed in the interface of the conversational function. The interface of the conversation function includes displaying suggested questions and their answers.

[0021] In some embodiments, based on the user's actions prior to a trigger operation, conversational information corresponding to the actions is displayed in the conversational function interface. This includes displaying first conversational information corresponding to the content of the action in the conversational function interface when the user's action prior to the trigger operation is a predetermined action.

[0022] In some embodiments, the information interaction method further includes displaying second conversation information on the interface of the conversation function when the user's behavior before the trigger operation is not a predetermined behavior, where the second conversation information includes candidate questions determined based on at least one of questions in the conversation function of other users, user attributes, and user history data.

[0023] In some embodiments, when the user uses the conversation function for the first time, the second conversation information includes first guidance information, and when the user does not use the conversation function for the first time but uses the conversation function for the first time within a predetermined time period, the second conversation information includes second guidance information different from the first guidance information.

[0024] In some embodiments, the information interaction method includes, in response to detecting information indicating the end of a conversation sent by the user on the interface of the conversation function, determining candidate questions based on questions in the conversation function of other users, and generating conversation information including the candidate questions.

[0025] In some embodiments, the information interaction method further includes displaying an answer to the selected candidate question in response to a selection operation on the candidate question of the user.

[0026] In some embodiments, the information interaction method further includes displaying an answer to the question and supplementary candidate questions generated based on the question and the answer in response to a question on the interface of the user's conversation function.

[0027] According to a second aspect of some embodiments of the present disclosure, an information display device is provided, the device comprising a memory and a processor coupled to the memory, the processor configured to perform any one of the aforementioned information interaction methods based on instructions stored in the memory.

[0028] A third aspect of some embodiments of the present disclosure provides a computer-readable storage medium in which a computer program is stored, and when the computer program is executed by a processor, one of the aforementioned information interaction methods is realized.

[0029] According to a fourth aspect of some embodiments of the present disclosure, a computer program is provided, the computer program including instructions, which, when executed by a processor, cause the processor to perform any one of the aforementioned information interaction methods.

[0030] Other features and advantages of this disclosure will become apparent by describing in detail exemplary embodiments of this disclosure with reference to the following drawings.

[0031] To more clearly illustrate the embodiments of this disclosure or the technical solutions in the prior art, the following is a brief introduction of the drawings that may be used in describing the embodiments or the prior art. Clearly, the drawings in the following description are some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these without any creative effort. [Brief explanation of the drawing]

[0032] [Figure 1] A flowchart of an information interaction method according to some embodiments of this disclosure is shown. [Figure 2A] Schematic diagrams of conversational functionality interfaces according to some embodiments of this disclosure are shown. [Figure 2B] Schematic diagrams of conversational functionality interfaces according to several other embodiments of this disclosure are shown. [Figure 2C] Schematic diagrams of conversational functionality interfaces according to several other embodiments of this disclosure are shown. [Figure 3] Schematic diagrams of search result interfaces according to some embodiments of this disclosure are shown as examples. [Figure 4] Schematic diagrams of conversational functionality interfaces according to some further embodiments of this disclosure are shown. [Figure 5] A schematic diagram of the configuration of an information interaction device according to some embodiments of this disclosure is shown. [Figure 6] Schematic diagrams of the configuration of an information interaction device according to several other embodiments of this disclosure are shown. [Figure 7] The following are schematic diagrams illustrating the configuration of an information interaction device according to several other embodiments of this disclosure. [Modes for carrying out the invention]

[0033] The technical solutions in the embodiments of this disclosure will be described clearly and completely below with reference to the drawings of the embodiments of this disclosure, but obviously the embodiments described are only a selection of embodiments of this disclosure, not all embodiments. The description of at least one exemplary embodiment below is in fact purely descriptive and does not in any way impose any limitation on this disclosure or its application or use. All other embodiments obtained by a person skilled in the art based on the embodiments of this disclosure without any creative effort are all within the scope of this disclosure.

[0034] Unless otherwise specified, the relative arrangements, numerical representations, and numerical values ​​of the components and steps described in these embodiments are not intended to limit the scope of this disclosure.

[0035] At the same time, for the sake of descriptive convenience, it should be understood that the sizes of the parts shown in the drawings are not depicted according to their actual scale.

[0036] While techniques, methods, and apparatus known to those skilled in the art may not be discussed in detail, such techniques, methods, and apparatus should be considered part of this specification where appropriate.

[0037] In all examples presented and considered herein, any specific values ​​should be interpreted as illustrative only and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0038] Furthermore, similar symbols and letters represent similar items in the drawings, so once an item is defined in one drawing, it does not need to be considered again in subsequent drawings.

[0039] Currently, chat robots still suffer from problems such as a lack of user understanding and inconvenient interaction, resulting in relatively low information interaction efficiency.

[0040] One technical challenge that the embodiments of this disclosure aim to solve is how to improve the efficiency of information interaction between a user and a chat robot.

[0041] According to the analysis, the low information interaction efficiency of chat robots is due to at least some users not understanding how to use chat robots, and users finding the operation input for questions relatively cumbersome. To at least solve the problem of low information interaction efficiency, this disclosure provides an information interaction method, apparatus, and computer-readable storage medium for improving the information interaction process of conversational functions.

[0042] In this disclosure, the conversational function is a function that can automatically generate information related to content sent by the user, and is similar to a function that allows interaction between a user and a chat robot. The interface of the conversational function may be presented in the style of a chat interface between a user and a chat robot, and the information sent by the user and the information sent by the chat robot (i.e., the information that the conversational function automatically generates) may be displayed in different ways. For example, user identifiers such as an avatar and user name may be added to the information sent by the user, and a chat robot identifier may be added to the information sent by the chat robot, or, for example, the information sent by the user and the information sent by the chat robot may be set to different background colors, or, for example, the information sent by the user may be aligned to one side of the interface, and the information sent by the chat robot may be aligned to the other side of the interface. The above layout methods in the interface are illustrative and do not limit the embodiments of this disclosure.

[0043] The conversation function may be integrated into various types of applications, such as video applications, search applications, or integrated applications that combine various functions. An entry for the conversation function may be set in one or more interfaces of the application as needed, so that when a user needs to use the conversation function, they can jump to the conversation function interface by triggering the conversation function entry.

[0044] In the embodiments of this disclosure, after a user triggers the conversation display function, the generated conversation information is automatically displayed in the interface of the conversation function. This allows the conversation function to automatically generate and display conversation information to the user based on information obtained through other channels, even without the user directly sending information within the conversation function.

[0045] To further improve the efficiency of information interaction, in embodiments of this disclosure, the displayed conversational information includes one or more candidate questions. The candidate questions are issues raised in the conversational function that the user may propose. This allows the user to select from these candidate questions, which are automatically submitted on behalf of the user, and the conversational function automatically provides an answer based on the submitted question. In some embodiments, the candidate questions may be located in an interactable control, and the user selects a candidate question by triggering the interactable control. This allows the user to interact with the conversational function through a simple selection operation if the candidate questions displayed in the conversational function interface contain what the user wants to hear. In addition to candidate questions, the conversational information may further include guidance information or other content.

[0046] Embodiments of the present disclosure provide a method for displaying conversational information based on the user's actions prior to a trigger operation. Embodiments of the information interaction method of the present disclosure are described below with reference to Figure 1. The methods of these embodiments may be performed by electronic devices, such as terminal devices including computers, mobile phones, tablets, and wearable devices.

[0047] Figure 1 shows a flowchart of an information interaction method according to some embodiments of the present disclosure. As shown in Figure 1, the information interaction method of the embodiment includes steps S102, S104, and S106.

[0048] In step S102, the system receives a trigger operation for the conversation function from the user. For example, an interactive control may be used to represent an entry for the conversation function, and the user can trigger the conversation function by triggering the entry. The trigger operation may be, for example, a click operation on the entry. Alternatively, for example, the user may invoke the conversation function by voice command, and thus the user is not limited to triggering the conversation function only in interfaces where the entry for the conversation function is located. If necessary, a person skilled in the art may use other triggering methods, which are not described here.

[0049] In step S104, the interface for the conversation function is displayed in response to the trigger operation. The interface that receives the trigger operation is different from the interface for the conversation function; that is, the user can jump from one interface to the interface for the conversation function after triggering the conversation function on that interface.

[0050] In step S106, based on the user's actions prior to the trigger operation, conversation information corresponding to the actions is displayed on the conversation function interface, where the conversation information includes candidate questions. The displayed conversation information is information sent from the conversation function to the user, for example, information sent from the chat robot to the user.

[0051] A user's actions prior to a trigger operation include, for example, watching multimedia content or performing a search. When a user performs several actions, a need for a question may already exist. This allows actions that indicate the existence of a need for a question to display conversational information corresponding to the content of that action. For example, in the case of a user watching multimedia content, the content related to the action may be the multimedia content itself, and in the case of a user's search action, the content related to the action may be the search terms.

[0052] The user's actions prior to the trigger operation may be actions relatively close to the timing of triggering the conversation function. For example, the action may be determined based on a specified number of recent user actions prior to the trigger operation, or based on user actions within a predetermined time period prior to the trigger operation.

[0053] In some embodiments, the interface that receives the trigger operation for the conversational function and the interface that corresponds to the action are the same interface. That is, the user's action occurs in the last interface before the conversational function interface is displayed. The content of the user's actions in that interface is more likely to be related to the problem the user wants to propose. For example, a user may have a question and trigger the conversational function when performing some actions in that interface. The conversational function interface can display suggested questions related to what the user is wondering about, providing the user with timely guidelines to resolve their question and improving the efficiency of information interaction.

[0054] Conversational information corresponding to content related to an action may be generated by a machine learning model that understands the content related to that action. In some embodiments, a machine learning model is used to process content related to a target action, generate conversational information, and display the conversational information. The machine learning model may be, for example, a text processing model, an image processing model, a video processing model, an audio processing model, or a comprehensive model that simultaneously possesses multiple of the above processing functions. Embodiments of this disclosure may employ one or more machine learning models as needed. The machine learning model may be pre-trained based on the type of content to be processed, the application scene, etc. For example, a pre-trained foundation model may be trained using training data of a specified type or application scene. As a result, the trained model can deeply understand content related to the target action and provide conversational information including candidate questions.

[0055] The embodiments of this disclosure can automatically generate potential questions from the user by utilizing the user's actions before triggering the conversation function to generate conversation information, including candidate questions, and displaying it in the conversation function interface, which is convenient for the user to quickly start a conversation. Therefore, the embodiments of this disclosure can improve the efficiency of information interaction.

[0056] The following describes embodiments of the information interaction of this disclosure, combining two scenarios: one in which a conversational function is triggered during the process of viewing multimedia content, and another in which a conversational function is triggered in the search results.

[0057] First, we describe an embodiment in which a conversation function is triggered during the process of viewing multimedia content. That is, conversation information is generated based on the user's actions in viewing multimedia content. Candidate questions included in the conversation information may be generated based on the multimedia content, for example, by processing the multimedia content using a machine learning model and obtaining candidate questions output by the machine learning model. The conversation information may further include at least one of the following: a descriptive text of the multimedia content generated based on the multimedia content, and answers to automatically generated questions.

[0058] For example, conversational information may include a summary of automatically generated multimedia content (i.e., descriptive text) and candidate questions, where the candidate questions are interactive controls. One example of conversational information sent to the user from the conversational function is shown in Figure 2A. In the conversational function interface 21 of Figure 2A, "Format A is a format widely used, especially in academic writing in sociology" is descriptive text about a video in Format A, and the following three candidate questions are underlined to indicate to the user that they are clickable and selectable. In this example, the conversational information further includes the guidance information "Further understanding is possible".

[0059] For example, the conversation function may automatically select a generated candidate question and display the corresponding answer and candidate question, where the candidate question is an interactive control. Another example of conversational information sent to the user from the conversation function is shown in Figure 2B. In the conversation function interface 22 of Figure 2B, "I am often asked what the A format is. The A format is proposed by... and may be used in academic writing. Its advantages are..." is an automatically generated answer to the question, "Could you tell me about the A format?". The candidate question in this example is omitted here, as please refer to the previous example.

[0060] In some embodiments, conversational information may include both descriptive text and automatically generated answers to questions. Further details are omitted here.

[0061] In some multimedia content applications, users may intentionally open the multimedia content interface in certain scenarios. For example, a user might click on a video entry, which is a video directory page. Taking a long video viewing application as an example, a user might click on a movie entry after browsing introductions to several movies on the application's homepage, triggering the movie's playback interface. At this point, it may be assumed that the user intentionally watches the movie. In such cases, in response to the user's trigger operation on the multimedia content playback page, the conversation function may directly generate conversational information based on the multimedia content.

[0062] On the other hand, in some other scenarios, each video played to the user is not necessarily a video the user has watched. For example, in a short video application, the user may switch between playback interfaces for multiple different videos pushed by the application by switching operations such as slide up or slide down. When playing a video, if the user decides they are not interested in it after only a short viewing and quickly switches to the next video, it may be assumed that the user has not watched that video. In such situations, a time-length threshold can be used to determine whether the multimedia content viewed by the user is a video that the user has a potential question about. In some embodiments, the actions used to generate dialogue information include exceeding a first threshold in the length of time spent viewing the multimedia content. Thus, when the user has viewed a certain multimedia content and reached the first threshold, that is, when the playback length of the multimedia content reaches the first threshold, further dialogue information is generated based on the user's actions in viewing the multimedia content (e.g., the multimedia content itself).

[0063] Of course, the processing methods in these two scenes are not restrictive, and a person skilled in the art may, if necessary, adopt a first threshold for viewing multimedia content in the first type of scene to determine the actions used to generate conversational information, and not limit the viewing time in the second type of scene.

[0064] In some embodiments, when the duration a user spends viewing multimedia content exceeds a duration threshold, it is determined, in combination with other information, whether or not to generate conversational information based on the content of that viewing behavior. For example, for multimedia content that meets target conditions, if the duration a user spends viewing the multimedia content exceeds a duration threshold, conversational information is generated based on that viewing behavior.

[0065] For example, the target condition is that data on searches or questions after viewing multimedia content exceeds a second threshold. A post-viewing search refers to a situation where the next action a user takes after viewing multimedia content is a search, and a post-viewing question refers to a situation where the next action a user takes after viewing multimedia content is a question (e.g., triggering a conversational function). The data on post-viewing searches or questions is determined based on the number of post-viewing searches or questions. In some embodiments, the data on post-viewing searches or questions is positively correlated with the number of searches or questions after viewing multimedia content and negatively correlated with the number of times the multimedia content has been viewed, for example, determined based on the ratio of the number of post-viewing searches or questions to the number of times it has been viewed. This allows the data on post-viewing searches or questions to reflect how users further understand the proportion of multimedia content through methods such as questions and searches after viewing the multimedia content. That is, when the amount of multimedia content viewed by a user that is likely to raise questions for the user exceeds a first threshold, conversational information is generated based on the content related to that viewing behavior.

[0066] Next, we describe an embodiment that triggers a conversational function during the search process. In some embodiments, the search results interface receives a trigger operation for the user's conversational function. The search term is related to the search behavior. That is, when a user performs a search, further conversational information may be generated based on the search term to explain that there is a question about the search term. For example, candidate questions may be generated based on the search term. A machine learning model may be used to process the search term, and candidate questions output by the machine learning model may be obtained.

[0067] In some embodiments, in addition to candidate questions, the conversational information further includes at least one of the following: multimedia content retrieved based on the search terms, and descriptive text generated based on the multimedia content. Another example of conversational information sent to the user from the conversational function is shown in Figure 2C. In the conversational function interface 23 of Figure 2C, "Format A is the document format of an academic paper in an academic journal." 1 This is generally the case in social sciences, where resource utilization is... 2 Used in fields such as sociology and education. 3 "Includes" is descriptive text generated based on the searched videos 1, 2, and 3. The interactive cards below the videos are suggested questions generated based on the search terms. Of course, additional suggested questions may be generated based on the search results in addition to the search terms.

[0068] This conversational information may be displayed directly in the search results. In some embodiments, the search results interface includes multimedia content retrieved based on a search term, descriptive text generated based on the multimedia content, and trigger controls for conversational functions. This allows the user to be provided with more multidimensional search results according to the descriptive text automatically generated based on the retrieved multimedia content. Figure 3 illustrates schematic diagrams of search results interfaces according to some embodiments of the present disclosure. As shown in Figure 3, the search results interface 30 displays the search results based on the search term "A format" in the search box 301, and the search results include a card 302, which includes descriptive text 3021, three videos 3022 most relevant to the search term, and trigger controls 3023, 3024 for conversational functions. Trigger control 3023 is used to trigger the interface shown, for example, in Figure 2C.

[0069] In some embodiments, the trigger control for the conversational function includes a suggested question generated based on a search term, for example, trigger control 3024 in Figure 3. When a user triggers the conversational function using the trigger control containing the suggested question, the conversational function interface displays the suggested question and its answer. This improves the efficiency of information interaction because the user can open the conversational function interface and ask a question in a single operation.

[0070] In some embodiments of this disclosure, depending on different conditions, when a user enters the conversation function, the conversation function may display content corresponding to those conditions.

[0071] In some embodiments, if the user's action prior to a trigger operation is a predetermined action, first conversational information corresponding to the action is displayed on the conversational function interface. Specific implementation methods for such situations should be referenced to the embodiments described above, and will not be explained here.

[0072] If the user's action prior to the trigger operation is not a predetermined action, second conversation information is displayed in the conversation function interface, where the second conversation information includes candidate questions determined based on at least one of the following: questions from other users' conversation functions, user attributes, and user history data.

[0073] In other words, if a "context" (a predetermined action) exists before the user enters the conversation function, the user may intentionally ask several questions, and in this case, conversation information may be generated based on the context. On the other hand, if no "context" exists before the user enters the conversation function, candidate questions may be generated based on at least one of the user's own information and information of other users. Other users are, for example, users whose activity level is higher than the activity threshold.

[0074] If "context" is not present, the information may be further subdivided depending on the user's usage of the conversational function. In some embodiments, when a user uses the conversational function for the first time, the second conversational information includes the first guidance information, and when a user is not using the conversational function for the first time but uses it for the first time within a specified time period (for example, within 24 hours), the second conversational information includes second guidance information that is different from the first guidance information. For example, the first guidance information may be an introduction to the conversational function, and the second guidance information may be "Welcome back." This allows for the provision of guidance information according to the user's proficiency with the conversational function, facilitating user understanding and use, and improving interaction efficiency.

[0075] Table 1 illustrates the content of conversational information displayed when entering the conversational function interface in some of the above cases. [Table 1]

[0076] Regardless of the content included or the format in which the candidate questions are displayed, the user may select any of them by triggering the interaction control for the candidate question and sending the candidate question to the conversation function. In the interaction function interface, the answer to the selected candidate question is displayed in response to the user's selection action.

[0077] Before using any of the technical examples in this disclosure, it is understood that the user should be informed in an appropriate manner, in accordance with applicable laws and regulations, about the type of personal information involved, the scope of use, and the usage scenarios, and that permission should be obtained from the user.

[0078] For example, in response to receiving a voluntary request from the user, prompt information is sent to the user to clearly prompt the user that the operation requested to be performed requires the acquisition and use of the user's personal information. This allows the user to choose whether or not to provide personal information to software or hardware such as electronic devices, application programs, servers, or storage media that perform the operation of the proposed technical method of this disclosure based on the prompt information.

[0079] As a selective but non-restrictive implementation, a method for sending prompt information to a user in response to receiving a voluntary request from the user may be, for example, a pop-up window, and the prompt information may be presented in text format within the pop-up window. Furthermore, the pop-up window may include a selection control that allows the user to choose whether to "agree" or "disagree" to providing personal information to the electronic device.

[0080] The above notice and user permission acquisition process are merely illustrative and do not limit the forms in which this disclosure may be implemented. It should be understood that other methods that comply with applicable laws and regulations may also be applicable to the implementation of this disclosure.

[0081] Figure 4 shows schematic diagrams of conversational function interfaces according to some further embodiments of the present disclosure. In Figure 4, the conversational function interface 40 displays three candidate questions 1, 2, and 3 provided by the conversational function. In response to the user selecting the interaction control 401 where candidate question 2 is located, candidate question 2 is automatically sent to the user, and the user does not need to enter the question into an input box, as shown in conversation card 402. The conversational function then further provides an answer to question 2, as shown in conversation card 402.

[0082] In some embodiments, the user conversation function interface displays the answer to a question and supplementary suggested questions generated based on the question and answer, in response to the question. These questions may be automatically submitted by the user by selecting a suggested question, or they may be questions manually entered by the user. Still referring to Figure 4, the conversation function may further display interaction controls 404 for supplementary suggested questions after providing the answer 403. This guides the user to ask further questions, efficiently resolving any further questions that arise after the user has read the answer.

[0083] In some embodiments, the conversational interface detects information sent by the user indicating the end of a conversation, determines candidate questions based on other users' questions in the conversational function, and generates conversational information including these candidate questions. For example, when a user sends content such as "thank you" or "goodbye," it can be determined that this indicates the end of a conversation, meaning the user's current question has already been resolved. In such cases, the user can be guided to continue interacting with the conversational function by being presented with several more candidate questions.

[0084] The interfaces in each of the embodiments described herein are merely schematic, and for example, the number of candidate questions may be set as needed, and the layout and style of the interface may also be set as needed, but these are not described here.

[0085] In the embodiments of this disclosure, the process of generating and responding to conversation information may be performed on a terminal that displays the interface of the conversation function, the terminal may send relevant information to a server to facilitate generation by the server, and the server may send the generated information to the terminal to facilitate display on the interface of the conversation function.

[0086] The following describes an embodiment of the information interaction device of this disclosure with reference to Figure 5.

[0087] Figure 5 shows schematic diagrams of the configuration of an information interaction device according to some embodiments of the present disclosure. As shown in Figure 5, the information interaction device 50 of the embodiment is A receiving module 510 configured to receive trigger operations for the user's conversation function, A first display module 520 is configured to display a conversational function interface in response to a trigger operation, The system includes a second display module 530 configured to display conversational information corresponding to the user's actions based on the user's actions prior to the trigger operation, wherein the conversational information includes candidate questions.

[0088] In some embodiments, the interface that receives the trigger operation for the conversation function and the interface that corresponds to the action are the same interface.

[0089] In some embodiments, the second display module 530 is further configured to use a machine learning model to process content related to target behavior, generate conversational information, and display the conversational information.

[0090] In some embodiments, the action includes exceeding a first threshold in the duration of viewing multimedia content.

[0091] In some embodiments, multimedia content meets the target criteria.

[0092] In some embodiments, the target condition is that the search or question data after viewing multimedia content exceeds a second threshold.

[0093] In some embodiments, post-viewing search or question data is positively correlated with the number of searches or questions conducted after viewing the multimedia content, and negatively correlated with the number of times the multimedia content was viewed.

[0094] In some embodiments, candidate questions are generated based on multimedia content.

[0095] In some embodiments, the conversation information further includes at least one of the following: descriptive text of the multimedia content generated based on the multimedia content, and answers to automatically generated questions.

[0096] In some embodiments, the receiving module 510 further... The multimedia content playback interface is configured to receive trigger operations for user conversation functions.

[0097] In some embodiments, multimedia content resides within a media stream.

[0098] In some embodiments, the action includes searching.

[0099] In some embodiments, candidate questions are generated based on the search terms used in the search.

[0100] In some embodiments, conversational information further includes at least one of multimedia content retrieved based on a search term and descriptive text generated based on the multimedia content.

[0101] In some embodiments, the receiving module 510 further... The search results interface is configured to receive trigger actions for user conversational features.

[0102] In some embodiments, the search results interface includes multimedia content retrieved based on the search terms, descriptive text generated based on the multimedia content, and trigger controls for conversational features.

[0103] In some embodiments, the trigger control for the conversational function includes a suggested question generated based on the search term, and a second display module 530 further... The conversation function interface is configured to display suggested questions and their answers.

[0104] In some embodiments, the second display module 530 further... The interface of the conversational function is configured to display first conversational information corresponding to the content of the action when the user's action prior to the trigger operation is a predetermined action.

[0105] In some embodiments, the information interaction device 50 is The system further includes a third display module 540 configured to display second conversation information on the conversation function interface if the user's action prior to a trigger operation is not a predetermined action, wherein the second conversation information includes candidate questions determined based on at least one of the following: questions in another user's conversation function, user attributes, and user history data.

[0106] In some embodiments, when a user uses the conversation function for the first time, the second conversation information includes the first guidance information, and when a user is not using the conversation function for the first time but uses it for the first time within a predetermined time period, the second conversation information includes second guidance information that is different from the first guidance information.

[0107] In some embodiments, the information interaction device 50 is The interface of the conversation function further includes a fourth display module 550 configured to, in response to detecting information indicating the end of a conversation sent by a user, determine candidate questions based on questions from other users in the conversation function, and generate conversation information including the candidate questions.

[0108] In some embodiments, the information interaction device 50 is The system further includes a fifth display module 560 configured to display an answer to a selected candidate question in response to a user's selection operation for a candidate question.

[0109] In some embodiments, the information interaction device 50 is The system further includes a sixth display module 570 configured to respond to questions in the user conversation interface by displaying the answer to the question and supplementary suggested questions generated based on the question and answer.

[0110] Figure 6 shows schematic diagrams of the configuration of an information interaction device according to some other embodiments of the present disclosure. As shown in Figure 6, the information interaction device 60 of the embodiment includes a memory 610 and a processor 620 coupled to the memory 610, the processor 620 being configured to execute the information interaction method of any one of the embodiments described above based on instructions stored in the memory 610.

[0111] Here, memory 610 may include, for example, system memory, a fixed non-volatile storage medium, etc. System memory stores, for example, an operating system, application programs, a boot loader, and other programs.

[0112] Figure 7 shows a schematic diagram of the configuration of an information interaction device according to some other embodiments of the present disclosure. As shown in Figure 7, the information interaction device 70 of the embodiment includes a memory 710 and a processor 720, and may further include an input / output interface 730, a network interface 740, a storage interface 750, and the like. These interfaces 730, 740, 750 and the memory 710 and processor 720 may be connected, for example, via a bus 760. Here, the input / output interface 730 provides a connection interface to input / output devices such as a display, mouse, keyboard, and touchscreen. The network interface 740 provides a connection interface to various network devices. The storage interface 750 provides a connection interface to external storage devices such as an SD card and a U memory disk.

[0113] Embodiments of the present disclosure further provide a computer-readable storage medium in which a computer program is stored, and which, when the computer program is executed by a processor, realizes one of the aforementioned information interaction methods.

[0114] Those skilled in the art will see that embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of complete hardware embodiments, complete software embodiments, or embodiments combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-available non-temporary storage media (including, but not limited to, disk memory, CD-ROM, optical memory, etc.) containing computer-available program code.

[0115] This disclosure has been described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of this disclosure. It should be understood that computer program instructions can realize each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams. By providing these computer program instructions to a processor of a general-purpose computer, a dedicated computer, an embedded processor, or other programmable data processing device, a device can be generated that realizes a function specified in one flow of a flowchart or one or more blocks of multiple flows and / or block diagrams by instructions executed by the processor of the computer or other programmable data processing device.

[0116] These computer program instructions may be stored in computer-readable memory that can guide a computer or other programmable data processing device to operate in a particular manner, thereby generating a product in which the instructions stored in the computer-readable memory generate an instruction unit that implements a function specified in one or more flows of a flowchart and / or one or more blocks of a block diagram.

[0117] These computer program instructions may be loaded into a computer or other programmable data processing device to perform a series of operational steps on the computer or other programmable device to generate processing that is implemented on the computer, thereby providing steps to implement a function specified in one or more flows of a flowchart and / or one or more blocks of a block diagram.

[0118] The foregoing are merely preferred embodiments of the Disclosure and do not limit the Disclosure. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the Disclosure should be included within the scope of the Disclosure.

Claims

1. An information interaction method, Receiving trigger actions for the user's conversation function, In response to the trigger operation, the interface of the conversation function is displayed, An information interaction method comprising displaying conversational information corresponding to the user's actions prior to the trigger operation on the interface of the conversational function, wherein the conversational information includes candidate questions.

2. The information interaction method according to claim 1, wherein the interface for receiving the trigger operation of the conversation function and the interface corresponding to the action are the same interface.

3. Displaying conversation information corresponding to the content of the user's actions prior to the trigger operation on the interface of the conversation function is: The process involves using a machine learning model to process the content related to the target behavior and generate the conversational information. The information interaction method according to claim 1 or 2, further comprising displaying the aforementioned conversation information.

4. The information interaction method according to any one of claims 1 to 3, wherein the action includes the duration of viewing multimedia content exceeding a first threshold.

5. The information interaction method according to claim 4, wherein the multimedia content conforms to the target conditions.

6. The information interaction method according to claim 5, wherein the target condition is that the search or question data after viewing the multimedia content exceeds a second threshold.

7. The information interaction method according to claim 6, wherein the post-viewing search or question data is positively correlated with the number of searches or questions after viewing the multimedia content and negatively correlated with the number of times the multimedia content has been viewed.

8. The information interaction method according to any one of claims 4 to 7, wherein the candidate questions are generated based on the multimedia content.

9. The information interaction method according to any one of claims 4 to 8, wherein the conversation information further comprises at least one of a descriptive text of the multimedia content generated based on the multimedia content and an answer to an automatically generated question.

10. Receiving the trigger operation for the conversation function of the user means that The information interaction method according to any one of claims 4 to 9, further comprising receiving the trigger operation of the user for the conversation function in the playback interface for the multimedia content.

11. The information interaction method according to any one of claims 4 to 10, wherein the multimedia content is located in a media stream.

12. The information interaction method according to any one of claims 1 to 11, wherein the action includes searching.

13. The information interaction method according to claim 12, wherein the candidate questions are generated based on the search terms of the search.

14. The information interaction method according to claim 13, wherein the conversation information further comprises at least one of multimedia content retrieved based on the search term and descriptive text generated based on the multimedia content.

15. Receiving the trigger operation for the conversation function of the user means that The information interaction method according to any one of claims 12 to 14, further comprising receiving the trigger operation of the user to the conversation function in the search results interface of the search.

16. The information interaction method according to claim 15, wherein the search results interface of the search includes multimedia content retrieved based on the search term, descriptive text generated based on the multimedia content, and a trigger control for the conversation function.

17. The trigger control of the conversation function includes candidate questions generated based on the search term, and displays conversation information corresponding to the user's actions prior to the trigger operation on the interface of the conversation function. The information interaction method according to claim 16, further comprising displaying the candidate questions and their answers on the interface of the conversation function.

18. Displaying conversation information corresponding to the content of the user's actions prior to the trigger operation on the interface of the conversation function is: The information interaction method according to any one of claims 1 to 17, further comprising displaying first conversational information corresponding to the content of the action on the interface of the conversational function when the user's action prior to the trigger operation is a predetermined action.

19. The information interaction method according to any one of claims 1 to 18, further comprising displaying second conversation information on the interface of the conversation function if the user's action prior to the trigger operation is not a predetermined action, wherein the second conversation information includes candidate questions determined based on at least one of another user's questions in the conversation function, the user's attributes, and the user's history data.

20. When the user uses the conversation function for the first time, the second conversation information includes the first guidance information. The information interaction method according to claim 19, wherein, if the user is not using the conversation function for the first time but is using the conversation function for the first time within a predetermined time period, the second conversation information includes second guidance information that is different from the first guidance information.

21. In the interface of the aforementioned conversation function, in response to detecting information indicating the end of a conversation sent by the user, candidate questions are determined based on the questions asked by other users in the aforementioned conversation function. The information interaction method according to any one of claims 1 to 20, further comprising generating conversation information including the aforementioned candidate questions.

22. The information interaction method according to any one of claims 1 to 21, further comprising displaying an answer to a selected candidate question in response to a selection operation by the user to the candidate question.

23. An information interaction method according to any one of claims 1 to 22, further comprising displaying an answer to a question and a supplementary candidate question generated based on the question and the answer, in response to a question from the user in the interface of the conversation function.

24. An information display device, Memory and An information display device comprising a processor coupled to the memory, wherein the processor is configured to execute the information interaction method according to any one of claims 1 to 23 based on instructions stored in the memory.

25. A computer-readable storage medium storing a computer program that, when executed by a processor, realizes the information interaction method described in any one of claims 1 to 23.

26. A computer program that, when executed by a processor, includes instructions causing the processor to execute the information interaction method described in any one of claims 1 to 23.

Images