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

Abstract

The embodiment of the invention relates to an information display method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring current behavior data of a target video in a playing process; the target video belongs to an object recommendation type video; based on the current behavior data, identifying a switching intention of the target video, and predicting a target display moment of an object acquisition control corresponding to the target video; and displaying the object acquisition control in a preset area of the target video based on the target display moment. Thus, before the user slides to switch the target video, the object acquisition control can be displayed in advance at a faster response speed, and the display probability of the object acquisition control is improved, so that the click rate of the object acquisition control and the user conversion rate of the target video are improved to a certain extent.

Description

Technical Field

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

[0002] As various types of videos become more and more popular, there are cases where an object (such as a physical product, virtual service, tourist attraction, or film and television program) is promoted or recommended through object recommendation videos. These object recommendation videos can display object acquisition controls as the video progresses, so as to provide users with an entry to acquire the object.

[0003] However, the display timing of the object acquisition control in the object recommendation video is fixed. For example, when the display timing is pre-fixed at a 15-second interval, the object acquisition control will pop up only when the video playback progress of the object recommendation video reaches the 15th second. In this way, if the user is not interested in the object recommendation video or has no knowledge of the recommended object, it is easy to give up watching the video early, resulting in the object acquisition control in the object recommendation video missing the display opportunity, which in turn causes the click-through rate and user conversion rate of the object acquisition control to be low. Summary of the invention

[0004] In order to solve the above technical problems, the embodiments of the present disclosure provide an information display method, apparatus, device, storage medium and program product.

[0005] In a first aspect, an embodiment of the present disclosure provides an information display method, the method comprising:

[0006] Acquire current behavior data of a target video during playback; the target video belongs to an object recommendation video;

[0007] Based on the current behavior data, identifying the switching intention of the target video, and predicting the target display time of the object acquisition control corresponding to the target video;

[0008] Based on the target display time, the object acquisition control is displayed in a preset area of ​​the target video.

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

[0010] A current behavior data acquisition module is used to acquire current behavior data of a target video during playback; the target video belongs to an object recommendation video;

[0011] A target display time prediction module, used to identify the switching intention of the target video based on the current behavior data, and predict the target display time of the object acquisition control corresponding to the target video;

[0012] The object acquisition control display module is used to display the object acquisition control in a preset area of ​​the target video based on the target display time.

[0013] In a third aspect, an embodiment of the present disclosure further provides an electronic device, the electronic device comprising:

[0014] processor;

[0015] A memory for storing executable instructions;

[0016] The processor is used to read executable instructions from the memory and execute the executable instructions to implement the information display method described in any embodiment of the present disclosure.

[0017] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor implements the information display method described in any embodiment of the present disclosure.

[0018] In a fifth aspect, an embodiment of the present disclosure further provides a computer program product, which is used to execute the information display method described in any embodiment of the present disclosure.

[0019] The information display method, apparatus, device, storage medium and program product of the embodiments of the present disclosure can obtain current behavior data of a target video during playback; the target video belongs to an object recommendation video; based on the current behavior data, the switching intention of the target video is identified, and the target display time of the object acquisition control corresponding to the target video is predicted; based on the target display time, the object acquisition control is displayed in a preset area of ​​the target video; and the display time of the object acquisition control is dynamically adjusted according to the real-time behavior data of the user watching the target video of the object recommendation class, so that the object acquisition control can be displayed in advance with a faster response speed before the user slides to switch the target video, thereby increasing the display probability of the object acquisition control, thereby improving the click-through rate of the object acquisition control and the user conversion rate of the target video to a certain extent, and providing a personalized user experience.

[0020] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the embodiments of the present disclosure are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0022] Figure 1 A schematic diagram of an object recommendation video provided by an embodiment of the present disclosure;

[0023] Figure 2 A flowchart of an information display method provided by an embodiment of the present disclosure;

[0024] Figure 3 A flowchart of another information display method provided by an embodiment of the present disclosure;

[0025] Figure 4 A schematic diagram of the structure of an information display device provided in an embodiment of the present disclosure;

[0026] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0028] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0029] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0030] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0031] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0032] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0033] In clients with video browsing functions (such as applications, applets, web pages, etc.), various types of videos can be presented to users in the form of information streams as they switch between videos. These videos include object recommendation videos (such as pre-recorded advertising videos that recommend products or promote brands, recorded live broadcast videos that recommend products or promote brands, etc.). Object recommendation videos mainly include two types of videos: Figure 1 The video with object information shown in (a) above: the logo (such as name, icon, introduction, etc.) of the recommended object (product or brand, etc.) and the introduction entry control for more information about the recommended object (such as a "view details" button) are always displayed in the video; another example is Figure 1 The video with the object acquisition control shown in (b) above: when the video is played to a certain extent, an interactive control (i.e., an object acquisition control, such as a "Get Object" button) for acquiring (eg, purchasing) the recommended object pops up.

[0034] However, the above two types of object recommendation videos have certain problems in the video display process. Figure 1 (a) The object recommendation videos containing object information have fixed video display intervals and video durations, which cannot meet the video viewing needs of different users. Users may feel that such videos frequently interrupt their interest in watching videos, or they may feel that frequent interactive operations are required to skip such videos to watch videos of their interest, affecting the overall viewing experience. Figure 1 (b) In an object recommendation video with an object acquisition control, the display time of the object acquisition control is fixed (e.g., 15 seconds relative to the start of the video). If the user switches the video before the video playback progress reaches the fixed display time, the object acquisition control will not be displayed, and the conversion opportunity will be missed.

[0035] Based on the above situation, the embodiment of the present disclosure provides an information display scheme, which analyzes the behavioral data of users in the process of watching videos to determine the behavioral habits and preferences of users in watching videos, so that for object recommendation videos containing object acquisition controls, the display timing of the object acquisition control can be dynamically adjusted to ensure that the object acquisition control can be displayed before the user switches to the object recommendation video as much as possible, thereby improving the click-through rate of the object acquisition control and the user conversion rate of the video; and for object recommendation videos containing object information, according to the interests and video browsing habits of different users, the object recommendation videos that meet the user's interests and are adapted to the viewing time can be displayed in a personalized manner at the right time (such as after browsing n ordinary videos), thereby reducing interference with the user's browsing of ordinary videos (i.e., non-object recommendation videos), and without interrupting the user's normal video browsing experience, the relevance and user acceptance of the object recommendation video display can be improved, thereby improving the viewing rate, click-through rate and user conversion rate of the object recommendation video.

[0036] The information display method provided by the embodiment of the present disclosure can be applied to the scene where multiple videos are presented in the form of information stream, for example, the scene where object recommendation videos are displayed while the client browsing the videos continuously browses multiple videos. The method can be executed by an information display device, which can be implemented by software and / or hardware, and the device can be integrated in an electronic device with video playback and switching functions. The electronic device can include but is not limited to smart phones, personal digital assistants (PDAs), tablet computers (Tablet Personal Computers, Tablet PCs), PMPs (portable multimedia players), wearable devices, laptop computers, desktop computers, vehicle-mounted terminals (such as vehicle-mounted navigation terminals) or digital televisions.

[0037] Figure 2 FIG. 1 is a flow chart showing a method for displaying information provided by an embodiment of the present disclosure. Figure 2 As shown, the information display method may include the following steps:

[0038] S210: Obtain current behavior data of the target video during playback.

[0039] The target video is a video currently being played that belongs to the object recommendation class. The current behavior data is real-time or near real-time (eg, within a short time window of a few seconds to a few minutes) behavior data.

[0040] Exemplarily, the current behavior data includes at least one of the current sliding behavior data, the current click behavior data, and the current viewing behavior data. The current sliding behavior data is the relevant behavior data of the sliding video corresponding to the current moment, such as the start timestamp, end timestamp, and screen distance of the sliding operation, which is used to reflect the user's behavior habits of browsing videos and the user's interest in the video. The current click behavior data is the relevant behavior data of the click operation performed on the video corresponding to the current moment, such as the click time and click position of the click operation, which is used to reflect the user's interaction mode and thus reflect the user's interest in the video. The current viewing behavior data is the relevant behavior data of the viewing video corresponding to the current moment, such as the start timestamp and end timestamp of the viewing video, which is used to reflect the user's interest in the video. Through the behavior data such as sliding, clicking, and viewing, the user's viewing interest in the target video can be fully analyzed, so that it can be determined whether the user will switch the target video, and then the appropriate display time of the object acquisition control in the target video can be predicted.

[0041] Specifically, users have great autonomy and personalization, and in the process of watching videos, it is easy for them to change their interest in watching videos with changes in the environment or personal mood, etc. Therefore, in the embodiments of the present disclosure, a function with the function of monitoring various interactive operations such as user sliding behavior, clicking behavior and viewing behavior can be called to monitor the user's video viewing behavior data in real time or near real time to obtain the current behavior data of the user in the process of watching the target video.

[0042] S220: Based on the current behavior data, identify the switching intention of the target video, and predict the target display time of the object acquisition control corresponding to the target video.

[0043] The switching intention is the user's idea or tendency to manually switch from the target video to the next video. The target display time is the predicted display time of the object acquisition control in the target video, which can be an absolute time or a relative time relative to the start time of the video.

[0044] Specifically, after the electronic device collects the current behavior data of the user watching the target video, it can analyze it to identify whether the user has the intention to switch to the target video in a short time. If there is no intention to switch, the default display time can be determined as the target display time; if there is an intention to switch, the default display time can be shortened to determine the target display time with a shorter time interval. In this way, the target display time of the object acquisition control in the target video can be adjusted in time according to the user's current video viewing situation, so as to ensure that the object acquisition control is displayed before switching videos as much as possible, so as to achieve the purpose of displaying the object acquisition control in the target video in a personalized way, thereby increasing the probability of the object acquisition control appearing, and further increasing the probability of the target video being clicked, thereby improving the user conversion rate of the target video.

[0045] For example, the current behavior data can be analyzed, and the analysis results can be matched with the preset matching rules corresponding to the switching intention to identify the intention. Then, the target display time is predicted based on the current behavior data, and the time before the possible switching operation is obtained as the target display time.

[0046] For example, a pre-trained machine learning model can be called based on the current behavior data. After being processed by the model, it can be identified whether the user has the intention to switch to the target video in a short period of time. When there is a switching intention, the model outputs its predicted target display time.

[0047] S230: Based on the target display time, display the object acquisition control in a preset area of ​​the target video.

[0048] Specifically, during the playback of the target video, the electronic device monitors in real time whether the video playback time reaches the target display time. If it reaches the target display time, the object acquisition control is displayed in the preset area of ​​the target video, such as Figure 1 (b) as shown.

[0049] The information display method provided by the above-mentioned embodiments of the present disclosure can obtain the current behavior data of the target video during the playback process; the target video belongs to the object recommendation type video; based on the current behavior data, the switching intention of the target video is identified, and the target display time of the object acquisition control corresponding to the target video is predicted; based on the target display time, the object acquisition control is displayed in a preset area of ​​the target video; it is realized that according to the real-time behavior data of the user watching the target video of the object recommendation type, the display time of the object acquisition control is dynamically adjusted, so that before the user slides to switch the target video, the object acquisition control is displayed in advance with a faster response speed, thereby improving the display probability of the object acquisition control, thereby improving the click rate of the object acquisition control and the user conversion rate of the target video to a certain extent.

[0050] In some embodiments, the switching intention can be identified and the target display time can be predicted by a pre-trained machine learning model. In this way, S220 includes the following steps A and B.

[0051] Step A: preprocess the current behavior data to generate current behavior features corresponding to the current behavior data.

[0052] Among them, the current behavior feature is the representative and distinguishing information extracted from the current behavior data. It is a summary and abstraction of the behavior data, used to describe and characterize the characteristics and patterns of the user's current behavior. The data structure of the current behavior feature is consistent with the data structure of the input data of the model called subsequently.

[0053] Specifically, the current behavior data is relatively superficial and scattered data. In order to adapt to the needs of subsequent models, the electronic device can pre-process the current behavior data to remove the noise data, and organize the remaining current behavior data into data indicators and data formats required by the model to obtain the current behavior characteristics. This can not only reduce the interference of noise data, improve the accuracy of intent recognition and target display time prediction, but also improve the processing efficiency of the model and enhance the real-time performance of intent recognition and target display time prediction.

[0054] In some examples, step A can be implemented as follows: based on a behavior data threshold, denoising the current behavior data to generate denoised behavior data; processing the denoised behavior data according to preset indicators to generate current behavior features corresponding to the current behavior data.

[0055] Among them, the behavior data threshold is the critical value of the behavior data, which is used to determine whether the current behavior data is abnormal behavior data. The behavior data threshold is determined based on the mean and standard deviation of the historical behavior data. The historical behavior data is the behavior data generated in the historical time period at the current moment and in the process of multiple users watching multiple videos. The mean and standard deviation of the historical behavior data can reflect the data distribution that conforms to the normal operation behavior of the user, so the behavior data threshold can be determined by (mean ± n * standard deviation). Here n is a positive integer greater than or equal to 1. The preset indicator is a data indicator pre-set according to the type of behavior data. For example, if the type of behavior data is sliding behavior data, then the preset indicator can be at least one of sliding speed, sliding distance, sliding frequency and sliding skip rate; for another example, if the type of behavior data is click behavior data, then the preset indicator can be click rate; for another example, if the type of behavior data is viewing behavior data, then the preset indicator can be viewing time and / or viewing frequency.

[0056] Specifically, the electronic device may determine a corresponding behavior data threshold according to the type of behavior data, and then filter and denoise the current behavior data according to the behavior data threshold to obtain denoised behavior data.

[0057] In one example, the type of behavior data may be sliding behavior data, and the abnormal sliding behavior data may be abnormal sliding behavior data with a short sliding time caused by the user accidentally touching the screen, or abnormal sliding behavior data with a long sliding time caused by application freeze, device problems or other abnormal operations. In this case, the electronic device can determine the corresponding behavior data thresholds as (sliding time mean-n*sliding time standard deviation) and (sliding time mean+m*sliding time standard deviation) according to the determined sliding time mean and sliding time standard deviation corresponding to the historical sliding behavior data, where m and n can be the same or different. Then, the electronic device can calculate the current sliding time of the current sliding operation through the start timestamp and end timestamp of the sliding operation recorded in the current behavior data. Afterwards, if the electronic device determines that the current sliding time is less than (sliding time mean-n*sliding time standard deviation) or the current sliding time is greater than (sliding time mean+m*sliding time standard deviation), the behavior data corresponding to the current sliding operation is removed; otherwise, the behavior data corresponding to the current sliding operation is retained.

[0058] In another example, the type of behavior data may be sliding behavior data, and abnormal sliding behavior data may be excessively high or low sliding speed. The sliding speed can be used to reflect the user's interest in the video, and can also reflect the user's behavior habits and behavior frequency of watching the video, thereby assisting in determining whether the user tends to slide quickly or browse carefully. Therefore, it is necessary to eliminate abnormal sliding speeds. In this case, the electronic device can determine the corresponding behavior data thresholds as (sliding speed mean-n*sliding speed standard deviation) and (sliding speed mean+m*sliding speed standard deviation) according to the determined sliding speed mean and sliding speed standard deviation corresponding to the historical sliding behavior data. Then, the electronic device can calculate the current sliding speed by the current sliding distance recorded in the current behavior data and the current sliding time calculated above. Afterwards, if the electronic device determines that the current sliding speed is less than (sliding speed mean-n*sliding speed standard deviation) or the current sliding speed is greater than (sliding speed mean+m*sliding speed standard deviation), the behavior data corresponding to the current sliding operation is eliminated; otherwise, the behavior data corresponding to the current sliding operation is retained.

[0059] Using the same processing method, electronic devices can perform denoising on abnormal sliding frequency and sliding skip rate. The sliding frequency is the number of times a user performs sliding operations per unit time, which can be obtained by calculating the number of sliding operations per unit time through the timestamps recorded in multiple sliding behavior data. The sliding skip rate is the probability that a user directly slides over an advertisement without watching it. Its function is to predict whether a user will click on the video or directly slide over the video.

[0060] In another example, the type of behavior data may be click behavior data, then abnormal click behavior data may occur in the scenario where the user clicks very quickly or delays too long, which can be judged by analyzing the click interval time. The click interval time can be calculated by the start timestamp and end timestamp recorded in the click behavior data, which can be used to calculate the click rate, thereby reflecting the user's interest in the video. In this case, the electronic device can determine the corresponding behavior data thresholds as (click interval mean - n * click interval standard deviation) and (click interval mean + m * click interval standard deviation) according to the click interval mean and click interval standard deviation corresponding to the determined historical click behavior data. Then, the electronic device can calculate the current click interval time of the current click operation through the current behavior data. Afterwards, if the electronic device determines that the current click interval time is less than (click interval mean - n * click interval standard deviation) or the current click time is greater than (click interval mean + m * click interval standard deviation), the behavior data corresponding to the current click operation is eliminated; otherwise, the behavior data corresponding to the current click operation is retained.

[0061] In another example, the type of behavior data is viewing behavior data, then the abnormal viewing behavior data may appear outside the normal duration range of the object recommendation class video, which can be determined by analyzing the viewing time. The viewing time can be calculated by the start timestamp and end timestamp recorded in the viewing behavior data, which can be used to reflect whether the user has watched the object recommendation class video completely, thereby reflecting the user's interest in the video. In this case, the electronic device can determine the corresponding behavior data thresholds, respectively, (viewing time mean-n*viewing time standard deviation) and (viewing time mean+m*viewing time standard deviation) according to the determined viewing time mean and viewing time standard deviation corresponding to the historical viewing behavior data. Then, the electronic device can calculate the current viewing time of the current viewing operation through the current behavior data. Afterwards, if the electronic device determines that the current viewing time is less than (viewing time mean-n*viewing time standard deviation) or the current viewing time is greater than (viewing time mean+m*viewing time standard deviation), the behavior data corresponding to the current viewing operation is eliminated; otherwise, the behavior data corresponding to the current viewing operation is retained.

[0062] After the above denoising process, denoised behavior data can be obtained. Then, the electronic device can continue to format the denoised behavior data to obtain behavior data with consistent data format. After that, the behavior data obtained by the above process can be calculated and normalized according to preset indicators, such as average sliding speed, sliding distance, sliding frequency, dwell time and click rate, to obtain the current behavior characteristics corresponding to the current behavior data.

[0063] The above-mentioned dwell time refers to the length of time that a user stays on a certain object recommendation video after a swipe. The above-mentioned click-through rate can be calculated by the number of clicks on the object recommendation video recorded in the behavior data and the total number of displayed object recommendation videos, which can reflect whether the user is interested in the content of the object recommendation video.

[0064] Step B: Based on the current behavior characteristics, call the first preset model to identify the switching intention of the target video and predict the target display time.

[0065] The first preset model is trained in advance using video samples and reference display time of object acquisition controls corresponding to the video samples. The reference display time is a display time of the object acquisition control pre-set for the video samples that is more in line with the user's behavior and interests in watching object recommendation videos.

[0066] Exemplarily, the first preset model includes a machine learning model with preset characteristics; the preset characteristics include at least one of the characteristics of processing data exceeding a preset dimension, the generalization characteristics exceeding a preset strength, the characteristics of processing missing values, and the characteristics of evaluating the importance of features. In other words, the first preset model needs to have the ability to process high-dimensional data of a data set containing multiple features, a strong generalization ability to maintain good prediction performance on unseen data, the ability to process missing values ​​in the case of some missing features, and the ability to provide feature importance output to help understand the model's support for feature importance evaluation. The more preset characteristics the selected machine learning model has, the stronger the performance of the model in switching intention recognition and display moment prediction.

[0067] Specifically, the electronic device can pre-train the selected machine learning model using the behavioral data corresponding to multiple groups of video samples and the reference display time of the corresponding object acquisition control, so that the model learns the relationship between the behavioral characteristics and the display time of the object acquisition control, and obtains the first preset model. Then, after obtaining the current behavioral characteristics, the electronic device can use it as the input data of the model, call the first preset model, and after the model is processed, output whether the user has the intention to switch to the target video at the current moment. When it is determined that there is a switching intention, the predicted target display time can be output at the same time. In this way, the current behavioral characteristics can be obtained through preprocessing, and the first preset model can be called based on this to more accurately obtain the target display time of the object acquisition control, thereby further improving the click-through rate and user conversion rate of the target video.

[0068] It should be noted that by setting up an experimental group and a control group, the click-through rate and conversion rate of the object recommendation videos of the two groups of users can be compared, the actual effect of the model can be evaluated through data analysis, and more appropriate video samples and their behavior data and reference display time can be continuously collected to continuously optimize the first preset model. The experimental group uses a dynamically adjusted target display time, while the control group uses a default fixed time interval display time.

[0069] It should also be noted that when the first preset model needs to be integrated into clients of different operating systems, the model can be first converted into a format that is compatible with the operating system, and then the format-converted model can be integrated into the client to achieve real-time prediction of the target display time of the object acquisition control in the object class recommendation video. After the model is optimized, the first preset model integrated in the client can be updated by hot update or other methods.

[0070] In other embodiments, the switching intention may be identified and the target display time may be predicted by pre-configured matching rules. Thus, S220 includes the following steps A′ and B′.

[0071] Step A′: based on the current behavior data, determine the behavior data change trend corresponding to the target video.

[0072] The behavior data change trend refers to the trend of the behavior data for the target video changing over time. Exemplarily, according to the type of behavior data, the behavior data change trend may include at least one of the viewing time change trend, the sliding speed change trend, and the stay time change trend. The viewing time change trend is the change trend of the viewing time of the object recommendation video that the user watches over time. The sliding speed change trend is the change trend of the sliding speed of the user for the object recommendation video over time. The stay time change trend is the trend of the length of time that the user stays after sliding to the object recommendation video over time.

[0073] Specifically, the electronic device can perform statistical analysis on the historical behavior data of the user browsing the recommended object video to obtain the basic behavior data change trend corresponding to the user. Then, the electronic device superimposes the current behavior data obtained in real time or near real time onto the above basic behavior data change trend to update it, and thus obtains the behavior data change trend corresponding to the target video.

[0074] Step B′: if it is identified that the target video has a switching intention based on the behavior data change trend, the switching moment corresponding to the switching intention is predicted based on the behavior data change trend, and the target display moment is predicted based on the switching moment.

[0075] Specifically, the electronic device can use the trend analysis method in the relevant technology to perform predictive analysis on subsequent behavior data changes according to the behavior data change trend corresponding to the target video, so as to determine whether the user has the intention to switch to the target video. For example, through the change trend of viewing time, it can be predicted that the average video viewing time in a shorter time window after the current moment will be shortened to before the default display time, and it can be considered that the user has the intention to switch; for another example, through the change trend of sliding speed, it can be predicted that the user's sliding speed is getting faster, and the user may switch the target video in a shorter time window after the current moment, and it can be considered that the user has the intention to switch; for another example, through the change trend of stay time, it can be predicted that the user's stay time after the sliding operation is shortening, and it can be considered that the user has the intention to switch.

[0076] Then, after identifying that the user has the intention to switch the target video, the electronic device can further refine and analyze the trend of behavior data changes to predict the switching moment corresponding to the switching intention. For example, the electronic device can use the trend of the change in viewing time corresponding to the target video to determine the latest average viewing time, and determine the switching moment as a moment less than the average viewing time; for another example, the electronic device can use the trend of the change in the sliding speed corresponding to the target video to predict the user's sliding speed for the target video, and estimate when the user may switch the video based on the sliding speed, and determine the estimated moment as the switching moment; for another example, the electronic device can use the trend of the change in the dwell time corresponding to the target video to predict the dwell time of the target video, and then estimate the remaining dwell time of the user in the target video based on the played time and the predicted dwell time, and determine the moment corresponding to the remaining dwell time as the switching moment, etc. Afterwards, the electronic device can determine an instantaneous moment in the time period after the current moment and before the switching moment as the predicted target display moment. In this way, more understandable rules / algorithms can be used to dynamically adjust the target display moment suitable for users to watch the target video.

[0077] Figure 3is a flow chart of another information display method provided by an embodiment of the present disclosure. The information display method can further add steps related to determining the target video and its playback timing. Figure 3 , the information display method specifically includes the following steps:

[0078] S310: Obtain historical behavior data of multiple historical videos within a historical time period.

[0079] Among them, the historical time period is a period of time before the current moment, and its time interval can be determined by the amount of historical behavior data of watching historical videos. For example, if the amount of historical behavior data is large, the historical time period can be set to a shorter duration, such as 7 days or a month, etc., which at least covers the duration of a user's work and rest cycle; for another example, if the amount of historical behavior data is small, the historical time period can be set to a longer duration, such as half a year or even a year. Historical videos are videos that have been watched within the historical time period, which can be object recommendation videos or ordinary videos of non-object recommendation categories. Historical behavior data is the behavior data of watching videos obtained in the historical time period.

[0080] Specifically, users' requirements for watching object recommendation videos may include: appropriate display time - a shorter video duration of a few seconds to more than ten seconds, so as not to interrupt their experience of browsing ordinary videos; and higher-quality video content; content relevance - personalized video content related to user interests and needs; and video content adapted to the video content of ordinary videos recently browsed by users or user behavior scenarios; non-disruptive video browsing experience - object recommendation videos with appropriate quantity and display timing, so as not to frequently interrupt the normal browsing experience; the operational experience of being able to easily skip or close object recommendation videos, etc. Therefore, for situations such as long duration, poor video content quality, video content that does not meet user interests, a large number of object recommendation videos, inappropriate display timing of object recommendation videos, etc., users are very likely to skip such videos directly or even exit the video client, resulting in problems such as low playback rate of object recommendation videos and low user conversion rate.

[0081] Based on the above situation, the disclosed embodiment can analyze the historical behavior data of users watching various videos, in order to capture the user's video browsing habits, their preferences for video content, and their viewing patterns of recommended videos, etc., so as to screen out target videos suitable for users to watch and determine their appropriate display time to meet the user's needs for recommended videos as much as possible. Therefore, the electronic device can first obtain the historical behavior data of users watching various videos in the historical time period.

[0082] S320: Preprocess the historical behavior data to generate historical behavior features corresponding to the historical behavior data.

[0083] Specifically, referring to the aforementioned embodiments for generating current behavior features, the electronic device may adopt the same preprocessing method to preprocess the behavior data to generate its corresponding historical behavior features.

[0084] S330: Based on the historical behavior characteristics, call the second preset model to determine the video viewing mode.

[0085] Among them, the second preset model is a pre-trained machine learning model, and its basic model can be the same as or different from the first preset model. The second preset model is pre-trained using the behavioral data of multiple video samples and their corresponding reference video viewing patterns, and is used to determine the user's video viewing pattern based on the behavioral data of browsing videos. The video viewing pattern is the user's behavioral habits or behavioral patterns when browsing videos, for example, it can be the behavioral habits / behavioral patterns of how long to watch an object recommendation video during busy periods or how many ordinary videos to watch before patiently watching an object recommendation video, how long to watch an object recommendation video during leisure periods or how many ordinary videos to watch before patiently watching an object recommendation video, etc.

[0086] Specifically, the electronic device inputs the obtained historical behavior characteristics into the second preset model, and after being processed by the model, can output the video viewing mode of the user.

[0087] S340: Based on the current video and the video viewing mode, determine the play time of the object recommendation category video that follows the current video.

[0088] The current video is the video currently being played, which can be a non-object recommendation video or an object recommendation video. The play time can be understood as the display time of the object recommendation video, for example, it can be expressed as the number of videos after the current video.

[0089] Specifically, the electronic device can determine the playback time of the object recommendation video that can be displayed after the current video according to whether the current video is an object recommendation video, the number of such videos played when the current video is a common video that is not an object recommendation video, and the video viewing mode determined above. For example, if the video viewing mode is five common videos + one object recommendation video, and the current video is the second common video played, then the playback time can be determined to be the fourth video after the current video; if the current video is an object recommendation video, then the playback time of the next object recommendation video adjacent to the current video is the sixth video after the current video.

[0090] S350: Determine a target video based on historical behavior characteristics.

[0091] Specifically, after determining the appropriate display time of the object recommendation video, it is necessary to further determine the specific object recommendation video that meets the user's viewing interests and viewing habits, so that the user can watch the displayed object recommendation video for a longer time instead of skipping it quickly. Therefore, the electronic device can analyze the historical behavior characteristics again to determine the video length, video content type, etc. of the object recommendation video preferred by the user. Then, the target video can be screened out from many object recommendation videos based on the obtained video length and video content type.

[0092] In some embodiments, S350 includes: determining video information of an adjacent video immediately before the playback moment; determining a target video segmentation type and a target video duration based on historical behavior characteristics; and determining a target video from multiple candidate videos based on the video information, the target video segmentation type and the target video duration.

[0093] Among them, video information is relevant information describing the video. Exemplarily, the video information can be the type of video content and the identification of the objects contained in the video content, etc. For example, the video information can be the type of film and television drama and the name of the film and television drama, or the shopping type and product name, etc. The video segmentation type is a video classification type of the next level under the larger video classification. For example, for the object recommendation class, the corresponding target video segmentation type can be a shopping type, a film and television drama type, a novel type, etc. The target video segmentation type is a video segmentation type that the user may be interested in. The target video duration is the video duration of the object recommendation class video that is acceptable to the user. The candidate video is a pre-provided object recommendation class video, which has the attribute of video duration and can carry a label of the video segmentation type.

[0094] Specifically, the fixed display timing and fixed video duration set for object recommendation videos in the related art cannot meet the needs of different users. Therefore, the electronic device can use pre-configured rules or pre-trained models to analyze the behavior characteristics related to object recommendation videos in historical behavior characteristics to determine the target video segmentation type and target video duration preferred by the user. At the same time, the video information of an ordinary video before the playback time of the object recommendation video can be obtained. Then, according to the video information, the target video segmentation type and the target video duration, the target video is screened from multiple candidate videos. For example, the target video segmentation type is the film and television drama type, the target video duration is 20 seconds, and the video information is the film and television drama type and "xx Biography", then the candidate video with a video duration of about 20 seconds, related to "xx Biography", and carrying the label of the film and television drama type (such as a video promoting the theater or movie ticket of "xx Biography") can be screened from multiple candidate videos as the target video. For another example, the target video subdivision type is shopping type, the target video length is 20 seconds, and the video information is the film and television drama type and "xx Legend". Then, candidate videos with a video length of about 20 seconds, related to "xx Legend", and carrying shopping type labels (such as videos recommending the same clothing or figures in "xx Legend") can be selected from multiple candidate videos as target videos.

[0095] In some embodiments, the electronic device can filter out multiple candidate videos that meet the requirements from multiple candidate videos based on video information, target video segmentation type, and target video duration. On this basis, the electronic device can further combine the historical behavioral characteristics of the object recommendation class videos that have been watched historically to determine the user's video viewing interests, and further filter out a candidate video from the multiple candidate videos that have been filtered out as the target video. For example, the filtered candidate videos that have at least one of the behavioral characteristics of a higher click-through rate, a longer viewing time / stay time, a lower sliding skip rate, and a lower sliding speed can be filtered out as the target video.

[0096] S360, display and start playing the target video at the playback time.

[0097] Specifically, when the electronic device detects that the current moment reaches the above-determined playback moment (such as the fifth ordinary video has been played at the current moment), it displays the above-determined target video and starts playing the target video.

[0098] S370, obtaining current behavior data of the target video during playback; the target video belongs to the object recommendation type video.

[0099] S380: Based on the current behavior data, the switching intention of the target video is identified, and the target display time of the object acquisition control corresponding to the target video is predicted.

[0100] S390: Based on the target display time, display the object acquisition control in a preset area of ​​the target video.

[0101] The information display method provided by the above-mentioned embodiments of the present disclosure obtains historical behavior data of multiple historical videos within a historical time period; pre-processes the historical behavior data to generate historical behavior features corresponding to the historical behavior data; based on the historical behavior features, calls a second preset model to determine a video viewing mode; based on the current video and the video viewing mode, determines the playback time of an object recommendation video that is after the current video; based on the historical behavior features, determines a target video; displays and starts playing the target video at the playback time; and predicts the time (i.e., the playback time) when a user is most likely to accept an object recommendation video based on the user's video browsing behavior data, and displays a target video that is more in line with the user's viewing interest and acceptable viewing time at the playback time, thereby improving the personalization of the displayed object recommendation video and the user's acceptance of it, thereby further improving the probability of the target video being viewed, and improving user retention and engagement.

[0102] The following is an embodiment of an information display device provided by an embodiment of the present invention. The device and the information display methods of the above-mentioned embodiments belong to the same inventive concept. For details not described in detail in the embodiment of the information display device, reference can be made to the embodiments of the above-mentioned information display method.

[0103] Figure 4 FIG. 1 is a schematic diagram showing the structure of an information display device provided by an embodiment of the present disclosure. Figure 4 As shown, the information display device 400 may include:

[0104] The current behavior data acquisition module 410 is used to acquire the current behavior data of the target video during the playback process; the target video belongs to the object recommendation type video;

[0105] The target display time prediction module 420 is used to identify the switching intention of the target video based on the current behavior data, and predict the target display time of the object acquisition control corresponding to the target video;

[0106] The object acquisition control display module 430 is used to display the object acquisition control in a preset area of ​​the target video based on the target display time.

[0107] The information display device provided by the above-mentioned embodiments of the present disclosure can obtain the current behavior data of the target video during the playback process; the target video belongs to the object recommendation type video; based on the current behavior data, the switching intention of the target video is identified, and the target display time of the object acquisition control corresponding to the target video is predicted; based on the target display time, the object acquisition control is displayed in a preset area of ​​the target video; it is realized that according to the real-time behavior data of the user watching the target video of the object recommendation type, the display time of the object acquisition control is dynamically adjusted, so that before the user slides to switch the target video, the object acquisition control is displayed in advance with a faster response speed, thereby improving the display probability of the object acquisition control, thereby improving the click rate of the object acquisition control and the user conversion rate of the target video to a certain extent.

[0108] In some embodiments, the target presentation time prediction module 420 includes:

[0109] A current behavior feature generation submodule is used to pre-process the current behavior data and generate current behavior features corresponding to the current behavior data;

[0110] The target display time prediction submodule is used to call the first preset model to identify the switching intention of the target video based on the current behavior characteristics and predict the target display time; the first preset model is pre-trained using the video sample and the object corresponding to the video sample to obtain the reference display time of the control.

[0111] In some embodiments, the current behavior feature generation submodule is specifically used to:

[0112] Based on the behavior data threshold, the current behavior data is denoised to generate denoised behavior data; the behavior data threshold is determined based on the mean and standard deviation of the historical behavior data;

[0113] According to the preset indicators, the denoised behavior data is processed to generate the current behavior features corresponding to the current behavior data.

[0114] In some embodiments, the first preset model includes a machine learning model having preset characteristics; the preset characteristics include at least one of a characteristic for processing data exceeding a preset dimension, a generalization characteristic exceeding a preset strength, a characteristic for processing missing values, and a characteristic for evaluating feature importance.

[0115] In some embodiments, the current behavior data includes at least one of current sliding behavior data, current clicking behavior data, and current viewing behavior data.

[0116] In some embodiments, the target presentation time prediction module 420 is specifically used to:

[0117] Based on the current behavior data, determining a behavior data change trend corresponding to the target video; the behavior data change trend includes at least one of a viewing time change trend, a sliding speed change trend, and a stay time change trend;

[0118] If it is identified that the target video has a switching intention based on the changing trend of the behavior data, the switching moment corresponding to the switching intention is predicted based on the changing trend of the behavior data, and the target display moment is predicted based on the switching moment.

[0119] In some embodiments, the information display device 400 further includes:

[0120] A historical behavior data acquisition module is used to acquire historical behavior data of multiple historical videos within a historical time period before acquiring current behavior data of a target video during playback;

[0121] A historical behavior feature generation module is used to pre-process the historical behavior data and generate historical behavior features corresponding to the historical behavior data;

[0122] A video viewing mode determination module, configured to call a second preset model based on historical behavior characteristics to determine a video viewing mode;

[0123] A playback time determination module, used to determine the playback time of the object recommendation class video after the current video based on the current video and the video viewing mode;

[0124] A target video determination module, used to determine the target video based on historical behavior characteristics;

[0125] The target video playback module is used to display and start playing the target video at the playback time.

[0126] Furthermore, the target video determination module is specifically used for:

[0127] Determine video information of an adjacent video immediately before the playback time;

[0128] Based on historical behavior characteristics, determine the target video segmentation type and target video duration;

[0129] A target video is determined from multiple candidate videos based on video information, target video segmentation type, and target video duration.

[0130] The information display device provided in the embodiment of the present invention can execute the information display method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0131] It is worth noting that in the embodiment of the above-mentioned information display device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this disclosure.

[0132] The present disclosure also provides an electronic device, which may include a processor and a memory, wherein the memory may be used to store executable instructions. The processor may be used to read the executable instructions from the memory and execute the executable instructions to implement the information display method in the above embodiment.

[0133] Figure 5 A schematic structural diagram of an electronic device provided by an embodiment of the present disclosure is shown.

[0134] like Figure 5 As shown, the electronic device 500 may include a processing device 501 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output interface (I / O interface) 505 is also connected to the bus 504.

[0135] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data.

[0136] It should be noted that Figure 5 The electronic device 500 shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure. Figure 5 The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0137] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the information display method of any embodiment of the present disclosure are executed.

[0138] The embodiments of the present disclosure further provide a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor implements the information display method in any embodiment of the present disclosure.

[0139] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0140] In some embodiments, the client and server may communicate using any currently known or future developed network protocol such as HTTP, and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0141] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0142] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the steps of the information display method described in any embodiment of the present disclosure.

[0143] In embodiments of the present disclosure, computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as a separate software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0144] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the equipment, method and computer program product according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0145] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0146] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0147] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0148] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0149] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. An information display method, characterized in that: include: Get the current behavior data of the target video during playback; The target video belongs to the object recommendation video category; Based on the current behavior data, identifying the switching intention of the target video, and predicting the target display time of the object acquisition control corresponding to the target video; Based on the target display time, the object acquisition control is displayed in a preset area of ​​the target video.

2. The method according to claim 1, characterized in that The step of identifying the switching intention of the target video based on the current behavior data and predicting the target display time of the object acquisition control corresponding to the target video includes: Preprocessing the current behavior data to generate current behavior features corresponding to the current behavior data; Based on the current behavior characteristics, a first preset model is called to identify the switching intention of the target video and predict the target display time; the first preset model is pre-trained using video samples and objects corresponding to the video samples to obtain a reference display time of the control.

3. The method according to claim 2, characterized in that The preprocessing of the current behavior data to generate current behavior features corresponding to the current behavior data includes: Based on a behavior data threshold, denoising the current behavior data to generate denoised behavior data; the behavior data threshold is determined based on the mean and standard deviation of the historical behavior data; The denoised behavior data is processed according to preset indicators to generate the current behavior features corresponding to the current behavior data.

4. The method according to claim 2, characterized in that: The first preset model includes a machine learning model with preset characteristics; the preset characteristics include at least one of a characteristic of processing data exceeding a preset dimension, a generalization characteristic exceeding a preset strength, a characteristic of processing missing values, and a characteristic of evaluating feature importance.

5. The method according to claim 1, characterized in that The current behavior data includes at least one of current sliding behavior data, current clicking behavior data, and current viewing behavior data.

6. The method according to claim 5, characterized in that The step of identifying the switching intention of the target video based on the current behavior data and predicting the target display time of the object acquisition control corresponding to the target video includes: Based on the current behavior data, determining a behavior data change trend corresponding to the target video; the behavior data change trend includes at least one of a viewing time change trend, a sliding speed change trend, and a stay time change trend; If it is identified that the target video corresponds to a switching intention based on the changing trend of the behavior data, then the switching moment corresponding to the switching intention is predicted based on the changing trend of the behavior data, and the target display moment is predicted based on the switching moment.

7. The method according to claim 1, characterized in that Before obtaining the current behavior data of the target video during playback, the method further includes: Obtain historical behavior data of multiple historical videos within a historical time period; Preprocessing the historical behavior data to generate historical behavior features corresponding to the historical behavior data; Based on the historical behavior characteristics, calling a second preset model to determine a video viewing mode; Based on the current video and the video viewing mode, determining a play time of the object recommendation video that follows the current video; Based on the historical behavior characteristics, determining the target video; The target video is displayed and started to be played at the playing time.

8. The method according to claim 7, characterized in that The determining the target video based on the historical behavior characteristics includes: Determine video information of an adjacent video immediately before the playback time; Based on the historical behavior characteristics, determine the target video segmentation type and target video duration; The target video is determined from multiple candidate videos based on the video information, the target video segmentation type and the target video duration.

9. An information display device, characterized in that: include: The current behavior data acquisition module is used to acquire the current behavior data of the target video during playback; The target video belongs to the object recommendation video category; A target display time prediction module, used to identify the switching intention of the target video based on the current behavior data, and predict the target display time of the object acquisition control corresponding to the target video; The object acquisition control display module is used to display the object acquisition control in a preset area of ​​the target video based on the target display time.

10. An electronic device, characterized in that: include: processor; A memory for storing executable instructions; The processor is used to read the executable instructions from the memory and execute the executable instructions to implement the information display method described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the information display method described in any one of claims 1 to 8.

12. A computer program product, characterized in that The computer program product is used to implement the information display method described in any one of claims 1 to 8.

Images