Information display method and device, equipment, storage medium and program product

Abstract

The invention relates to the technical field of data processing, and discloses an information display method and device, equipment, a storage medium and a program product, and the method comprises the steps: displaying a target video and a comment control on a video playing interface; obtaining a predicted trigger time for the comment control and a predicted display opportunity of the target recommendation content, wherein the predicted display opportunity is obtained by predicting based on the predicted trigger time; loading the target recommendation content and comment data of a target comment area corresponding to the comment control based on the predicted triggering time; and in response to an interaction operation of the comment control, displaying comment data of the target comment area, and displaying the target recommendation content in the target comment area based on the predicted display opportunity. According to the method and the device, the problem of slow data display of the comment area caused by slow data loading of the comment area can be effectively avoided, so that the display efficiency of the comment area data of the online application is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to an information display method, device, equipment, storage medium and program product. Background Art

[0002] As the usage rate of online applications increases, more and more users will comment on the data released by online applications, and the comment area is becoming more and more important for online applications. However, due to the large amount of comment data and unstable network, the data in the comment area is often loaded slowly, resulting in slow display of the data in the comment area. Summary of the invention

[0003] In view of this, the present disclosure provides an information display method, apparatus, device, storage medium and program product to solve the problem of slow display of data in the comment area.

[0004] In a first aspect, the present disclosure provides an information display method, the method comprising:

[0005] Display the target video and comment controls on the video playback interface;

[0006] Obtaining a predicted trigger time for the comment control and a predicted display timing for target recommended content, wherein the predicted display timing is predicted based on the predicted trigger time;

[0007] Loading the target recommended content and the comment data of the target comment area corresponding to the comment control based on the predicted trigger time;

[0008] In response to the interactive operation of the comment control, the comment data of the target comment area is displayed, and the target recommended content is displayed in the target comment area based on the predicted display timing.

[0009] In a second aspect, the present disclosure provides an information display device, the device comprising:

[0010] A first display module, used to display the target video and comment controls on the video playback interface;

[0011] An information acquisition module, used to acquire a predicted trigger time for the comment control and a predicted display timing of target recommended content, wherein the predicted display timing is predicted based on the predicted trigger time;

[0012] An information loading module, used for loading the target recommended content and the comment data of the target comment area corresponding to the comment control based on the predicted trigger time;

[0013] The second display module is used to display the comment data of the target comment area in response to the interactive operation of the comment control, and to display the target recommended content in the target comment area based on the predicted display timing.

[0014] In a third aspect, the present disclosure provides an electronic device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the above-mentioned information display method by executing the computer instructions.

[0015] In a fourth aspect, the present disclosure provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the above-mentioned information display method.

[0016] In a fifth aspect, the present disclosure provides a computer program product, including computer instructions, and the computer instructions are used to enable a computer to execute the above-mentioned information display method.

[0017] The information display method provided by the disclosed embodiment obtains the predicted trigger time for the comment control on the video playback interface and the predicted display timing of the target recommended content; wherein the predicted display timing is predicted based on the predicted trigger time. And the target recommended content and the comment data of the target comment area corresponding to the comment control are loaded in advance based on the predicted trigger time. Therefore, the comment data and the target recommended content can be loaded in advance. Thus, the comment data of the target comment area can be quickly displayed in response to the interactive operation of the comment control, thereby improving the display efficiency of the data in the comment area. And the target recommended content is displayed in the target comment area based on the predicted display timing, so as to recommend the target recommended content at a time point that may be interested in the target recommended content, thereby improving the recommendation effect of the target recommended content. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the specific embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 is a flowchart of an information display method according to an embodiment of the present disclosure;

[0020] Figure 2 is a first display schematic diagram according to an embodiment of the present disclosure;

[0021] Figure 3 is a second display schematic diagram according to an embodiment of the present disclosure;

[0022] Figure 4 is a third display schematic diagram according to an embodiment of the present disclosure;

[0023] Figure 5 is a fourth display schematic diagram according to an embodiment of the present disclosure;

[0024] Figure 6 is a fifth display schematic diagram according to an embodiment of the present disclosure;

[0025] Figure 7 is a sixth display schematic diagram according to an embodiment of the present disclosure;

[0026] Figure 8 is a flowchart of a method for determining a target comment prediction model according to an embodiment of the present disclosure;

[0027] Fig. 9 is a flowchart of a method for determining a target recommendation prediction model according to an embodiment of the present disclosure;

[0028] Fig.10 is a flowchart of another information display method according to an embodiment of the present disclosure;

[0029] Fig.11 is a structural block diagram of an information display device according to an embodiment of the present disclosure;

[0030] Fig.12 is a structural block diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0032] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0033] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0034] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0035] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0036] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0037] As the usage rate of online applications increases, more and more users will comment on the data published by online applications, and the comment area is becoming more and more important for online applications. However, in the related art, the data display in the comment area of ​​online applications has the following problems: First, due to the large amount of comment data and unstable network, the data in the comment area is often loaded slowly. Second, the recommended content in some comment areas does not meet the needs and interests of users. When the number of recommended content is too large, the recommendation effect of the recommended content is not good. Third, due to the large uncertainty of the operation behavior in the comment area, it becomes more difficult to access the data in the comment area and predict the data display.

[0038] In summary, in the related art, the data in the comment area is loaded slowly, the number of recommended contents is too large and the recommended contents are irrelevant, which results in the slow display of the data in the comment area and poor recommendation effect of the recommended contents.

[0039] In view of this, according to an embodiment of the present disclosure, an information display method embodiment is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0040] In this embodiment, an information display method is provided, which can be used in a client of a business application. Figure 1 is a flow chart of an information display method according to an embodiment of the present disclosure, such as Figure 1 As shown, the process includes the following steps:

[0041] Step S101, displaying the target video and comment controls on the video playback interface.

[0042] For example, Figure 2 As shown, during the process of displaying the target video on the video playback interface, a comment control will be displayed on the video playback interface. By clicking the comment control, the target comment area corresponding to the target video can be displayed. The target comment area includes at least one comment data related to the target video.

[0043] It should be noted that the comment control corresponds to the target video.

[0044] Step S102, obtaining a predicted trigger time for the comment control and a predicted display timing of the target recommended content, wherein the predicted display timing is predicted based on the predicted trigger time.

[0045] Specifically, the service end of the business application predicts the predicted trigger time of the comment control by analyzing the interactive data of the target video content and the target comment area. The server analyzes the interactive data of the target video content and the historical recommended content in the target comment area, and predicts the predicted display timing of the target recommended content in the target comment area in combination with the predicted trigger time. For example, when the user wants to take a break while watching the target video, after finishing watching the target video, etc. Then, the server sends the predicted trigger time and predicted display timing to the corresponding client.

[0046] Specifically, the client of the business application can also predict the predicted trigger time of the comment control by analyzing the interactive data of the video content of the target video and the target comment area. The client predicts the predicted display timing of the target recommended content in the target comment area by analyzing the interactive data of the video content of the target video and the historical recommended content in the target comment area and combining the predicted trigger time.

[0047] Optionally, the predicted display timing includes at least one of a predicted display position of the target recommended content in the target comment area, a target interaction attribute to the target comment area, and a predicted display time.

[0048] Step S103, loading the target recommended content and the comment data of the target comment area corresponding to the comment control based on the predicted trigger time.

[0049] Specifically, if the current time reaches the predicted trigger time, the target recommended content and the comment data of the target comment area corresponding to the comment control are loaded to the server.

[0050] It should be noted that after loading the target recommended content and comment data, you need to wait for the interactive operation of the comment control before displaying the target recommended content and comment data. If you switch to the next video, you need to re-determine the predicted trigger time and predicted display timing to reload the target recommended content and comment data. If you switch to the next video before the predicted trigger time is reached, you do not need to load the target recommended content and comment data.

[0051] Step S104, in response to the interactive operation of the comment control, the comment data of the target comment area is displayed, and the target recommended content is displayed in the target comment area based on the predicted display timing.

[0052] It should be noted that, in step S104, the comment data and the target recommended content may be displayed alternately or simultaneously, and the display order of the comment data and the target recommended content may be adjusted according to actual conditions.

[0053] The information display method provided in this embodiment obtains the predicted trigger time for the comment control on the video playback interface and the predicted display timing of the target recommended content; wherein the predicted display timing is predicted based on the predicted trigger time. And the target recommended content and the comment data of the target comment area corresponding to the comment control are loaded in advance based on the predicted trigger time. Therefore, the comment data and the target recommended content can be loaded in advance. Thus, the comment data of the target comment area can be quickly displayed in response to the interactive operation of the comment control, thereby improving the display efficiency of the data in the comment area. And the target recommended content is displayed in the target comment area based on the predicted display timing, so as to recommend the target recommended content at a time point that may be interested in the target recommended content, so as to improve the recommendation effect of the target recommended content.

[0054] In some optional implementations, displaying the comment data of the target comment area in the above step S104 includes: obtaining a predicted display order of the comment data for the target comment area; sorting the comment data based on the predicted display order; and displaying the sorted comment data of the target comment area.

[0055] Specifically, the service application server predicts the predicted display order of the comment data in the target comment area by analyzing the video content of the target video and the interactive data in the target comment area, and sends it to the client. Alternatively, the service application client predicts the predicted display order of the comment data in the target comment area by analyzing the video content of the target video and the interactive data in the target comment area.

[0056] Specifically, when predicting the display order of comment data, the interactive data of the target comment area used includes the viewing order of each comment data in the target comment area, so as to determine the user's interest and priority for different comment data. For example, if comment data 1 is viewed first, then comment data 2 is viewed, and finally comment data 3 is viewed, then the predicted display order may be to display comment data 1, comment data 2, and comment data 3 in sequence.

[0057] The information display method provided in this embodiment sorts the comment data based on the predicted display order of the comment data for the target comment area, and displays the sorted comment data for the target comment area. Therefore, the quality and popularity of the comment data displayed in the target comment area can be improved to enhance the activity of the target comment area.

[0058] In some optional implementations, the predicted display opportunity includes the predicted display position. Then, the step S104 of displaying the target recommended content in the target comment area based on the predicted display opportunity includes: displaying the target recommended content in an area corresponding to the predicted display position in the target comment area.

[0059] Specifically, Figure 3 As shown, assuming that through the analysis of the target video content and the interactive data of the target comment area, the target recommended content has a better recommendation effect in the position between comment data 1 and comment data 2, then the predicted display position is the display area between comment data 1 and comment data 2, and the target recommended content is displayed between comment data 1 and comment data 2. In addition, if there are replies to the comment data, the predicted display position can also be set in the replies of the hot comment data. For example Figure 3 As shown, there are 3 replies to comment data 1 and comment data 2. Assuming that comment data 1 is a hot comment data, the replies to comment data 1 can be displayed by expanding the interaction of the control, and the target recommended content can be displayed in the replies.

[0060] In addition, at least one of a reply control, a share control, a like control, and a not interested control may be displayed below each comment data to reply to the comment data, share the comment data, like the comment data, or mark the comment data as not interested.

[0061] It should be noted that, in the actual display process, in response to the interactive operation on the comment control, the user may jump to the comment display interface, for example Figure 3 As shown, the comment data and target recommended content in the target comment area are displayed on the comment display interface. Figure 4 As shown, the video display interface is paged, and the video display interface is divided into a video display area and a target comment area, which respectively display the target video, comment data and target recommended content.

[0062] The information display method provided in this embodiment displays the target recommended content in the area corresponding to the predicted display position in the target comment area. Therefore, the target recommended content can be displayed at a position with a better recommendation effect in the target comment area to improve the recommendation effect and conversion rate of the target recommended content.

[0063] In some optional implementations, the predicted display timing includes a target interaction attribute for the target comment area. Then, the step S104 of displaying the target recommended content in the target comment area based on the predicted display timing includes: if the current interaction attribute for the target comment area satisfies the target interaction attribute, displaying the target recommended content in the target comment area.

[0064] Optionally, the current interaction attribute and the target interaction attribute are used to characterize the interaction operation on the target comment area, such as scrolling the target comment area or jumping to the next display page of the target comment area.

[0065] In the information display method provided in this embodiment, the interactive attribute of the target comment area can reflect the degree of interaction and participation in the target comment area. Therefore, when the current interactive attribute of the target comment area satisfies the target interactive attribute, the target recommended content is displayed, which can increase the click rate of the target recommended content and effectively improve the recommendation effect of the target recommended content.

[0066] In some optional implementations, the predicted display opportunity includes the predicted display time. Then, the step S104 of displaying the target recommended content in the target comment area based on the predicted display opportunity includes: if the interval between the predicted display time and the predicted trigger time is less than the preset duration, then based on the priority of the comment data and the target recommended content, determining the display strategy of the comment data and the target recommended content, the display strategy including the display order or the display area.

[0067] Specifically, if the interval between the predicted display time and the predicted trigger time is less than the preset time, the display order of the target recommended content and the comment data can be determined according to the comment data and the priority of the target recommended content. In addition, the display order of the target recommended content and the comment data can also be determined according to the weight of the comment data and the target recommended content. Then, the comment data and the target recommended content are displayed according to the display order.

[0068] It is understandable that if the interval between the predicted display time of the target recommended content and the predicted trigger time of the comment control is short, the display of the target recommended content may interfere with the normal browsing of the comment data. Therefore, the target recommended content and the comment data can be displayed at different times, for example, Figure 5 The comment data is displayed as shown, and combined with the interactive attributes of the target comment area (such as scrolling the target comment area), in the case of scrolling the target comment area, Figure 6. Figure 6 As shown in the figure, the target recommended content is displayed first, and then combined with the content display time, the target recommended content is displayed after the preset display time, such as Figure 5 The comment data is shown.

[0069] Furthermore, if the interval between the predicted display time and the predicted trigger time is less than the preset time, the display area of ​​the target recommended content and the comment data can be determined according to the priority of the comment data and the target recommended content. In addition, the display area of ​​the target recommended content and the comment data can be determined according to the weight of the comment data and the target recommended content. Then, the comment data and the target recommended content are displayed according to the determined display area.

[0070] Specifically, the target comment area can be divided into display areas of different sizes, and the display areas corresponding to the target recommended content and comment data can be determined according to the priority or weight. The higher the priority or the greater the weight, the larger the allocated display area.

[0071] For example, Figure 7 As shown, if the priority of the target recommended content is higher, a larger display area can be allocated for the target recommended content and a smaller display area can be allocated for the comment data, and vice versa.

[0072] In the information display method provided in this embodiment, if the interval between the predicted display time and the predicted trigger time is less than the preset time, the display order or display area of ​​the comment data and the target recommended content is determined based on the priority of the comment data and the target recommended content. Therefore, data browsing interference caused by the simultaneous display of the comment data and the target recommended content can be avoided, thereby ensuring that the display of the comment data and the recommendation effect of the target recommended content are maximized.

[0073] In some optional embodiments, the predicted trigger time is predicted based on the first video feature of the target video and the first interaction feature of the target comment area, and the predicted display timing is predicted based on the predicted trigger time, the second video feature of the target video and the second interaction feature of the historical recommended content in the target comment area.

[0074] Specifically, the first video feature includes at least one of the following data features: video ID, total video duration, video category, video release time, video viewing duration, page scrolling depth of the video display interface where the target video is located, and session duration. The session duration includes the duration of all activities for the target video. Specifically, the session duration includes at least one of the duration of playing the target video, the duration of pausing the target video, and the duration of viewing the target comment area. The first interactive feature includes at least one of the following data features: the operation ID, the number of clicks on the comment data in the target comment area, and the number of comments posted corresponding to the operation ID.

[0075] It should be noted that the operation identifier can be understood as a client identifier or a user identifier.

[0076] Specifically, the second video feature includes at least one of the data features of the video identifier, the total duration of the video, and the video category. The second interaction feature includes at least one of the feature data of the operation identifier, the viewing duration of the historical recommended content, the skip time of the historical recommended content, and the number of comments corresponding to the operation identifier.

[0077] Furthermore, the predicted display order of the comment data in the target comment area may also be obtained, and the predicted display timing is predicted based on the predicted trigger time, the predicted display order, the second video feature, and the second interaction feature.

[0078] Specifically, the predicted trigger time can be predicted based on the first video feature of the target video and the first interactive feature of the target comment area through statistical analysis or a target comment prediction model. The predicted display timing can be predicted based on the predicted trigger time, the second video feature of the target video and the second interactive feature of the historical recommended content in the target comment area through statistical analysis or a target recommendation prediction model.

[0079] The information display method provided in this embodiment predicts the trigger time based on the first video feature of the target video and the first interactive feature of the target comment area, and predicts the display timing based on the predicted trigger time, the second video feature of the target video, and the second interactive feature of the historical recommended content in the target comment area. Therefore, the trigger time of the comment control and the recommendation timing of the target recommended content can be accurately predicted by the video features of the target video and the interactive features of the target comment area, so as to reasonably load the comment data in advance and improve the efficiency of comment data display. In addition, the target recommended content is displayed at a time when it may be of interest, thereby improving the recommendation effect of the target recommended content.

[0080] In some optional embodiments, the predicted trigger time is obtained by inputting the first video feature and the first interaction feature into the target comment prediction model to predict the trigger time of the comment control; the predicted display timing is obtained by inputting the predicted trigger time, the second video feature, and the second interaction feature into the target recommendation prediction model to predict the display timing of the target recommended content.

[0081] Specifically, the target review prediction model and the target recommendation prediction model can adopt models based on deep learning algorithms such as random forest classifiers, multi-layer perceptrons, and neural networks.

[0082] Furthermore, in the target comment prediction model and the target recommendation prediction model, classification models such as logistic regression models may be used to predict the prediction trigger time or the prediction display timing.

[0083] Understandably, logistic regression is a widely used classification algorithm that predicts data as either 0 or 1, making it convenient for solving binary classification problems and easy to use and interpret.

[0084] The information display method provided in this embodiment analyzes the first video feature and the first interaction feature through the target comment prediction model to predict the predicted trigger time. Therefore, the learning ability and computing power of the prediction model can be used to improve the accuracy and efficiency of the predicted trigger time. And, the predicted trigger time, the second video feature and the second interaction feature are analyzed through the target recommendation prediction model to predict the predicted display timing. Therefore, the learning ability and computing power of the prediction model can be used to improve the accuracy and efficiency of the predicted display timing.

[0085] In some optional embodiments, such as Figure 8 As shown, the target comment prediction model is determined by:

[0086] Step S801, obtaining candidate video features of each category of the sample video, candidate interaction features of each category of the sample comment area, and the trigger time tag of the corresponding sample comment area, the sample comment area corresponds to the sample video.

[0087] Specifically, the candidate video features include at least one of the data features of video identification, total video duration, video category, video release time, video viewing duration, page scrolling depth of the video display interface where the target video is located, and session duration. Among them, each video has a unique comment area, so the video identification can be used to represent the identification of the comment area. The video viewing duration can be determined by the start time and end time of the user watching the video. The candidate interactive features include at least one of the data features of operation identification, comment identification, number of clicks on comment data in the target comment area, viewing time of comment data, operation time of comment data, viewing time of comment data, number of comments corresponding to the operation identification, viewing time of historical recommended content, skip time of historical recommended content, type of comment operation, and operation label. Among them, the comment identification is used to track specific comment behavior. The viewing time of comment data can be used to record the interaction time between the user and the comment data. The comment operation type includes viewing comment data, clicking comment data, posting comment data, liking comment data, or other operations. At the same time, it is necessary to record an operation label for each comment operation. For example, an operation label of 0 indicates that the comment data is not clicked, and an operation label of 1 indicates that the comment data is clicked. It should be noted that the operation tag of 0 may also mean that the comment data has been scrolled through. Therefore, for each comment operation, the operation tag can be used to record whether the comment data is clicked, thereby capturing richer interactive information.

[0088] Step S802: determining a first sample video feature based on the correlation between the candidate video feature and the trigger time tag, wherein the first sample video feature and the first video feature belong to the same category.

[0089] Specifically, candidate video features related to the trigger time tag are screened out from the candidate video features as the first sample video features.

[0090] Furthermore, the above step S802 includes: obtaining display order labels of sample comments in the sample comment area; and screening out candidate video features related to trigger time labels and display order labels from candidate video features as first sample video features.

[0091] It should be noted that the display order labels are determined based on the viewing order of the sample comments.

[0092] Step S803: determining a first sample interaction feature based on the correlation between the candidate interaction feature and the trigger time tag, wherein the first sample interaction feature and the first interaction feature belong to the same category.

[0093] Specifically, candidate interaction features related to the trigger time tag are screened out from the candidate interaction features as the first sample interaction features.

[0094] Furthermore, the above step S803 includes: screening out candidate interaction features related to the trigger time label and the display order label from the candidate interaction features as the first sample interaction features.

[0095] Step S804: input the first sample video feature and the first sample interaction feature into a preset comment prediction model, predict the trigger time of the sample comment area, and obtain a first prediction result.

[0096] Furthermore, the above step S804 includes: inputting the first sample video feature and the first sample interaction feature into a preset comment prediction model, predicting the triggering time of the sample comment area and the display order of the sample comments in the sample comment area, and obtaining a first prediction result. The first prediction result includes the prediction results of the triggering time of the sample comment area and the display order of the sample comments.

[0097] Step S805: based on the difference between the first prediction result and the trigger time tag, update the parameters of the preset comment prediction model to obtain a target comment prediction model.

[0098] Furthermore, the above step S805 includes: based on the difference between the first prediction result and the trigger time label and the display order label, updating the parameters of the preset comment prediction model to obtain the target comment prediction model.

[0099] Therefore, the target comment prediction model can predict the triggering time of the target comment area and the display order of the comment data to obtain a predicted display order.

[0100] The information display method provided in this embodiment determines the first sample video feature based on the correlation between the candidate video feature and the trigger time label. And, determines the first sample interaction feature based on the correlation between the candidate interaction feature and the trigger time label. The first sample video feature and the first sample interaction feature are input into the preset comment prediction model, the trigger time of the sample comment area is predicted, and the parameters of the preset comment prediction model are updated according to the difference between the prediction result and the trigger time label to obtain the target comment prediction model. Therefore, the accuracy of the target comment prediction model in predicting the trigger time can be improved.

[0101] In some optional implementations, the method for obtaining the candidate video features and the candidate interaction features in the above step S801 includes:

[0102] Step a1, obtaining the first characteristic data of the sample video and the second characteristic data of the sample comment area, the first characteristic data including the description data of the sample video and at least one of the operation data for the sample video, the second characteristic data including the description data of the sample comment area, the operation data for the sample comment area, the operation data for the sample comments in the sample comment area, and at least one of the operation data for the sample recommended content in the sample comment area.

[0103] Specifically, the description data of the sample video includes at least one of the video ID, total video duration, video category, and video release time of the sample video. The operation data for the sample video includes at least one of the video viewing duration of the sample video, the page scrolling depth of the video display interface where the sample video is located, and the session duration.

[0104] Specifically, the description data of the sample comment area includes at least one of the type of the sample comment area, the video to which the sample comment area belongs, and the label of the sample comment area. Among them, the type of the sample comment area includes at least one of the general comment area, the question and answer comment area, the voting comment area, the evaluation comment area, and the picture and text comment area. In the general comment area, comments and replies can be posted. In the question and answer comment area, there is an area for asking questions and answering. In the voting or evaluation comment area, content can be rated and voted. The picture and text comment area supports the posting of picture and text content.

[0105] Specifically, the operation data for the sample comment area includes at least one of the operation identifier, the creation time of the sample comment area, the modification time of the sample comment area, the deletion time of the sample comment area, and the activity time window of the sample comment area. Among them, the activity time window refers to the time range from the first creation of the sample comment area to the last active time. The creation time of the sample comment area is usually the time when the sample comment area or the video to which it belongs is created, which can be obtained from the video release time. The last active time is the time of the last comment, like, share and other interactions. Activity time window = [creation time of the sample comment area, last active time]. The operation data for the sample comments in the sample comment area includes at least one of the number of clicks on the sample comments, the number of comments corresponding to the operation identifier, and the modification time of the sample comments. The operation data for the sample recommended content in the sample comment area includes at least one of the viewing time of the sample recommended content and the skip time of the sample recommended content.

[0106] Step a2, performing one-hot encoding on different categories of data in the first feature data and the second feature data, respectively, to obtain candidate video features of each category and candidate interaction features of each category.

[0107] Specifically, the above step a2 includes: performing one-hot encoding and standardization processing on different categories of data in the first feature data and the second feature data, respectively, to obtain candidate video features of each category and candidate interaction features of each category.

[0108] It is worth noting that in addition to obtaining candidate video features and candidate interaction features through one-hot encoding (also known as one-hot encoding), other data processing and analysis tools can also be used to convert the first feature data and the second feature data into numerical variables so that the data format of the candidate video features and the candidate interaction features can be recognized by the prediction model based on the deep learning algorithm.

[0109] The information display method provided in this embodiment performs unique-hot encoding on different categories of data in the first feature data and the second feature data to obtain candidate video features of each category and candidate interaction features of each category. Therefore, the correctness of the subsequent comment prediction model and the recommendation prediction model can be ensured, and the accuracy of the model can be improved.

[0110] In some optional embodiments, such as Fig. 9 As shown, the target recommendation prediction model is determined by:

[0111] Step S901, obtaining the recommendation timing label of the sample recommended content in the sample comment area.

[0112] Specifically, the recommendation timing label includes at least one of a display position, an interactive attribute, and a display time of the sample recommended content.

[0113] Step S902: determining a second sample video feature based on the correlation between the candidate video feature and the recommendation timing label, wherein the second sample video feature and the second video feature belong to the same category.

[0114] Specifically, candidate video features related to the recommendation timing label are screened out from the candidate video features as the second sample video features.

[0115] Furthermore, the above step S902 includes: obtaining a recommendation effect label of the sample recommended content; and screening out candidate video features related to the recommendation timing label and the recommendation effect label from the candidate video features as the second sample video features.

[0116] Step S903: determining a second sample interaction feature based on the correlation between the candidate interaction feature and the recommendation opportunity label, wherein the second sample interaction feature and the second interaction feature belong to the same category.

[0117] Specifically, candidate interaction features related to the recommendation timing label are screened out from the candidate interaction features as the second sample interaction features.

[0118] Furthermore, the above step S903 includes: selecting candidate interaction features related to the recommendation timing label and the recommendation effect label from the candidate interaction features as second sample interaction features.

[0119] Step S904: input the second sample video feature, the second sample interaction feature and the first prediction result into a preset recommendation prediction model, predict the recommendation timing of the sample recommended content, and obtain a second prediction result.

[0120] Furthermore, the above step S904 includes: inputting the second sample video feature, the second sample interaction feature and the first prediction result into a preset recommendation prediction model, predicting the recommendation timing and recommendation effect of the sample recommended content, and obtaining a second prediction result. The second prediction result includes the prediction result of the recommendation timing and recommendation effect of the sample recommended content.

[0121] Step S905 , based on the difference between the second prediction result and the recommendation opportunity label, update the parameters of the preset recommendation prediction model to obtain a target recommendation prediction model.

[0122] Furthermore, the above step S905 includes: based on the difference between the second prediction result and the recommendation opportunity label and the recommendation effect label, updating the parameters of the preset recommendation prediction model to obtain the target recommendation prediction model.

[0123] Therefore, the target recommendation prediction model can predict the recommendation timing and recommendation effect of the target recommendation content to obtain the predicted recommendation effect.

[0124] The information display method provided in this embodiment determines the second sample video feature based on the correlation between the candidate video feature and the recommendation timing label. And, based on the correlation between the candidate interaction feature and the recommendation timing label, the second sample interaction feature is determined. Then, the second sample video feature, the second sample interaction feature and the first prediction result are input into the preset recommendation prediction model to predict the recommendation timing of the sample recommended content, and based on the difference between the predicted second prediction result and the recommendation timing label, the parameters of the preset recommendation prediction model are updated to obtain the target recommendation prediction model. Therefore, it is possible to improve the accuracy of the target recommendation prediction model in predicting the recommendation timing of the target recommended content.

[0125] In some optional implementations, the output data of the target recommendation prediction model also includes the predicted recommendation effect of the target recommended content. The predicted recommendation effect is obtained by inputting the predicted trigger time, the second video feature, and the second interaction feature into the target recommendation prediction model to predict the recommendation effect of the target recommended content. Then, the information display method of the present disclosure also includes:

[0126] Step b1: display a feedback control in an area corresponding to the target recommended content in the target comment area.

[0127] Specifically, the feedback control includes at least one of a close control, a click control, and a rating control for the target recommended content.

[0128] Step b2, in response to the interactive operation on the feedback control, obtaining the feedback effect of the target recommended content.

[0129] It should be noted that in addition to obtaining the feedback effect of the target recommended content through the interactive operation of the feedback control, the feedback effect of the target recommended content can also be obtained through at least one of the click rate, conversion rate, and dwell time on the target recommended content.

[0130] Step b3: based on the difference between the feedback effect and the target recommendation effect, update the parameters of the target recommendation prediction model.

[0131] Specifically, the client can update the parameters of the target recommendation prediction model locally based on the difference between the feedback effect and the target recommendation effect. Alternatively, the client feeds back the difference between the feedback effect and the target recommendation effect to the server so that the server updates the parameters of the target recommendation prediction model.

[0132] The information display method provided in this embodiment obtains the feedback effect of the target recommended content in response to the interactive operation on the feedback control. Then, based on the difference between the feedback effect and the target recommendation effect, the parameters of the target recommendation prediction model are updated. Therefore, the target recommendation prediction model can be improved by predicting the recommendation effect and the feedback effect, thereby improving the prediction accuracy of the target recommendation prediction model. Thus, the insertion timing of the recommended content in the comment area can be dynamically adjusted by predicting the recommendation effect and the feedback effect, thereby improving the recommendation effect of the recommended content. At the same time, it is easy to select recommended content with high expected effects to achieve a high conversion rate of the recommended content. Furthermore, while ensuring that the comment data is browsed normally, the click-through rate and recommendation effect of the recommended content are maximized.

[0133] It is worth noting that in addition to using the target comment prediction model and the target recommendation prediction model to respectively predict the predicted trigger time of the comment control and the predicted display timing of the target recommended content, the same prediction model can also be used to predict the predicted trigger time of the comment control and the predicted display timing of the target recommended content.

[0134] It is worth noting that the target comment prediction model and the target recommendation prediction model can be determined on the server side of the business application or on the client side.

[0135] It is worth noting that in the process of updating the parameters of the predictive comment prediction model and the preset recommendation prediction model, if data overfitting occurs, the model's regularization parameters, number of parameter update iterations, etc. should be appropriately adjusted.

[0136] Furthermore, the target comment prediction model can be tested using the first test set, and the prediction effect of the target comment prediction model can be evaluated based on classification performance measurement tools, such as accuracy, precision, recall, F1 score, etc., and the target comment prediction model can be continuously optimized.

[0137] Furthermore, the target recommendation prediction model can be tested using a second test set, and the prediction effect of the target recommendation prediction model can be evaluated based on classification performance measurement tools, such as accuracy, precision, recall, F1 score, etc., and the target recommendation prediction model can be continuously optimized.

[0138] As a specific application example, Fig.10 As shown, the specific process of the information display method disclosed in the present invention using the target comment prediction model and the target recommendation prediction model for prediction is as follows:

[0139] Process 1: Extract the first characteristic data and the second characteristic data related to the triggering time of the comment area and the display order of the comment data from the historical data stored in the database. At the same time, associate the first characteristic data (such as viewing time, viewing frequency) with the second characteristic data to determine the possible triggering time of the comment area and the display order of the comment data in the comment area.

[0140] Specifically, historical data includes historical behavior data, user preference data, description data of the comment area, and time series data. Among them, historical behavior data includes the number and frequency of user operations on channels, pages, and videos. User preference data includes the types of videos that users like to watch, video themes, video tags, etc. The description data of the comment area includes the type of comment area, the video to which the comment area belongs, the tags of the comment area, etc. The time series data includes the timestamps of the creation, modification, and deletion of the comment area, the timestamps of a single user from the creation of the comment area to the comment, and the activity time window of the comment area.

[0141] Process 2: Perform data cleaning and preprocessing on the first characteristic data and the second characteristic data.

[0142] Process 3: Use time series analysis technology to sort the feature data processed by process 2 by time to remove duplicate feature data.

[0143] Process 4: Extract representative feature data from the feature data processed by process 3, such as the click time, operation identifier, comment area identifier, etc. of the comment data.

[0144] Process 5: According to the timestamp of the feature data, the feature data processed by process 4 is segmented according to the time window to extract the time series features.

[0145] Process 6: Use data processing and analysis tools such as one-hot encoding to perform data conversion on the feature data processed by process 5 to convert the feature data into numerical variables that can be perceived by the deep learning algorithm, and obtain candidate video features and candidate interaction features.

[0146] Process 7. From the candidate video features and the candidate interaction features, select the first sample video features and the first interaction video features, input the first sample video features and the first interaction video features as input data into the preset comment prediction model, predict the trigger time of the sample comment area and the display order of the sample comments in the sample comment area and use the prediction results as output data, and update the parameters of the preset comment prediction model in combination with the corresponding trigger time label and display order label to train and obtain the target comment prediction model.

[0147] Process 8. From the candidate video features and the candidate interaction features, select the second sample video features and the second interaction video features, input the output data of the preset comment prediction model, the second sample video features and the second interaction video features as input data into the preset recommendation prediction model, predict the recommendation timing and recommendation effect of the sample recommendation content and use the prediction results as output data, and update the parameters of the preset recommendation prediction model in combination with the corresponding recommendation timing labels and recommendation effect labels to train and obtain the target recommendation prediction model.

[0148] Process 9: Based on the target comment prediction model, the triggering time of the comment control and the display order of the comment data in the target comment area are predicted in real time. Also, based on the target recommendation prediction model, the recommendation timing of the target recommended content and the recommendation effect of the target recommended content are predicted in real time.

[0149] Process 10: Merge the output results of the target review prediction model and the target recommendation prediction model.

[0150] It is worth noting that the information display method disclosed in the present invention predicts the trigger time of the target comment area and the display order of the comment data in the target comment area, as well as the recommendation timing and recommendation effect of the target recommended content through two independent target comment prediction models and target recommendation prediction models, so that the two models can be optimized separately to optimize the user experience and recommendation effect. Not only that, because each model focuses on a specific task, a separate model training and prediction process is carried out, and then better prediction results are provided through collaborative work in actual applications. Therefore, the user experience of the comment area and the recommendation effect of the recommended content can be greatly improved.

[0151] It is worth noting that, on the one hand, the information display method disclosed in the present invention can effectively avoid the problem of slow display of comment data caused by slow data loading and loading delay in the comment area in related technologies by accurately predicting the user's behavior and preferences in the comment area, and can greatly improve the user experience. On the other hand, the information display method disclosed in the present invention determines the display timing of recommended content in the comment area by analyzing the video features and the interactive features of the comment area. Therefore, it is possible to cleverly insert recommended content during the idle time when the user is watching the video based on factors such as the user's viewing habits and rest time, thereby improving the conversion rate of recommended content.

[0152] It should be noted that in actual model deployment, the target comment prediction model and the target recommendation prediction model can be deployed in the server of the business application through the Representational State Transfer Application Programming Interface (RESTful API) and other methods, so that the client can send a request and obtain the prediction data (such as prediction trigger time, prediction display order, prediction display timing, prediction recommendation effect) from the server. Among them, the server can store the prediction results in the database and return the prediction results to the client in a timely manner.

[0153] As a specific application example, a client of a business application is installed on a mobile phone, and the business application is used to publish and play videos. In the client, you can search and play videos of interest, and comment on the played videos. In the process of displaying the target video, the client loads the target recommended content and the comment data corresponding to the target video in advance through the information display method disclosed in the present invention. Then, the user can touch the comment control on the video playback interface to make the client display the comment data and the target recommended content.

[0154] It is worth noting that the information display method disclosed in the present invention analyzes and predicts the data in the comment area to determine the time to load the comment data in advance and the timing of the target recommended content delivery. And adopts deep learning algorithms and data mining and other technologies to improve the accuracy of the prediction of comment area data (such as the triggering time of the comment control, the display order of the comment data in the target comment area), as well as the accuracy of the target recommended content delivery, so as to improve the data loading speed of the comment area, the display efficiency of the comment data and the recommendation effect of the target recommended content. It can be seen that the information display method disclosed in the present invention can effectively improve the user experience of the comment area and the recommendation effect of the recommended content through technical means such as comment area technology, data collection and processing, deep learning algorithms, data mining, and network performance optimization.

[0155] In this embodiment, an information display device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0156] This embodiment provides an information display device, such as Fig.11 As shown, including:

[0157] The first display module 1101 is used to display the target video and comment controls on the video playback interface;

[0158] An information acquisition module 1102 is used to acquire a predicted trigger time for a comment control and a predicted display timing of a target recommended content, where the predicted display timing is predicted based on the predicted trigger time;

[0159] An information loading module 1103 is used to load the target recommended content and the comment data of the target comment area corresponding to the comment control based on the predicted trigger time;

[0160] The second display module 1104 is used to display the comment data of the target comment area in response to the interactive operation of the comment control, and display the target recommended content in the target comment area based on the predicted display timing.

[0161] In some optional implementations, the predicted display timing includes a predicted display position. Then, the second display module 1104 includes:

[0162] The first display unit is used to display target recommended content in an area corresponding to the predicted display position in the target comment area.

[0163] In some optional implementations, the predicted display timing includes the target interaction attribute of the target comment area. Then, the second display module 1104 further includes:

[0164] The second display unit is used to display target recommended content in the target comment area if the current interaction attribute of the target comment area meets the target interaction attribute.

[0165] In some optional implementations, the predicted display opportunity includes the predicted display time. Then, the second display module 1104 further includes:

[0166] The third display unit is used to determine the display strategy of the comment data and the target recommended content based on the priority of the comment data and the target recommended content if the interval between the predicted display time and the predicted trigger time is less than the preset time, and the display strategy includes the display order or the display area.

[0167] In some optional implementations, the second display module 1104 further includes:

[0168] A sequence acquisition unit, used to acquire a predicted display sequence of comment data for a target comment area;

[0169] A comment sorting unit, used to sort the comment data based on the predicted display order;

[0170] The fourth display unit is used to display the sorted comment data of the target comment area.

[0171] In some optional embodiments, the predicted trigger time in the information acquisition module 1102 is predicted based on the first video feature of the target video and the first interactive feature of the target comment area, and the predicted display timing in the information acquisition module 1102 is predicted based on the predicted trigger time, the second video feature of the target video, and the second interactive feature of the historical recommended content in the target comment area.

[0172] In some optional implementations, the predicted trigger time in the information acquisition module 1102 is obtained by inputting the first video feature and the first interaction feature into the target comment prediction model to predict the trigger time of the comment control. The predicted display timing in the information acquisition module 1102 is obtained by inputting the predicted trigger time, the second video feature and the second interaction feature into the target recommendation prediction model to predict the display timing of the target recommended content.

[0173] In some optional embodiments, the method for determining the target comment prediction model includes: obtaining candidate video features of each category of the sample video, candidate interaction features of each category of the sample comment area, and the trigger time tag of the corresponding sample comment area, the sample comment area corresponds to the sample video; based on the correlation between the candidate video features and the trigger time tag, determining the first sample video feature, the first sample video feature and the first video feature belong to the same category; based on the correlation between the candidate interaction features and the trigger time tag, determining the first sample interaction feature, the first sample interaction feature and the first interaction feature belong to the same category; inputting the first sample video feature and the first sample interaction feature into the preset comment prediction model, predicting the trigger time of the sample comment area, and obtaining a first prediction result; based on the difference between the first prediction result and the trigger time tag, updating the parameters of the preset comment prediction model to obtain the target comment prediction model.

[0174] In some optional embodiments, the method for determining the target recommendation prediction model includes: obtaining the recommendation timing label of the sample recommended content in the sample comment area; determining the second sample video feature based on the correlation between the candidate video feature and the recommendation timing label, and the second sample video feature and the second video feature belong to the same category; determining the second sample interaction feature based on the correlation between the candidate interaction feature and the recommendation timing label, and the second sample interaction feature and the second interaction feature belong to the same category; inputting the second sample video feature, the second sample interaction feature and the first prediction result into the preset recommendation prediction model, predicting the recommendation timing of the sample recommended content, and obtaining a second prediction result; based on the difference between the second prediction result and the recommendation timing label, updating the parameters of the preset recommendation prediction model to obtain the target recommendation prediction model.

[0175] In some optional embodiments, the method for obtaining candidate video features and candidate interaction features includes: obtaining first feature data of a sample video and second feature data of a sample comment area, the first feature data including description data of the sample video and at least one of operation data for the sample video, and the second feature data including description data of the sample comment area, operation data for the sample comment area, operation data for sample comments in the sample comment area, and operation data for sample recommended content in the sample comment area; performing unique-hot encoding on different categories of data in the first feature data and the second feature data, respectively, to obtain candidate video features of each category and candidate interaction features of each category.

[0176] In some optional implementations, the output data of the target recommendation prediction model also includes the predicted recommendation effect of the target recommendation content. The information display device of the present disclosure also includes:

[0177] A third display module, configured to display a feedback control in an area corresponding to the target recommended content in the target comment area;

[0178] A feedback acquisition module, used to obtain feedback effects of target recommended content in response to interactive operations on the feedback control;

[0179] The parameter updating module is used to update the parameters of the target recommendation prediction model based on the difference between the feedback effect and the target recommendation effect.

[0180] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0181] The information display device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0182] The present disclosure also provides an electronic device having the above Fig.11 The information display device shown.

[0183] See also Fig.12 , Fig.12 is a structural block diagram of an electronic device provided by an optional embodiment of the present disclosure, such as Fig.12 As shown, the electronic device includes: one or more processors 1201, memory 1202, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig.12 A processor 1201 is taken as an example.

[0184] The processor 1201 may be a central processing unit, a network processor or a combination thereof. The processor 1201 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable logic gate array, a general purpose array logic or any combination thereof.

[0185] The memory 1202 stores instructions executable by at least one processor 1201, so that the at least one processor 1201 executes the method shown in the above embodiment.

[0186] The memory 1202 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 1202 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 1202 may optionally include a memory remotely arranged relative to the processor 1201, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0187] The memory 1202 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 1202 may also include a combination of the above types of memory.

[0188] The electronic device also includes an input device 1203 and an output device 1204. The processor 1201, the memory 1202, the input device 1203 and the output device 1204 may be connected via a bus or other means. Fig.12 The example of connecting through bus is taken in the following.

[0189] The input device 1203 can receive input digital or character information, and generate key signal input related to the user settings and function control of the electronic device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator rod, one or more mouse buttons, a trackball, a joystick, etc. The output device 1204 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0190] The embodiments of the present disclosure also provide a computer-readable storage medium. The above-mentioned method according to the embodiments of the present disclosure can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium and downloaded through a network, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0191] A part of the present disclosure may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present disclosure through the operation of the computer. Those skilled in the art should understand that the existence of computer program instructions in computer-readable media includes, but is not limited to, source files, executable files, installation package files, etc., and accordingly, the way in which computer program instructions are executed by a computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to the computer.

[0192] Although the embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. An information display method, characterized in that: The method comprises: Display the target video and comment controls on the video playback interface; Obtaining a predicted trigger time for the comment control and a predicted display timing for target recommended content, wherein the predicted display timing is predicted based on the predicted trigger time; Loading the target recommended content and comment data of the target comment area corresponding to the comment control based on the predicted trigger time; In response to the interactive operation of the comment control, the comment data of the target comment area is displayed, and the target recommended content is displayed in the target comment area based on the predicted display timing.

2. The information display method according to claim 1, characterized in that: The predicted display timing includes a predicted display position, and displaying the target recommended content in the target comment area based on the predicted display timing includes: The target recommended content is displayed in an area corresponding to the predicted display position in the target comment area.

3. The information display method according to claim 1, characterized in that: The predicted display timing includes a target interactive attribute of the target comment area, and displaying the target recommended content in the target comment area based on the predicted display timing includes: If the current interaction attribute of the target comment area satisfies the target interaction attribute, the target recommended content is displayed in the target comment area.

4. The information display method according to claim 1, characterized in that: The predicted display timing includes a predicted display time, and displaying the target recommended content in the target comment area based on the predicted display timing includes: If the interval between the predicted display time and the predicted trigger time is less than a preset time, a display strategy for the comment data and the target recommended content is determined based on the priority of the comment data and the target recommended content, and the display strategy includes a display order or a display area.

5. The information display method according to claim 1, characterized in that: The displaying of the comment data of the target comment area includes: Obtaining a predicted display order of the comment data for the target comment area; sorting the review data based on the predicted display order; Display the sorted comment data of the target comment area.

6. The information display method according to claim 1, characterized in that: The predicted trigger time is predicted based on the first video feature of the target video and the first interactive feature of the target comment area, and the predicted display timing is predicted based on the predicted trigger time, the second video feature of the target video and the second interactive feature of the historical recommended content in the target comment area.

7. The information display method according to claim 6, characterized in that: The predicted trigger time is obtained by inputting the first video feature and the first interaction feature into the target comment prediction model to predict the trigger time of the comment control; the predicted display timing is obtained by inputting the predicted trigger time, the second video feature and the second interaction feature into the target recommendation prediction model to predict the display timing of the target recommended content.

8. The information display method according to claim 7, characterized in that: The target review prediction model is determined in the following manner: Obtaining candidate video features of each category of the sample video, candidate interaction features of each category of the sample comment area, and a corresponding trigger time tag of the sample comment area, wherein the sample comment area corresponds to the sample video; Determine a first sample video feature based on the correlation between the candidate video feature and the trigger time tag, where the first sample video feature and the first video feature belong to the same category; Determine a first sample interaction feature based on the correlation between the candidate interaction feature and the trigger time tag, where the first sample interaction feature and the first interaction feature belong to the same category; Inputting the first sample video feature and the first sample interaction feature into a preset comment prediction model, predicting the trigger time of the sample comment area, and obtaining a first prediction result; Based on the difference between the first prediction result and the trigger time tag, the parameters of the preset comment prediction model are updated to obtain the target comment prediction model.

9. The information display method according to claim 8, characterized in that: The method for determining the target recommendation prediction model includes: Obtaining a recommendation timing label of the sample recommended content in the sample comment area; Determining a second sample video feature based on the correlation between the candidate video feature and the recommendation timing label, where the second sample video feature and the second video feature belong to the same category; Determining a second sample interaction feature based on the correlation between the candidate interaction feature and the recommendation timing label, where the second sample interaction feature and the second interaction feature belong to the same category; Inputting the second sample video feature, the second sample interaction feature and the first prediction result into a preset recommendation prediction model, predicting the recommendation timing of the sample recommended content, and obtaining a second prediction result; Based on the difference between the second prediction result and the recommendation opportunity label, the parameters of the preset recommendation prediction model are updated to obtain the target recommendation prediction model.

10. The information display method according to claim 8, characterized in that: The method of obtaining the candidate video features and the candidate interaction features includes: Acquire first feature data of the sample video and second feature data of the sample comment area, wherein the first feature data includes at least one of description data of the sample video and operation data for the sample video, and the second feature data includes at least one of description data of the sample comment area, operation data for the sample comment area, operation data for sample comments in the sample comment area, and operation data for sample recommended content in the sample comment area; One-hot encoding is performed on different categories of data in the first feature data and the second feature data to obtain the candidate video features of each category and the candidate interaction features of each category.

11. The information display method according to claim 7, characterized in that: The output data of the target recommendation prediction model also includes the predicted recommendation effect of the target recommendation content; the method also includes: Displaying a feedback control in an area corresponding to the target recommended content in the target comment area; In response to an interactive operation on the feedback control, obtaining a feedback effect of the target recommended content; Based on the difference between the feedback effect and the target recommendation effect, parameters of the target recommendation prediction model are updated.

12. An information display device, characterized in that: The device comprises: A first display module, used to display the target video and comment controls on the video playback interface; An information acquisition module, used to acquire a predicted trigger time for the comment control and a predicted display timing of target recommended content, wherein the predicted display timing is predicted based on the predicted trigger time; An information loading module, used for loading the target recommended content and the comment data of the target comment area corresponding to the comment control based on the predicted trigger time; The second display module is used to display the comment data of the target comment area in response to the interactive operation of the comment control, and to display the target recommended content in the target comment area based on the predicted display timing.

13. An electronic device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the information display method according to any one of claims 1 to 11 by executing the computer instructions.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the information display method according to any one of claims 1 to 11.

15. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the information display method according to any one of claims 1 to 11.

Images