Video playback method, device, electronic device and storage medium

Abstract

The present disclosure relates to a video playback method, device, electronic device and storage medium. The method includes: obtaining recommendation feedback results of multiple target videos displayed on a video recommendation page; adjusting the recommendation weight corresponding to each target video according to the feedback behavior characterized by the recommendation feedback results of each target video to obtain the adjusted recommendation weight; the order of the recommendation weights of the multiple target videos after the adjustment is different from the order of the recommendation weights before the adjustment; in response to an event that multiple target videos are included again in multiple videos displayed on the video recommendation page during the browsing process of the video recommendation page, the target video to be played is determined according to the size of the adjusted recommendation weights of each target video. In the present disclosure, when the terminal includes the same target video again in the video recommendation page, it can play it in a different order to avoid playing fixed videos and improve the efficiency of users in obtaining suitable videos.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a video playback method, device, electronic device and storage medium. Background Art

[0002] With the development of computer technology, in order to assist users to quickly browse videos of interest, the recommendation weight of a video can be determined, and the video can be recommended with the help of the recommendation weight.

[0003] In related technologies, the server can pre-calculate the recommendation weights of multiple videos to be displayed, and return the recommendation weights and video resources to the client, so that the client can recommend and play videos according to the recommendation weights provided by the server.

[0004] However, before the server re-issues new recommendation weights, the client plays videos based on the existing recommendation weights each time, which can easily cause fixed videos to be played in a loop, making it difficult to quickly obtain videos suitable for users to browse. Summary of the invention

[0005] The present disclosure provides a video playback method, device, electronic device, storage medium and computer program product to at least solve the problem of low video acquisition efficiency in the related art. The technical solution of the present disclosure is as follows:

[0006] According to a first aspect of an embodiment of the present disclosure, a video playback method is provided, including:

[0007] Obtaining recommendation feedback results of multiple target videos displayed on a video recommendation page; the video recommendation page displays multiple videos at the same time, and the multiple videos are played in sequence based on the size of the recommendation weights, and the recommendation feedback results represent the feedback behavior of the user object on the displayed target videos;

[0008] According to the feedback behavior represented by the recommendation feedback result of each target video, the recommendation weight corresponding to each target video is adjusted to obtain an adjusted recommendation weight; the order of the recommendation weights of the plurality of target videos after the adjustment is different from the order of the recommendation weights before the adjustment;

[0009] In response to an event that the multiple target videos are included again in the multiple videos displayed on the video recommendation page during browsing of the video recommendation page, the target videos to be played are determined according to the sizes of the adjusted recommendation weights of the respective target videos.

[0010] In an exemplary embodiment, adjusting the recommendation weight corresponding to each target video according to the feedback behavior represented by the recommendation feedback result of each target video to obtain the adjusted recommendation weight includes:

[0011] If the recommendation feedback result of the target video indicates that the target video has not been played, the recommendation weight corresponding to the target video is increased to obtain an adjusted recommendation weight.

[0012] In an exemplary embodiment, the step of increasing the recommendation weight corresponding to the target video to obtain an adjusted recommendation weight includes:

[0013] The sum of the preset weight increase coefficient and the recommendation weight corresponding to the target video is obtained as the adjusted recommendation weight.

[0014] In an exemplary embodiment, adjusting the recommendation weight corresponding to each target video according to the feedback behavior represented by the recommendation feedback result of each target video to obtain the adjusted recommendation weight includes:

[0015] If the recommendation feedback result of the target video indicates that the target video has been automatically played, the predetermined recommendation weight of the target video is reduced to obtain an adjusted recommendation weight.

[0016] In an exemplary embodiment, reducing the predetermined recommendation weight of the target video to obtain an adjusted recommendation weight includes:

[0017] The ratio of the recommendation weight corresponding to the target video to the predetermined weight reduction coefficient is obtained as the adjusted recommendation weight.

[0018] In an exemplary embodiment, adjusting the recommendation weight corresponding to each target video according to the feedback behavior represented by the recommendation feedback result of each target video to obtain the adjusted recommendation weight includes:

[0019] If the recommendation feedback result of the target video indicates that the target video has been clicked, obtaining the number of clicks of the target video;

[0020] Determine a weight adjustment probability corresponding to the number of clicks;

[0021] If the pre-acquired random number is less than the weight adjustment probability, the recommendation weight corresponding to the target video is adjusted to obtain an adjusted recommendation weight.

[0022] In an exemplary embodiment, determining the weight adjustment probability corresponding to the number of clicks includes:

[0023] Obtaining the recommendation weight of the target video candidate, and determining the difference between the recommendation weight of the target video candidate and the current recommendation weight; the recommendation weight of the candidate is determined based on the sum of the number of clicks and the click rate of the target video;

[0024] A weight adjustment probability corresponding to the difference is obtained; the weight adjustment probability is positively correlated with the difference.

[0025] In an exemplary embodiment, obtaining recommendation feedback results of multiple target videos displayed on a video recommendation page includes:

[0026] In response to an operation of pausing browsing of a video recommendation page, or in response to an operation of displaying a video playback page corresponding to a video in the video recommendation page, recommendation feedback results of multiple target videos displayed in the video recommendation page are obtained.

[0027] In an exemplary embodiment, obtaining recommendation feedback results of multiple target videos displayed on a video recommendation page includes:

[0028] Determining feedback behavior information of the user object on multiple target videos displayed on the video recommendation page, wherein the feedback behavior information includes at least one of the following: number of clicks, number of automatic plays, and play time;

[0029] Based on the feedback behavior information of each target video, the recommendation feedback result of each target video is obtained.

[0030] According to a second aspect of an embodiment of the present disclosure, a video playback device is provided, including:

[0031] A recommendation feedback result acquisition unit is configured to execute acquisition of recommendation feedback results of multiple target videos displayed in a video recommendation page; the video recommendation page displays multiple videos at the same time, and the multiple videos are played in sequence based on the size of the recommendation weights, and the recommendation feedback result represents the feedback behavior of the user object on the displayed target video;

[0032] A weight adjustment unit is configured to perform a feedback behavior characterized by a recommendation feedback result of each target video, adjust the recommendation weight corresponding to each target video, and obtain an adjusted recommendation weight; the order of the recommendation weights of the plurality of target videos after the adjustment is different from the order of the recommendation weights before the adjustment;

[0033] The target video playback unit is configured to execute a response to an event in which the multiple target videos are included again in the multiple videos displayed on the video recommendation page during browsing of the video recommendation page, and determine the target video to be played according to the size of the adjusted recommendation weight of each target video.

[0034] According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device, including:

[0035] processor;

[0036] a memory for storing instructions executable by the processor;

[0037] The processor is configured to execute the instructions to implement the video playback method as described in any one of the above items.

[0038] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute any of the video playback methods described above.

[0039] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided, wherein the computer program product includes instructions, and when the instructions are executed by a processor of an electronic device, the electronic device is enabled to execute any of the video playback methods described above.

[0040] The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects:

[0041] In the present disclosure, the terminal can timely adjust the recommendation weight of each target video according to the user's recommendation feedback results on the target videos displayed in the video recommendation page, so that the order of the recommendation weights of multiple target videos is changed. Therefore, when the same target videos are included in the video recommendation page again, they can be played in a different order to avoid playing fixed videos, thereby increasing the user's chances of browsing different videos and the probability of obtaining suitable videos, and improving the user's efficiency in obtaining suitable videos.

[0042] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0044] Figure 1 The diagram is a diagram of an application environment of a video playback method according to an exemplary embodiment.

[0045] Figure 2 The figure is a flowchart of a video playing method according to an exemplary embodiment.

[0046] Figure 3 The figure is an example diagram of a video recommendation page according to an exemplary embodiment.

[0047] Figure 4 The present invention is a flowchart showing a step of adjusting a recommendation weight according to an exemplary embodiment.

[0048] Figure 5 The present invention is a flowchart showing a step of obtaining a recommendation feedback result according to an exemplary embodiment.

[0049] Figure 6 The figure is a block diagram of a video playback device according to an exemplary embodiment.

[0050] Figure 7 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0051] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0052] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0053] It should also 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 display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0054] The video playback method provided by the present disclosure can be applied to Figure 1 In the application environment shown. In this application environment, the terminal can communicate with the server through the network. The server can have a corresponding data storage system, which can store data that the server needs to process, such as multiple videos and recommended weights for video configurations. In actual applications, the data storage system can be integrated on the server, or placed on the cloud or other network servers.

[0055] In the present disclosure, a terminal can obtain a video from a server and display the video on a video recommendation page to make a video recommendation, wherein the video recommendation page displays multiple videos at the same time, and the multiple videos on the video recommendation page are played in sequence based on the size of the recommendation weight. Then, the terminal can obtain the recommendation feedback results of the multiple target videos displayed on the video recommendation page, and the recommendation feedback results can characterize the feedback behavior of the user object on the displayed target video; then, the recommendation weight corresponding to each target video can be adjusted according to the feedback behavior characterized by the recommendation feedback result of each target video to obtain the adjusted recommendation weight, and the size order of the adjusted recommendation weights of the multiple target videos is different from the size order of the recommendation weights before the adjustment; in response to the event that multiple target videos are included again in the multiple videos displayed on the video recommendation page during the sliding process of the video recommendation page, the terminal can determine the target video to be played according to the size of the adjusted recommendation weights of each target video.

[0056] The terminals may be, but are not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices and portable wearable devices. IoT devices may be smart TVs, smart car devices, etc.; portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server may be implemented as an independent server or a server cluster consisting of multiple servers.

[0057] Figure 2 is a flowchart of a video playing method according to an exemplary embodiment. Figure 2 As shown, the video playback method in this embodiment is applied in a terminal and includes the following steps.

[0058] In step S210, recommendation feedback results of multiple target videos displayed on the video recommendation page are obtained; the video recommendation page displays multiple videos at the same time, and the multiple videos are played in sequence based on the size of the recommendation weights. The recommendation feedback results represent the feedback behavior of the user object on the displayed target videos.

[0059] In a specific implementation, the terminal can display a video recommendation page to the user object. The video recommendation page can be used to recommend and display videos. For example, the videos displayed on the video recommendation page can include recorded videos or live videos. Among them, at least two videos can be displayed on the video recommendation page at the same time. For example, for multiple videos displayed on the video recommendation page, a display window can be set for each video, and the video cover or video content can be displayed in the display window. In addition, the video recommendation page can also display relevant introduction information of the video, such as at least one of the following information: video name, video views, and video publisher.

[0060] When displaying multiple videos at the same time, the video recommendation page can automatically play multiple videos in the video recommendation page in sequence. Each video can have a corresponding recommendation weight, which can be a floating point number greater than 0 determined and issued by the server. The larger the value, the higher the priority of the play. In an optional embodiment, the server can obtain the recommendation weight based on the probability value of the video playback time exceeding the preset time threshold, wherein the probability value can be determined based on the relevant information of the user object (such as historical browsing records or interest preferences, etc.) or the popularity information of the video (such as at least one of the number of views, number of evaluations, and popularity).

[0061] Furthermore, when the terminal displays multiple videos through the video recommendation page, the multiple videos can be played in sequence based on the recommendation weights of the multiple videos. Figure 3 The video recommendation page of an embodiment is shown, in which four videos A, B, C, and D are displayed, and the recommendation weights of the four videos decrease in sequence. When the video recommendation page stays on the current page, the video content of the preset time can be played in the corresponding display area (such as the display window corresponding to the video) in the order of A, B, C, and D. For example, when the video recommendation page stays on Figure 3 When the page shown in the figure is displayed, the video content of video A can be played for 5 seconds in the display window of video A, then the video A can be paused, and then the video content of video B can be played for 5 seconds in the display window of video B. By obtaining the video recommendation weight and displaying according to the recommendation weight, the probability of users clicking to enter the video playback page to browse the details can be increased.

[0062] When the terminal displays multiple videos through a video recommendation page, the user object can give corresponding feedback to the multiple videos currently being displayed. For example, the user object may stay on the current video recommendation page for several seconds and browse the video content automatically played on the video recommendation page; for example, when the user object is interested in a video on the video recommendation page, the user can click on the display window of the video of interest to enter the video playback page of the video and browse the specific content of the video; of course, the user can also directly slide the video recommendation page to update the multiple videos displayed on the video recommendation page. Before the user slides the video recommendation page, one or more videos displayed on the video recommendation page may have been played or not played.

[0063] In this embodiment, for multiple target videos displayed on the video recommendation page, the terminal can obtain the recommendation feedback result corresponding to each target video, and the recommendation feedback result can reflect the feedback behavior of the user object on the target video. For example, it can be determined whether the displayed target video is played or clicked through the recommendation feedback result.

[0064] In step S220, the recommendation weight corresponding to each target video is adjusted according to the feedback behavior represented by the recommendation feedback result of each target video to obtain the adjusted recommendation weight; the order of the recommendation weights of the multiple target videos after the adjustment is different from the order of the recommendation weights before the adjustment.

[0065] After obtaining the recommendation feedback results for each target video, since the feedback behaviors represented by different recommendation feedback results are different, it can be indicated that for the multiple target videos displayed in the video recommendation page, the user object's attention level is also different. For example, for the target video that has been automatically played, the user object can passively pay more attention to the target video. In this step, the terminal can adjust the recommendation weight corresponding to each video according to the feedback behavior represented by the recommendation feedback results of each target video to obtain the adjusted recommendation weight. In one example, the terminal can be provided with a recommendation library, which can also be called a scattered library, which can be used to adjust the recommendation weight and sort and play the videos according to the recommendation weight.

[0066] For example, if the feedback behavior represented by the recommendation feedback result (for example, for negative feedback behavior, the user object has not clicked or played the video), indicates that the user object has a low level of attention to the target video, the user object has not noticed the video content in the target video, and there is a possibility that the user object ignores the video it needs, then the terminal can increase the recommendation weight of the target video; if the feedback behavior represented by the recommendation feedback result indicates that the user object has paid attention to the target video, then the terminal can lower the recommendation weight of the target video to avoid frequently and automatically recommending the same video to the user object. It can be understood that if the terminal adjusts the recommendation weight for the first time, the adjusted recommendation weight can be the recommendation weight of the target video issued by the server. If the terminal adjusts the recommendation weight again, such as after the first recommendation weight adjustment, the adjusted recommendation weight is the recommendation weight obtained after the terminal's last adjustment.

[0067] In the present disclosure, based on the feedback behaviors represented by different recommendation feedback results, there are differences in the adjustment direction and / or adjustment range of the recommendation weight. After adjusting the recommendation weight of each target video according to the recommendation feedback results and obtaining the adjusted recommendation weight, the order of the recommendation weights of the multiple target videos after the adjustment is different from the order of the recommendation weights of the multiple target videos before the adjustment. For example, the order of the recommendation weights of videos A, B, C, and D before adjustment is A>B>C>D, and the order of the recommendation weights after adjustment may be A>C>B>D.

[0068] In step S230, in response to an event that multiple target videos are included again in multiple videos displayed on the video recommendation page during browsing of the video recommendation page, the target video to be played is determined according to the size of the adjusted recommendation weight of each target video.

[0069] After adjusting the recommendation weights of multiple target videos, it can be determined whether a target event is detected during the user's browsing of the video recommendation page. The target event is that the multiple videos displayed on the video recommendation page again include the multiple target videos that have been displayed. For example, in the process of sliding the video recommendation page, the video recommendation page originally including multiple target videos is switched to the video recommendation page including other videos by sliding or clicking, and then returns to the video recommendation page originally including multiple target videos.

[0070] When multiple videos displayed on the video recommendation page include multiple target videos again, the terminal can determine the target video to be played according to the adjusted recommendation weights of the target videos, and play the target video.

[0071] For example, if the multiple videos in the video recommendation page only include multiple target videos that were originally displayed at the same time, the video playback order can be determined according to the sizes of the adjusted recommendation weights of the multiple target videos. The larger the recommendation weight, the higher the playback priority. Since the size order of the adjusted recommendation weights of the multiple target videos has changed, when the target videos to be played are determined based on the sizes of the adjusted recommendation weights, it is possible to avoid playing multiple target videos in a fixed order, thereby increasing the possibility of user objects browsing different videos and obtaining suitable videos. The number of times users watch different videos increases, which can improve the efficiency of users in obtaining suitable videos.

[0072] If the multiple videos in the video recommendation page include other videos in addition to the original multiple target videos displayed simultaneously, the video playback order can be determined according to the recommendation weights of the multiple target videos and other videos. In this case, although the video recommendation page also includes other videos, the relative playback order between the multiple target videos can still be determined based on the order of the adjusted recommendation weights of the multiple target videos, so that the user object can avoid playing the target videos in a fixed order when browsing multiple videos.

[0073] In the above-mentioned video playing method, the terminal can obtain the recommendation feedback results of multiple target videos displayed in the video recommendation page, and the video recommendation page displays multiple videos at the same time. The multiple videos are played in sequence based on the size of the recommendation weight, and the recommendation feedback result represents the feedback behavior of the user object on the displayed target video; then, according to the feedback behavior represented by the recommendation feedback result of each target video, the terminal can adjust the recommendation weight corresponding to each target video to obtain the adjusted recommendation weight, and the size order of the recommendation weights of the multiple target videos after the adjustment is different from the size order of the recommendation weights before the adjustment; then, in response to the event that the multiple target videos are included again in the multiple videos displayed on the video recommendation page during the browsing process of the video recommendation page, the target video to be played is determined according to the size of the recommendation weight adjusted for each target video. In the present disclosure, the terminal can timely adjust the recommendation weight of each target video according to the recommendation feedback result of the user on the target video displayed on the video recommendation page, so that the size order of the recommendation weights of the multiple target videos changes, so that when the same target video is included again in the video recommendation page, it can be played in a different order, avoiding the playback of fixed videos, increasing the opportunity for users to browse different videos and the probability of obtaining suitable videos, and improving the efficiency of users to obtain suitable videos.

[0074] In an exemplary embodiment, in step S220, adjusting the recommendation weight corresponding to each target video according to the feedback behavior represented by the recommendation feedback result of each target video to obtain the adjusted recommendation weight may include the following steps:

[0075] If the recommendation feedback result of the target video indicates that the target video has not been played, the recommendation weight corresponding to the target video is increased to obtain an adjusted recommendation weight.

[0076] In a specific implementation, the target video in the video recommendation page may be displayed but not played. Specifically, the multiple target videos displayed on the video recommendation page can be automatically played when a preset trigger condition is met, such as staying on the current video recommendation page for more than a preset time. In some possible embodiments, after the video recommendation page displays multiple target videos, the user object quickly scrolls down the video recommendation page, such as scrolling down the page before the target video displayed on the video recommendation page starts to play automatically or scrolling down the page while part of the target video is playing, so that at least some of the target videos in the video recommendation page are not played.

[0077] In case that the recommendation feedback result indicates that the target video has not been played, the terminal may increase the recommendation weight corresponding to the target video, and use the increased recommendation weight as the adjusted recommendation weight.

[0078] In this embodiment, by increasing the recommendation weight corresponding to the target video that has not been played, an adjusted recommendation weight is obtained, which can increase the probability of the target video that has not been played being browsed by the user, avoid the target video recommended in the video recommendation page from being unable to be browsed by the user, and improve the user's chance of obtaining a suitable video.

[0079] In an exemplary embodiment, increasing the recommendation weight corresponding to the target video to obtain the adjusted recommendation weight may include the following steps:

[0080] The sum of the preset weight increase coefficient and the recommendation weight corresponding to the target video is obtained as the adjusted recommendation weight.

[0081] In a specific implementation, a weight increase coefficient may be preset, and the weight increase coefficient is a value greater than 0, for example, 1. Exemplarily, the value of the weight increase coefficient may be obtained by statistically analyzing the recommendation weights of multiple videos. For example, the range and the lower limit of the range may be determined based on the recommendation weights of multiple videos, and the product of the lower limit of the range and the preset percentage may be used as the weight increase coefficient, so that when the recommendation weight is increased, the recommendation weight may be increased according to a suitable gradient.

[0082] After obtaining the weight increase coefficient, the weight increase coefficient and the recommendation weight corresponding to the target video may be summed, and the sum of the two may be used as the adjusted recommendation weight.

[0083] In this embodiment, by taking the sum of the preset weight increase coefficient and the recommendation weight corresponding to the target video as the adjusted recommendation weight, the weight increase coefficient and the recommendation weight of the target video can be successively accumulated in an additive manner to avoid a one-time sharp increase in the recommendation weight, thereby achieving imperceptible recommendation weight adjustment.

[0084] In an exemplary embodiment, in step S220, adjusting the recommendation weight corresponding to each target video according to the feedback behavior represented by the recommendation feedback result of each target video to obtain the adjusted recommendation weight may include the following steps:

[0085] If the recommendation feedback result of the target video indicates that the target video has been automatically played, the predetermined recommendation weight of the target video is reduced to obtain an adjusted recommendation weight.

[0086] In actual applications, the target video in the video recommendation page can be automatically played when the preset trigger conditions are met. For example, when the current video recommendation page stays for more than a preset time, the corresponding videos are automatically played in the display window in the video recommendation page according to the recommendation weight of each target video.

[0087] If the recommendation feedback result of the target video indicates that the target video has been automatically played, the terminal may reduce the recommendation weight of the target video to obtain an adjusted recommendation weight.

[0088] In this embodiment, by reducing the recommendation weight of the target video that has been automatically played, an adjusted recommendation weight is obtained. This can reduce the playback priority of the target video when the target video has been played, increase the probability that the unplayed video will be browsed by the user first, and give the user the opportunity to browse multiple different videos and select a suitable video to watch, thereby ensuring fairness in the video recommendation process.

[0089] In an exemplary embodiment, reducing a predetermined recommendation weight of a target video to obtain an adjusted recommendation weight may include the following steps:

[0090] The ratio of the recommendation weight corresponding to the target video to the predetermined weight reduction coefficient is obtained as the adjusted recommendation weight.

[0091] In a specific implementation, a weight reduction coefficient may be pre-set. The weight reduction coefficient may also be called a decay factor. The appropriate weight reduction coefficient may be determined by combining the record of the past historical reduction of the recommendation weight and the feedback behavior of the user object on the video after the adjustment.

[0092] In this embodiment, if the recommendation feedback result of the target video indicates that the target video has been played automatically, the terminal can obtain a predetermined weight reduction coefficient, and determine the ratio of the recommendation weight corresponding to the target video to the weight reduction coefficient (i.e., the recommendation weight divided by the weight reduction coefficient), and use the ratio as the adjusted recommendation weight.

[0093] In this embodiment, by taking the ratio of the recommendation weight corresponding to the target video and the predetermined weight reduction coefficient as the adjusted recommendation weight, the recommendation weight of the target video that has been played can be quickly reduced in a multiplicative manner, significantly increasing the chances of other weighted videos that have not been played to obtain priority playback, allowing users to have the opportunity to browse multiple different videos and select a suitable video to watch.

[0094] In an exemplary embodiment, if Figure 4 As shown, in step S220, according to the feedback behavior represented by the recommendation feedback result of each target video, the recommendation weight corresponding to each target video is adjusted to obtain the adjusted recommendation weight, which may include the following steps:

[0095] In step S410, if the recommendation feedback result of the target video indicates that the target video has been clicked, the number of clicks on the target video is obtained.

[0096] In step S420, the weight adjustment probability corresponding to the number of clicks is determined.

[0097] As an example, the weight adjustment probability can be understood as the probability of the event of adjusting the recommendation weight.

[0098] In a specific implementation, if the recommendation feedback result of the target video indicates that the target video has been clicked by the user object, although the click on the target video is actively triggered by the user object, the click behavior of the user object on the target video is not necessarily a positive signal; for example, if the user is interested in the target video and intends to watch the specific video content, he can click on the display area of ​​the target video in the video recommendation page and enter the specific video playback page. For example, when the user accidentally touches the target video, he will also click on the target video.

[0099] Based on this, when the recommendation feedback result of the target video indicates that the target video has been clicked, the terminal can obtain the number of clicks of the target video and determine the weight adjustment probability corresponding to the number of clicks, so as to probabilistically adjust the recommendation weight of the target video according to the weight adjustment probability.

[0100] In step S430, if the pre-acquired random number is less than the weight adjustment probability, the recommendation weight corresponding to the target video is adjusted to obtain an adjusted recommendation weight.

[0101] Specifically, after obtaining the weight adjustment probability, a random number can be obtained, which can be a random number in the range of [0,1]. Then, the pre-obtained random number can be compared with the weight adjustment probability. If the random number is less than the weight adjustment probability, the recommendation weight corresponding to the target video can be adjusted, and the adjusted recommendation weight can be obtained; if the random number is greater than or equal to the weight adjustment probability, the terminal does not adjust the recommendation weight corresponding to the target video, but keeps the current recommendation weight of the target video unchanged.

[0102] In this embodiment, if the recommendation feedback result of the target video indicates that the target video has been clicked, the probability can be adjusted according to the weight corresponding to the number of clicks, and the recommendation weight of the target video can be adjusted probabilistically to avoid continuously increasing the recommendation weight when the click behavior may be a non-positive signal, thereby affecting the user's browsing of other videos.

[0103] In an exemplary embodiment, in step S320, determining the weight adjustment probability corresponding to the number of clicks may include the following steps:

[0104] The recommendation weight of the target video candidate is obtained, and the difference between the recommendation weight of the target video candidate and the current recommendation weight is determined; the weight adjustment probability corresponding to the difference is obtained; and the weight adjustment probability is positively correlated with the difference.

[0105] The recommendation weight of the candidate may be determined based on the sum of the number of clicks and the click rate of the target video.

[0106] In actual applications, the terminal can determine the number of clicks and click-through rate of the target video, and then determine the recommendation weight of the candidate based on the sum of the number of clicks and the click-through rate. It can be understood that the greater the number of clicks or the click-through rate, the greater the recommendation weight of the target video candidate, that is, the recommendation weight of the candidate can be positively correlated with the number of clicks and the click-through rate. In one example, the recommendation weight of the candidate can be determined based on the following method:

[0107] Candidate recommendation weight = number of clicks + number of clicks / (number of exposures + 1.0)

[0108] After obtaining the recommendation weight of the target video candidate, the weight adjustment probability can be determined using the idea of ​​simulated annealing algorithm, so that the adjustment of the recommendation weight has convergence. Specifically, the difference between the recommendation weight of the target video candidate and the current recommendation weight can be obtained, and the difference can be substituted into the preset algorithm to obtain the weight adjustment probability corresponding to the difference, wherein the weight adjustment probability obtained by the algorithm is positively correlated with the difference. It can be understood that since the current recommendation weight of the target video has been predetermined, the larger the recommendation weight of the candidate, the greater the weight adjustment probability, and the recommendation weight of the candidate is positively correlated with the number of clicks and click-through rate, therefore, the weight adjustment probability is also positively correlated with the number of clicks and click-through rate. In one example, the method for determining the weight adjustment probability can be as follows:

[0109] P=1 / 1+e^(-Δw)

[0110] Among them, Δw is the difference, e is a natural constant, and P is the weight adjustment probability.

[0111] In this embodiment, the difference between the candidate recommendation weight of the target video and the current recommendation weight can be determined, and the weight adjustment probability can be obtained based on the difference. The weight adjustment probability is positively correlated with the difference, so that the weight adjustment probability can change with the number of clicks and click-through rate of the target video, thereby associating the video recommendation method with user behavior.

[0112] In an exemplary embodiment, in step S210, obtaining recommendation feedback results of multiple target videos displayed on the video recommendation page may include:

[0113] In response to an operation of pausing browsing of a video recommendation page, or in response to an operation of displaying a video playback page corresponding to a video in the video recommendation page, recommendation feedback results of multiple target videos displayed in the video recommendation page are obtained.

[0114] In this embodiment, after the terminal displays the video recommendation page, the user can continue to browse the video recommendation page to browse different displayed target videos, or click on a video in the video recommendation page.

[0115] When the terminal detects an operation of pausing browsing of a video recommendation page, such as pausing sliding a video recommendation page, it can be determined that the user object's feedback behavior on the video recommendation page is temporarily stopped, and at this time, the recommendation feedback results of multiple target videos displayed on the video recommendation page can be obtained in time; or, when the terminal detects an operation of displaying a specific video playback page of a video in a video recommendation page, such as entering the video playback page by clicking on the video, since the page currently displayed by the terminal will switch, it can also be determined that the user object's feedback behavior on the current video recommendation page is temporarily stopped, so that the recommendation feedback results of the target video in the video recommendation page can be obtained.

[0116] Accordingly, when browsing the video recommendation page and returning to the video recommendation page containing multiple target videos, or returning to the video recommendation page by exiting the video playback page, the target video to be played can be determined according to the adjusted recommendation weight.

[0117] In this embodiment, by obtaining recommendation feedback results of multiple target videos displayed on the video recommendation page when pausing the browsing of the video recommendation page or displaying the video playback page, the recommendation weight can be adjusted in time according to the user operation while avoiding hindering the user from normally browsing the videos on the video recommendation page.

[0118] In an exemplary embodiment, if Figure 5 As shown, in step S210, obtaining recommendation feedback results of multiple target videos displayed on the video recommendation page may include:

[0119] In step S510, feedback behavior information of a user object on a plurality of target videos displayed on a video recommendation page is determined.

[0120] The feedback behavior information includes at least one of the following: whether to click, the number of clicks, whether to play automatically, the number of automatic plays, and the playing time.

[0121] In a specific implementation, the feedback behavior information of the user object on each target video displayed on the video recommendation page can be determined. For example, when the user object clicks on the target video, the number of clicks on the target video can be updated and recorded; for another example, it can be obtained through the function callback of the first frame when the terminal player pulls the video stream. After receiving the callback, the terminal can set whether the target video has been played to true and update the number of automatic plays to 1; in addition, the terminal can also obtain the number of exposures of the target video. For example, when the video recommendation page is scrolling, if a callback is received for the willdisplay function of the target video, the number of exposures of the target video can be increased by 1.

[0122] In step S520, based on the feedback behavior information of each target video, a recommendation feedback result of each target video is obtained.

[0123] After obtaining the feedback behavior information of the target video, based on the feedback behavior information of each target video, the recommended feedback result of each target video is obtained. For example, the feedback behavior information can be used as the recommended feedback result, or the feedback behavior information can be further statistically processed to obtain the type of feedback behavior of the user object, and the type of feedback behavior can be used as the recommended feedback result.

[0124] In this embodiment, when the user browses the video recommendation page, the terminal can collect the user's feedback behavior information on the recommended target video in real time, which can provide a reliable basis for the subsequent adjustment of the recommendation weight.

[0125] In order to enable those skilled in the art to better understand the above steps, the embodiment of the present disclosure is illustrated below by using an example, but it should be understood that the embodiment of the present disclosure is not limited thereto.

[0126] The terminal can display the following information through the client: Figure 3 The video recommendation interface shown includes videos A, B, C, and D. The terminal can obtain in advance from the server that the recommendation weights of videos A, B, C, and D are 9, 8, 7, and 6 respectively.

[0127] When users browse the video recommendation page, Figure 3 The dwell time on the video recommendation page shown meets the trigger condition, triggering the client to automatically play the videos on the video recommendation page according to the size of the recommendation weight (in descending order), and the terminal automatically plays video A at this time.

[0128] When videos B, C, and D are not played, the user slides down the video recommendation page. When the user stops sliding down the video recommendation page, the terminal collects the recommendation feedback results of videos A, B, C, and D. Specifically, since video A has been played, the preset weight reduction coefficient is 2. According to the recommendation weight reduction method: adjusted recommendation weight = original recommendation weight / max(1.0, weight reduction coefficient), the recommendation weight of video A is adjusted to 4.5; and since videos B, C, and D have not been played, their corresponding recommendation weights are added by 1 on the basis of the original recommendation weights, and the adjusted recommendation weights of videos B, C, and D are 9, 8, and 7 respectively.

[0129] When the user swipes back to Figure 3 When the video recommendation page shown in the figure is displayed, if the triggering conditions for automatically playing the video are met, video B will be played first according to the adjusted recommendation weight.

[0130] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0131] It can be understood that the same / similar parts between the various embodiments of the above method in this specification can refer to each other, and each embodiment focuses on the differences from other embodiments. For related points, please refer to the description of other method embodiments.

[0132] Based on the same inventive concept, the embodiment of the present disclosure also provides a video playback device for implementing the above-mentioned video playback method.

[0133] Figure 6 is a block diagram of a video playback device according to an exemplary embodiment. Figure 6 The device includes a recommendation feedback result acquisition unit 601, a weight adjustment unit 602 and a target video playback unit 603.

[0134] The recommendation feedback result acquisition unit 601 is configured to execute acquisition of recommendation feedback results of multiple target videos displayed in a video recommendation page; the video recommendation page displays multiple videos at the same time, and the multiple videos are played in sequence based on the size of the recommendation weights, and the recommendation feedback result represents the feedback behavior of the user object on the displayed target video;

[0135] The weight adjustment unit 602 is configured to perform a feedback behavior represented by the recommendation feedback result of each target video, adjust the recommendation weight corresponding to each target video, and obtain an adjusted recommendation weight; the order of the recommendation weights of the plurality of target videos after the adjustment is different from the order of the recommendation weights before the adjustment;

[0136] The target video playback unit 603 is configured to execute a response to an event in which the multiple target videos are included again in the multiple videos displayed on the video recommendation page during browsing of the video recommendation page, and determine the target video to be played according to the size of the adjusted recommendation weight of each target video.

[0137] In an exemplary embodiment, the weight adjustment unit 602 includes:

[0138] The weight increasing module is configured to increase the recommendation weight corresponding to the target video if the recommendation feedback result of the target video indicates that the target video has not been played, so as to obtain an adjusted recommendation weight.

[0139] In an exemplary embodiment, the weight increasing module is configured to execute:

[0140] The sum of the preset weight increase coefficient and the recommendation weight corresponding to the target video is obtained as the adjusted recommendation weight.

[0141] In an exemplary embodiment, the weight adjustment unit 602 includes:

[0142] The weight reduction module is configured to reduce a predetermined recommendation weight of the target video to obtain an adjusted recommendation weight if the recommendation feedback result of the target video indicates that the target video has been automatically played.

[0143] In an exemplary embodiment, the weight reduction module is configured to execute:

[0144] The ratio of the recommendation weight corresponding to the target video to the predetermined weight reduction coefficient is obtained as the adjusted recommendation weight.

[0145] In an exemplary embodiment, the weight adjustment unit 602 includes:

[0146] A click count acquisition module is configured to execute, if the recommendation feedback result of the target video indicates that the target video has been clicked, to acquire the number of clicks of the target video;

[0147] A probability determination module is configured to determine a weight adjustment probability corresponding to the number of clicks;

[0148] The random adjustment module is configured to adjust the recommendation weight corresponding to the target video if the pre-acquired random number is less than the weight adjustment probability, so as to obtain the adjusted recommendation weight.

[0149] In an exemplary embodiment, the probability determination module is configured to perform:

[0150] Obtaining the recommendation weight of the target video candidate, and determining the difference between the recommendation weight of the target video candidate and the current recommendation weight; the recommendation weight of the candidate is determined based on the sum of the number of clicks and the click rate of the target video;

[0151] A weight adjustment probability corresponding to the difference is obtained; the weight adjustment probability is positively correlated with the difference.

[0152] In an exemplary embodiment, the recommendation feedback result acquisition unit 601 is configured to execute:

[0153] In response to an operation of pausing browsing of a video recommendation page, or in response to an operation of displaying a video playback page corresponding to a video in the video recommendation page, recommendation feedback results of multiple target videos displayed in the video recommendation page are obtained.

[0154] In an exemplary embodiment, the recommendation feedback result acquisition unit 601 is configured to execute:

[0155] Determining feedback behavior information of the user object on multiple target videos displayed on the video recommendation page, wherein the feedback behavior information includes at least one of the following: number of clicks, number of automatic plays, and play time;

[0156] Based on the feedback behavior information of each target video, the recommendation feedback result of each target video is obtained.

[0157] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0158] Each module in the above video playback device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0159] Figure 7 1 is a block diagram of an electronic device 700 for implementing a video playback method according to an exemplary embodiment. For example, the electronic device 700 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0160] Reference Figure 7 , the electronic device 700 may include one or more of the following components: a processing component 702 , a memory 704 , a power component 706 , a multimedia component 708 , an audio component 710 , an input / output (I / O) interface 712 , a sensor component 714 , and a communication component 716 .

[0161] The processing component 702 generally controls the overall operation of the electronic device 700, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 702 may include one or more processors 720 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 702 may include one or more modules to facilitate the interaction between the processing component 702 and other components. For example, the processing component 702 may include a multimedia module to facilitate the interaction between the multimedia component 708 and the processing component 702.

[0162] The memory 704 is configured to store various types of data to support operations on the electronic device 700. Examples of such data include instructions for any application or method operating on the electronic device 700, contact data, phone book data, messages, pictures, videos, etc. The memory 704 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk, an optical disk, or a graphene memory.

[0163] The power supply component 706 provides power to the various components of the electronic device 700. The power supply component 706 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 700.

[0164] The multimedia component 708 includes a screen that provides an output interface between the electronic device 700 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 708 includes a front camera and / or a rear camera. When the electronic device 700 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0165] The audio component 710 is configured to output and / or input audio signals. For example, the audio component 710 includes a microphone (MIC), and when the electronic device 700 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 704 or sent via the communication component 716. In some embodiments, the audio component 710 also includes a speaker for outputting an audio signal.

[0166] I / O interface 712 provides an interface between processing component 702 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0167] The sensor assembly 714 includes one or more sensors for providing various aspects of status assessment for the electronic device 700. For example, the sensor assembly 714 can detect the open / closed state of the electronic device 700, the relative positioning of the components, such as the display and keypad of the electronic device 700, and the sensor assembly 714 can also detect the position change of the electronic device 700 or the components of the electronic device 700, the presence or absence of contact between the user and the electronic device 700, the orientation or acceleration / deceleration of the device 700, and the temperature change of the electronic device 700. The sensor assembly 714 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 714 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 714 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0168] The communication component 716 is configured to facilitate wired or wireless communication between the electronic device 700 and other devices. The electronic device 700 can access a wireless network based on a communication standard, such as WiFi, a carrier network (such as 2G, 3G, 4G or 5G), or a combination thereof. In an exemplary embodiment, the communication component 716 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 716 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0169] In an exemplary embodiment, the electronic device 700 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0170] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 704 including instructions, and the above instructions can be executed by the processor 720 of the electronic device 700 to perform the above method. For example, the computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0171] In an exemplary embodiment, a computer program product is further provided. The computer program product includes instructions. The instructions can be executed by the processor 720 of the electronic device 700 to complete the above method.

[0172] It should be noted that the above-mentioned devices, electronic devices, computer-readable storage media, computer program products, etc. may also include other implementation methods according to the description of the method embodiments. The specific implementation methods can refer to the description of the relevant method embodiments, which will not be described one by one here.

[0173] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

[0174] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A video playback method, characterized in that: include: Obtain recommendation feedback results for multiple target videos displayed on the video recommendation page; The video recommendation page displays multiple videos at the same time, and the multiple videos are played in sequence based on the size of the recommendation weights. The recommendation feedback result represents the feedback behavior of the user object on the displayed target video; If the recommendation feedback result of the target video indicates that the target video has been clicked, obtaining the number of clicks of the target video; Determine a weight adjustment probability corresponding to the number of clicks; If the pre-acquired random number is less than the weight adjustment probability, the recommendation weight corresponding to the target video is adjusted to obtain an adjusted recommendation weight; the order of the recommendation weights of the plurality of target videos after the adjustment is different from the order of the recommendation weights before the adjustment; In response to an event that the multiple target videos are included again in the multiple videos displayed on the video recommendation page during browsing of the video recommendation page, the target videos to be played are determined according to the sizes of the adjusted recommendation weights of the respective target videos.

2. The method according to claim 1, characterized in that Also includes: If the recommendation feedback result of the target video indicates that the target video has not been played, the recommendation weight corresponding to the target video is increased to obtain an adjusted recommendation weight.

3. The method according to claim 2, characterized in that The step of increasing the recommendation weight corresponding to the target video to obtain an adjusted recommendation weight includes: The sum of the preset weight increase coefficient and the recommendation weight corresponding to the target video is obtained as the adjusted recommendation weight.

4. The method according to claim 1, characterized in that: Also includes: If the recommendation feedback result of the target video indicates that the target video has been automatically played, the predetermined recommendation weight of the target video is reduced to obtain an adjusted recommendation weight.

5. The method according to claim 4, characterized in that The step of reducing the predetermined recommendation weight of the target video to obtain an adjusted recommendation weight includes: The ratio of the recommendation weight corresponding to the target video to the predetermined weight reduction coefficient is obtained as the adjusted recommendation weight.

6. The method according to claim 1, characterized in that The determining of the weight adjustment probability corresponding to the number of clicks includes: Obtaining the recommendation weight of the target video candidate, and determining the difference between the recommendation weight of the target video candidate and the current recommendation weight; the recommendation weight of the candidate is determined based on the sum of the number of clicks and the click rate of the target video; A weight adjustment probability corresponding to the difference is obtained; the weight adjustment probability is positively correlated with the difference.

7. The method according to any one of claims 1 to 6, characterized in that: The step of obtaining recommendation feedback results of multiple target videos displayed on the video recommendation page includes: In response to an operation of pausing browsing of a video recommendation page, or in response to an operation of displaying a video playback page corresponding to a video in the video recommendation page, recommendation feedback results of multiple target videos displayed in the video recommendation page are obtained.

8. The method according to claim 1, characterized in that The step of obtaining recommendation feedback results of multiple target videos displayed on the video recommendation page includes: Determining feedback behavior information of the user object on multiple target videos displayed on the video recommendation page, wherein the feedback behavior information includes at least one of the following: number of clicks, number of automatic plays, and play time; Based on the feedback behavior information of each target video, the recommendation feedback result of each target video is obtained.

9. A video playback device, characterized in that: include: A recommendation feedback result acquisition unit is configured to execute acquisition of recommendation feedback results of multiple target videos displayed on the video recommendation page; The video recommendation page displays multiple videos at the same time, and the multiple videos are played in sequence based on the size of the recommendation weights. The recommendation feedback result represents the feedback behavior of the user object on the displayed target video; A weight adjustment unit is configured to execute, if the recommendation feedback result of the target video indicates that the target video has been clicked, obtaining the number of clicks on the target video; Determine a weight adjustment probability corresponding to the number of clicks; if the pre-acquired random number is less than the weight adjustment probability, adjust the recommendation weight corresponding to the target video to obtain an adjusted recommendation weight; the order of the recommended weights of the plurality of target videos after the adjustment is different from the order of the recommended weights before the adjustment; The target video playback unit is configured to execute a response to an event in which the multiple target videos are included again in the multiple videos displayed on the video recommendation page during browsing of the video recommendation page, and determine the target video to be played according to the size of the adjusted recommendation weight of each target video.

10. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the method as claimed in any one of claims 1 to 8.

Images