Video display method and device, electronic equipment and storage medium

Abstract

The invention relates to the field of video display, and provides a video display method and device, electronic equipment and a storage medium. The method comprises the steps that in response to the fact that a service request of an application is triggered, configuration information of the service request is obtained, and the configuration information indicates whether the service request relates to use of real-time features or not; when the service request relates to the use of the real-time features, service parameters in the service request are updated, the updated service parameters represent the features of the operation performed by the user on the application, and the features are related to the service request; the updated service request is sent to a server, a service response from the server is received, and the service response comprises a plurality of videos to be displayed related to the updated service parameters and a recommendation sequence of the videos to be displayed; and displaying the to-be-displayed videos in the recommendation sequence. In this case, the server can obtain real-time user data and give a recommendation result with better quality, thereby improving the user experience.

Description

Technical Field

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

[0002] As the content on video playback platforms becomes increasingly rich and diverse, it becomes more difficult for users to actively find content they are interested in in the video library. Therefore, filtering and sorting the content that users are interested in and recommending the selected content to users have become the key to improving user experience.

[0003] Users’ interests are constantly changing, so the real-time nature of user data is crucial to the effectiveness of content recommendations. In the prior art, cloud servers can recommend content to users based on user data in a personalized manner, but the user data obtained by cloud servers may not be real-time enough, resulting in reduced recommendation effectiveness and user experience. In addition, cloud servers generally need to set up a dedicated data collection interface to obtain user data, which has a high collection cost. Summary of the invention

[0004] In view of this, the present disclosure proposes a video display method, device, electronic device and storage medium.

[0005] According to one aspect of the present disclosure, a video display method is provided, the method is applied to a user device, an application for displaying videos is run on the user device, the method comprising: in response to a service request of the application being triggered, obtaining configuration information of the service request, the configuration information indicating whether the service request involves the use of real-time features; when the service request involves the use of real-time features, updating service parameters in the service request, and sending the updated service request to a server, wherein the updated service parameters represent characteristics of the user's operation on the application, and the characteristics are related to the service request; receiving a service response from the server, the service response including a plurality of videos to be displayed related to the updated service parameters and a recommended order of the videos to be displayed; and displaying the videos to be displayed in the recommended order.

[0006] In one possible implementation, the user device also includes a feature pool, which records the characteristics of the user's operations on the application; when the service request involves the use of real-time features, the service parameters in the service request are updated, including: when the service request involves the use of real-time features, obtaining characteristics related to the service request from the feature pool, and updating the service parameters in the service request based on the obtained characteristics.

[0007] In one possible implementation, the user device includes a user database, which stores user logs. The method also includes: updating the user log according to the user's operation on the application; in response to the application being started, loading an event monitoring script, wherein the event monitoring script is used to monitor events that reflect user interests; when the event monitoring script monitors the event, reading all or part of the user log from the user database, and updating the feature pool according to the read user log.

[0008] In a possible implementation, the event includes at least one of a click event and a playback end event not triggered by the user.

[0009] In a possible implementation, the event monitoring script includes one or more of a Python script and a JavaScript script.

[0010] In one possible implementation, the user device includes a user database, which stores user logs. The method also includes: updating the user logs according to the user's operation on the application; in response to the application being started, reading all or part of the user logs from the user database at every preset time period, and updating the feature pool according to the read user logs.

[0011] In one possible implementation, the feature pool includes one or more of a list of series videos played by a user, a list of independent videos played by a user, a list of videos liked by a user, a list of video publishers followed by a user, a list of videos collected by a user, a list of videos shared by a user, and a list of videos searched by a user. The series video is a video that belongs to the same series as other videos, and the independent video is a video that does not belong to the same series as other videos.

[0012] In a possible implementation, the characteristics of the operation performed by the user on the application include characteristics of the operation collected within the latest preset time range.

[0013] In one possible implementation, when the service request involves the use of real-time features, it is triggered by at least one of the following operations of the user on the application: jumping to the video recommendation page, swiping up on the video recommendation page, and swiping down on the video recommendation page.

[0014] According to another aspect of the present disclosure, a video display device is provided, which is applied to a user device, and an application for displaying videos is run on the user device, and the device includes: a first acquisition module, which is used to obtain configuration information of the service request in response to a service request of the application being triggered, and the configuration information indicates whether the service request involves the use of real-time features; a first update module, which is used to update service parameters in the service request when the service request involves the use of real-time features, and send the updated service request to a server, wherein the updated service parameters represent characteristics of the user's operation on the application, and the characteristics are related to the service request; a receiving module, which is used to receive a service response from the server, and the service response includes multiple videos to be displayed related to the updated service parameters and a recommended order of each video to be displayed; and a display module, which is used to display each video to be displayed in the recommended order.

[0015] In one possible implementation, the user device also includes a feature pool, which records the characteristics of the user's operations on the application; when the service request involves the use of real-time features, the service parameters in the service request are updated, including: when the service request involves the use of real-time features, obtaining characteristics related to the service request from the feature pool, and updating the service parameters in the service request based on the obtained characteristics.

[0016] In one possible implementation, the user device includes a user database, which stores user logs. The apparatus also includes: a second update module, which is used to update the user log according to the user's operation on the application; a loading module, which is used to load an event monitoring script in response to the application being started, and the event monitoring script is used to monitor events that reflect user interests; a third update module, which is used to read all or part of the user log from the user database when the event monitoring script monitors the event, and update the feature pool according to the read user log.

[0017] In a possible implementation, the event includes at least one of a click event and a playback end event not triggered by the user.

[0018] In a possible implementation, the event monitoring script includes one or more of a Python script and a JavaScript script.

[0019] In one possible implementation, the user device includes a user database, which stores user logs. The apparatus also includes: a fourth update module, which is used to update the user log according to the user's operation on the application; and a fifth update module, which is used to read all or part of the user log from the user database at every preset time period in response to the application being started, and update the feature pool according to the read user log.

[0020] In one possible implementation, the feature pool includes one or more of a list of series videos played by a user, a list of independent videos played by a user, a list of videos liked by a user, a list of video publishers followed by a user, a list of videos collected by a user, a list of videos shared by a user, and a list of videos searched by a user. The series video is a video that belongs to the same series as other videos, and the independent video is a video that does not belong to the same series as other videos.

[0021] In a possible implementation, the characteristics of the operation performed by the user on the application include characteristics of the operation collected within the latest preset time range.

[0022] In one possible implementation, when the service request involves the use of real-time features, it is triggered by at least one of the following operations of the user on the application: jumping to the video recommendation page, swiping up on the video recommendation page, and swiping down on the video recommendation page.

[0023] According to another aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0024] According to another aspect of the present disclosure, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored, wherein the computer program instructions implement the above method when executed by a processor.

[0025] According to another aspect of the present disclosure, a computer program product is provided, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0026] According to the video display method of the embodiment of the present disclosure, in response to the service request of the application being triggered, the configuration information of the service request is obtained, and when the configuration information indicates that the service request involves the use of real-time features, the service parameters in the service request are updated so that the updated service parameters represent the features of the user's operations on the application that are related to the service request. The updated service request is sent to the server. In this case, the service request obtained by the server can include real-time user data (i.e., updated service parameters). The server can determine the service response based on the service request and send the service response to the user device. The service response includes multiple videos to be displayed related to the updated service parameters and the recommended order of each video to be displayed. The service response at this time is a better quality recommendation result that the server can give based on real-time user data, which can improve the user experience.

[0027] In the embodiment of the disclosure, when the configuration information indicates that the service request involves the use of real-time features, the service parameters in the service request are updated and the real-time user data is uploaded to the server. The action of returning the real-time user data to the server is cleverly limited to the time when the service request is triggered and the service request involves the use of real-time features. The timing of data return and the algorithm requirements of the server are accurately synchronized, and the characteristics of updating the service parameters are related to the service request. Therefore, the data utilization rate is higher, the timeliness, real-time and accuracy of user data provision are guaranteed, and there is no need to regularly transmit a large amount of invalid user data to the server. The processing cost is effectively dispersed on each user device, and the user device dynamically releases real-time user data based on actual service needs and using service requests, which reduces the data transmission pressure and processing pressure of the server and improves the system response speed and efficiency. In addition, the method does not need to add hardware resources for collecting user data on the server, thereby reducing the cost of the server. The service request obtained by the server already includes real-time user data (service parameters), so the server does not need to obtain user data additionally, and can directly execute the recommendation algorithm based on the service parameters, which improves the response speed and response efficiency of the server.

[0028] In summary, the video display method disclosed in the present invention recommends videos that are more compatible with the user's interests to the user, which is conducive to extending the user's stay time on the first application and strengthening user stickiness. In addition, the recommendation algorithm can also adjust the delivery strategy of the advertising video according to the updated service parameters, so that the advertising video can be presented at a time when the user is more interested in the video and at a location where the user is more likely to notice, thereby improving the delivery effect of the advertising video. The video display method disclosed in the present invention makes full use of the computing resources of the user's device, provides more real-time data for the server running the recommendation algorithm, greatly enhances the recommendation effect of the recommendation algorithm, and is conducive to the intelligent and personalized video recommendation.

[0029] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0031] Figure 1 An exemplary application scenario of the video display method according to an embodiment of the present disclosure is shown.

[0032] Figure 2 A schematic diagram showing the process of a video display method according to an embodiment of the present disclosure.

[0033] Figure 3 A schematic diagram showing a user equipment acquiring configuration information according to an embodiment of the present disclosure.

[0034] Figure 4 A schematic diagram showing updating a feature pool according to an embodiment of the present disclosure is shown.

[0035] Figure 5 A schematic diagram showing the structure of a video display device according to an embodiment of the present disclosure.

[0036] Figure 6 A block diagram of an electronic device 1900 according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0037] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0038] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0039] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present disclosure.

[0040] As described above, in the prior art, a cloud server can recommend content to users based on user data in a personalized manner according to a service request triggered by the user. However, the user data obtained by the cloud server may not be real-time enough, resulting in reduced recommendation effect and a lower user experience.

[0041] In addition, some existing technologies also propose to set up a special data collection interface on the cloud server, which is responsible for collecting the characteristics of the user's operation on the application so that the cloud server can obtain real-time user data. However, the new interface also makes the collection cost higher.

[0042] In view of this, the present disclosure proposes a video display method, device, electronic device and storage medium. The method enables the service request obtained by the server to include real-time user data, so that the server can give a better quality recommendation result based on the real-time user data, and when the user device displays the recommendation result, the user experience can be improved. The embodiment of the present disclosure cleverly limits the action of real-time user data backflow to the server to the time when the service request is triggered and the service request involves the use of real-time features, accurately synchronizes the timing of data backflow and server algorithm requirements, and the characteristics of updating service parameters are related to the service request, so the data utilization rate is higher, and the timeliness, real-time and accuracy of user data provision are guaranteed. There is no need to regularly transmit a large amount of invalid user data to the server, and the processing cost is effectively distributed on each user device. The user device dynamically publishes real-time user data based on actual service needs and using service requests, which reduces the data transmission pressure and processing pressure on the server, and improves the system response speed and efficiency. In addition, the method does not need to add hardware resources for collecting user data on the server, thereby reducing the cost of the server. The service request received by the server already includes real-time user data (service parameters), so the server does not need to obtain additional user data and can directly execute the recommendation algorithm based on the service parameters, thereby improving the response speed and efficiency of the server.

[0043] It has been verified that the video display method of the disclosed embodiment can increase the average number of times each user visits the application / average dwell time by 4%, the service conversion rate (the proportion of users completing specific target actions (such as purchase, registration, etc.)) by 3.53%, the number of times a single user visits the application within a certain period of time by 4.91%, the time a single user stays on the application by 5.22%, the time users stay on the main pages of the website by 6.23%, and the average dwell time of users on the immersive content stream of the application homepage by 3.42%.

[0044] Figure 1 An exemplary application scenario of the video display method according to an embodiment of the present disclosure is shown.

[0045] like Figure 1As shown, the exemplary application scenario may include a first device, a first server, and a second server. The video display method of the embodiment of the present disclosure may be applied to the first device. The first device may be a user device used by a user. An application for displaying a video, such as a first application, may be installed on the first device.

[0046] The first server and the second server may be cloud servers. The first server may be responsible for processing service requests, and the second server may be responsible for running the recommendation algorithm.

[0047] In this exemplary application scenario, the user's operation on the first application (such as clicking, sliding, long pressing, etc.) can trigger a service request (such as refreshing the page, jumping to the page, searching, etc.). The service parameters included in the service request can be used as inputs to the recommendation algorithm, and may include keywords of the video you want to recommend, such as variety shows, food, travel, etc.

[0048] The first device may send a service request to the first server. The first server may send service parameters to the second server based on the service request. The second server may execute a recommendation algorithm based on the received service parameters to recommend videos that the user may be interested in. The second server may return recommendation metadata (which may include the identifiers of the videos recommended by the second server executing the recommendation algorithm and the recommended order of each video) to the first server. The first server may obtain the complete video recommended by the second server based on the recommendation metadata, and generate a service response, so that the service response includes the complete video recommended by the second server and the recommended order of each video. The first server may return the service response to the first device, and the first device may display each video in the service response based on the recommended order of each video in the service response.

[0049] Those skilled in the art should understand that the embodiments of the present disclosure do not limit the specific division of the functions implemented by the first server and the second server. In another exemplary application scenario, a cloud server can be used to replace the first server and the second server, and the cloud server is responsible for processing service requests and running the recommendation algorithm at the same time. The embodiments of the present disclosure do not limit the specific number of cloud servers.

[0050] Figure 2 A schematic diagram showing the process of a video display method according to an embodiment of the present disclosure.

[0051] like Figure 2 As shown, in a possible implementation, an embodiment of the present disclosure proposes a video display method, the method is applied to a user device, an application for displaying a video is run on the user device, and the method includes:

[0052] Step S21, in response to a service request of an application being triggered, obtaining configuration information of the service request, the configuration information indicating whether the service request involves the use of real-time features;

[0053] Step S22, when the service request involves the use of real-time features, the service parameters in the service request are updated, and the updated service request is sent to the server, wherein the updated service parameters represent the features of the user's operation on the application, and the features are related to the service request;

[0054] Step S23, receiving a service response from the server, the service response including a plurality of videos to be displayed related to the updated service parameters and a recommended order of the videos to be displayed;

[0055] Step S24, displaying each video to be displayed in a recommended order.

[0056] For example, an application for displaying a video (such as a first application) may be run on a user device, and the user may operate the first application, such as clicking or sliding on the display interface of the first application. Different operations performed at different locations on the display interface may trigger different service requests.

[0057] There are many types of service requests, and some service requests involve the use of real-time features. In one possible implementation, when a service request involves the use of real-time features, it can be triggered by at least one of the following operations of the user on the application: the operation of jumping to the video recommendation page, the swiping up operation on the video recommendation page, and the swiping down operation on the video recommendation page. For example, after the user clicks the jump control corresponding to the video recommendation page on the display interface of the first application (that is, the operation of jumping to the video recommendation page), a service request to jump to the video recommendation page may be triggered. After responding to the service request, multiple videos recommended by the recommendation algorithm may be displayed on the page after the jump. Due to the limited size of the display interface, only a part of the recommended videos may be displayed on the display interface. If the user slides up on the display interface (that is, the swiping up operation on the video recommendation page), a service request for displaying more videos recommended by the recommendation algorithm may be triggered. If the user slides down on the display interface (that is, the swiping down operation on the video recommendation page), a service request for re-recommending videos may be triggered.

[0058] Some service requests do not involve the use of real-time features. For example, the videos displayed on the fixed-category video display page are usually irrelevant to the user's interests. Therefore, after the user clicks the jump control corresponding to the fixed-category video display page on the display interface of the first application, a service request to jump to the fixed-category video display page may be triggered. After responding to the service request, the corresponding category video display interface (such as the category "movie") may be displayed on the page after the jump. In this case, the service request may not involve the use of real-time features.

[0059] The service request may also be automatically triggered by the application, for example, the application periodically automatically triggers a service request to update the display interface. If the display interface displays a video recommendation page, the service request to update the display interface may involve the use of real-time features. If the display interface does not display a video recommendation page, the service request to update the display interface may not involve the use of real-time features.

[0060] Those skilled in the art should understand that no matter whether the service request involves the use of real-time features, there may be more triggering methods, and the present disclosure does not limit the specific triggering method of the service request.

[0061] Those skilled in the art should understand that as long as considering the user's interest is beneficial to improving the response effect of the service request, it can be determined that the service request involves the use of the real-time feature. If considering the user's interest is irrelevant to improving the response effect of the service request, it can be determined that the service request does not involve the use of the real-time feature. The embodiments of the present disclosure do not limit which specific service requests involve the use of the real-time feature and which service requests do not involve the use of the real-time feature.

[0062] In a possible implementation, the user device further includes a feature pool, which records the features of the user's operation on the application. Accordingly, in step S22, when the service request involves the use of real-time features, updating the service parameters in the service request may include: when the service request involves the use of real-time features, acquiring features related to the service request from the feature pool, and updating the service parameters in the service request according to the acquired features.

[0063] The operations performed by the user on the first application may indicate the user's interests. For example, operations such as playing a video, liking a video, following a video publisher, adding a video to favorites, sharing a video, and searching for a video may all indicate the user's interests. Therefore, a feature pool may be set on the user device to record the features of the operations performed by the user on the first application. In this case, the features recorded by the feature pool may reflect the user's interests. "Features" may include the type of operation, the object of the operation, the time point at which the operation occurs, the duration of the operation, etc.

[0064] Examples of features included in the feature pool are given below.

[0065] In one possible implementation, the feature pool includes one or more of a list of series videos played by a user, a list of independent videos played by a user, a list of videos liked by a user, a list of video publishers followed by a user, a list of videos collected by a user, a list of videos shared by a user, and a list of videos searched by a user. A series video is a video that belongs to the same series as other videos, and an independent video is a video that does not belong to the same series as other videos.

[0066] For example, the feature pool may include at least one list for storing features, each list stores different types of features, and the maximum length of each list can be preset, and can be the same or different, for example, they can all be set to 20. The features in each list can be sorted in such a way that the features with the latest collection time are at the front, and the features with the earliest collection time are at the end. The features stored in each list can be features collected within a certain time range. The collection time requirements for the features stored in each list can be the same or different, for example, they are all set to the collection time within the past 24 hours. The embodiments of the present disclosure do not limit the collection time of the features stored in each list, the maximum length of each list, the sorting method of each feature in the list, and the specific number of lists.

[0067] The features stored in the list of series videos played by the user may include the identifier of the series videos played by the user. A series video may be a video that belongs to the same series as other videos. The play time of a video may also reflect the user's interest in the video, so the features stored in the list of series videos played by the user may also include the play time of each video in the list.

[0068] The features stored in the list of independent videos played by the user may include the identifier of the independent video played by the user. An independent video is a video that does not belong to the same series as other videos. Considering that the play time of a video also reflects the user's interest in the video, the features stored in the list of independent videos played by the user may also include the play time of each video in the list.

[0069] The features stored in the list of videos liked by the user may include identifications of the videos liked by the user.

[0070] The features stored in the list of video publishers followed by the user may include identifications of the video publishers followed by the user.

[0071] The features stored in the list of favorite videos of the user may include identifications of the favorite videos of the user.

[0072] The features stored in the list of videos shared by the user may include the identification of the videos shared by the user.

[0073] The features stored in the list of videos searched by the user may include the identifiers of the videos searched by the user. Further, the features may also include the keywords and search time used by the user when searching for videos.

[0074] Those skilled in the art should understand that the above lists may include more features, and the feature pool may include more lists, as long as the features recorded in the feature pool can reflect the interests of the user. For example, it may also include a list of video publishers that the user has unfollowed, a list of videos that the user has disliked (indicating that the user does not like), etc. The present disclosure embodiment does not limit the specific types of features recorded in the feature pool.

[0075] By setting up a diverse feature list in the feature pool, the features stored in the feature pool are both highly real-time and can more comprehensively reflect user interests. Therefore, through data processing on the user device side, the server side can obtain more and more real-time user data, thereby improving the user perception ability on the server side and further improving the recommendation effect of the recommendation algorithm.

[0076] The configuration information of various service requests that may be triggered can be predetermined by the staff and pre-stored on a server in the cloud. The configuration information can indicate whether the service request involves the use of real-time features. When the service request involves the use of real-time features, the configuration information can also record the category of at least one feature related to the service request, so that the user device can clearly understand which categories of features can be used to update the service parameters of the service request. Features collected too early in the feature pool may no longer match the user's current interests. Therefore, the configuration information can also record the collection time requirements of the features used to update the service parameters. In this way, in step S22, the features of the user's operations on the application may include the features of the operations collected within the latest preset time range. The latest preset time range can be indicated by the collection time requirements in the configuration information to ensure the real-time nature of the features.

[0077] Taking the service request of re-recommending videos as an example, re-recommending videos involves the use of real-time features, so the configuration information of the service request can record the use of real-time features involved in the service request. The features related to the service request recorded in the configuration information of the service request can be a series of videos played by the user, an independent video played by the user, a video liked by the user, etc. The collection time requirement recorded in the configuration information of the service request can be within the past 30 minutes.

[0078] In step S21, in response to a service request of an application being triggered, the user equipment may obtain configuration information of the service request.

[0079] Figure 3 A schematic diagram showing a user equipment acquiring configuration information according to an embodiment of the present disclosure.

[0080] exist Figure 3In the example of , the third server may be a server in the cloud for storing configuration information. The first device may be a user device. After the application (such as the first application) is started, the first device may first obtain configuration information of various service requests of the application from the third server. When executing step S21, in response to the triggered service request, the first device may directly obtain the configuration information of the service request locally.

[0081] In another example, the first device may also be triggered in response to the service request of the application, and obtain the configuration information of the service request from the third server. The embodiment of the present disclosure does not limit the specific manner in which the user device obtains the configuration information of the service request.

[0082] As described above, the configuration information may record various information such as whether the service request involves the use of real-time features, the category of at least one feature related to the service request, and the collection time requirement of the features used to update the service parameters. Therefore, when executing step S21, the information on whether the service request involves the use of real-time features may be obtained first. If the service request does not involve the use of real-time features, it is not necessary to obtain other information included in the configuration information of the service request to save data transmission costs.

[0083] The third server can be independent of the first server and the second server, and the first server or the second server can also implement the function of the third server. The embodiment of the present disclosure does not limit the function allocation of the cloud server.

[0084] The configuration information records whether the service request involves the use of real-time features, so the user equipment can directly determine whether the service request involves the use of real-time features according to the configuration information. The specific determination process will not be repeated here.

[0085] When the service request involves the use of real-time features, the configuration information of the service request may record the features related to the service request. Therefore, in step S22, when the service request involves the use of real-time features, the user device may update the service parameters in the service request so that the updated service parameters represent the features of the user's operations on the application, and the features are related to the service request. The method of updating the service parameters may include adding new keywords obtained by compressing the features to the original service parameters, deleting some or all of the keywords in the original service parameters, etc. Among them, compressing or extracting the features to obtain the keywords of the features can be implemented based on related technologies. The keywords in the service parameters can be spliced ​​together. The embodiments of the present disclosure do not limit the specific method of updating the service parameters, as long as the updated service parameters can reflect the features obtained by the user device.

[0086] The user device may send the updated service request to the server, and the server may determine a service response according to the service request and send the service response to the user device. In step S23, the user device may receive the service response. The service response may include a plurality of videos to be displayed and a recommended order of each video to be displayed related to the updated service parameters. The way in which the server determines the service response can be implemented based on the prior art, which will not be repeated here.

[0087] In step S24, after receiving the service response, the user equipment may display the videos to be displayed in a recommended order on the display interface.

[0088] In one example, assuming that the service parameters included in the service request triggered when executing step S21 are variety shows, food, and travel, and the user has played multiple videos related to pets in the past 30 minutes, when executing step S22, the updated service parameters may be variety shows, food, travel, and pets. In this case, there is a high probability that the videos displayed when executing step S24 will include videos related to pets.

[0089] In another example, assuming that the service parameters included in the service request triggered when executing step S21 are variety shows, food, and travel, but the user has disliked multiple food-related videos in the past 30 minutes (indicating that the user does not like the video), when executing step S22, the updated service parameters may be variety shows and travel. In this case, there is a small probability that a food-themed video will appear in the videos displayed when executing step S24.

[0090] According to the video display method of the embodiment of the present disclosure, in response to the service request of the application being triggered, the configuration information of the service request is obtained, and when the configuration information indicates that the service request involves the use of real-time features, the service parameters in the service request are updated so that the updated service parameters represent the features of the user's operations on the application that are related to the service request. The updated service request is sent to the server. In this case, the service request obtained by the server can include real-time user data (i.e., updated service parameters). The server can determine the service response based on the service request and send the service response to the user device. The service response includes multiple videos to be displayed related to the updated service parameters and the recommended order of each video to be displayed. The service response at this time is a better quality recommendation result that the server can give based on real-time user data, which can improve the user experience.

[0091] In the embodiment of the disclosure, when the configuration information indicates that the service request involves the use of real-time features, the service parameters in the service request are updated and the real-time user data is uploaded to the server. The action of returning the real-time user data to the server is cleverly limited to the time when the service request is triggered and the service request involves the use of real-time features. The timing of data return and the algorithm requirements of the server are accurately synchronized, and the characteristics of updating the service parameters are related to the service request. Therefore, the data utilization rate is higher, the timeliness, real-time and accuracy of user data provision are guaranteed, and there is no need to regularly transmit a large amount of invalid user data to the server. The processing cost is effectively dispersed on each user device, and the user device dynamically releases real-time user data based on actual service needs and using service requests, which reduces the data transmission pressure and processing pressure of the server and improves the system response speed and efficiency. In addition, the method does not need to add hardware resources for collecting user data on the server, thereby reducing the cost of the server. The service request obtained by the server already includes real-time user data (service parameters), so the server does not need to obtain user data additionally, and can directly execute the recommendation algorithm based on the service parameters, which improves the response speed and response efficiency of the server.

[0092] The "feature pool" mentioned above can be constructed asynchronously with the service request. In other words, in the actual application scenario, the service request update process of the first device and the feature generation process of the first device (see below and Figure 4 Examples) can be implemented in different modules to avoid the impact of the feature generation process on the service request process.

[0093] For example, the feature pool can be updated according to a preset cycle or update condition, and when a service request involving the use of the implementation feature is triggered, the features related to the service request are obtained from the feature pool. Therefore, on the one hand, the original service request-service response process is slightly changed, which reduces the difficulty of development, and the feature pool is pre-built so that the corresponding features can be obtained from the feature pool immediately after the service request is triggered, thereby improving the efficiency of feature acquisition. The following examples illustrate several exemplary ways of building a feature pool. Those skilled in the art should understand that the way the feature pool is built is not limited to the examples listed. Moreover, the features of user operations may not be stored or obtained in the form of a feature pool. For example, in response to a service request being triggered and the service request involving the use of real-time features, the features of user operations may be directly extracted from the user log. This application does not limit the way in which operation features are obtained.

[0094] In a possible implementation manner, the user equipment includes a user database, the user database stores user logs, and the method further includes:

[0095] Update user logs based on user operations on the application;

[0096] In response to the application being started, loading an event monitoring script, the event monitoring script is used to monitor events reflecting user interests;

[0097] When the event monitoring script monitors an event, it reads all or part of the user log from the user database and updates the feature pool according to the read user log.

[0098] Figure 4 A schematic diagram showing updating a feature pool according to an embodiment of the present disclosure is shown.

[0099] For example, if Figure 4 As shown, the first device may be a user device, and the first device may include a user database for storing user logs. The first device may update the user log according to the user's operation on the application (such as the first application). The update of the user log may be implemented based on the existing technology, for example, Figure 4 As shown, operations involving log updates can be tracked, and when the user's operation on the first application is a pre-tracked operation, the user log in the user database is updated according to the operation. Tracking can be for any preset type of operation, or only for operations that can indicate the user's interests. The method of updating the user log can be to add a record of the user's operation on the first application and the time when the operation occurred in the user log. If the user log is full, the earliest recorded operation and the corresponding time in the user log can be cleared, and then a new operation and the corresponding time can be added. The embodiments of the present disclosure do not limit the specific implementation method of updating the user log.

[0100] In order to improve the real-time performance of the features in the feature pool, the events reflecting the user's interests in the user's operation on the first application can be monitored. The staff can pre-write an event monitoring script for monitoring the events reflecting the user's interests. The events reflecting the user's interests can be set by the staff, and exemplary events reflecting the user's interests are given later.

[0101] In response to the first application being started, the first device may load an event monitoring script. After the event monitoring script is loaded, it may start to monitor events that reflect the user's interests, and update the feature pool when corresponding events are monitored. Figure 4 As shown, in one example, after the event monitoring script is loaded, a task trigger can be registered. When the task trigger monitors that the user's operation on the first application is a pre-buried operation, it determines whether the operation generates an event that the event monitoring script is to monitor. If the operation generates an event that the event monitoring script is to monitor, the feature update task is triggered, and the first device executes the feature update task to update the feature pool.

[0102] Exemplarily, when the first device performs a feature update task, it can read all of the user log from the user database and update the feature pool according to the read user log. Alternatively, since the first device also read the user log from the user database when it last updated the feature pool, the data read from the user database when the first device updates the feature pool this time can include the data recorded in the user log between the last update of the feature pool and the current update of the feature pool, that is, read part of the user log and update the feature pool according to the read user log. In this way, the data handling cost and data processing cost inside the user device can be reduced.

[0103] In this case, the features in the feature pool are more closely matched with user needs. After using the features to update the service parameters, the recommendation effect can be improved.

[0104] In a possible implementation, the event reflecting the user's interest includes at least one of a click event and a playback end event not triggered by the user.

[0105] For example, the user can click on the first application to like the video, collect the video, share the video, play the video, follow the video publisher, search for the video, pause the video, and end the video. Liking the video, collecting the video, sharing the video, playing the video, following the video publisher, and searching for the video can all indicate that the user's interest in the video has increased; pausing the video and ending the video can indicate that the user's interest in the video has decreased. Therefore, the event reflecting the user's interest may include a click event. In this way, the real-time nature of the features in the feature pool is made higher.

[0106] For example, if a video reaches the end, the video will automatically end even if the user does not click to end the video. This indicates that the user is very interested in the video. To this end, the non-user-triggered end of playback event can also be set as an event that reflects user interest.

[0107] In this way, when the video playback ends automatically after reaching the end, the update of the feature pool can also be triggered, further improving the real-time performance of the features in the feature pool.

[0108] The relevant logs of the operations required by the feature pool and indicating the user's interests may be filtered out from the read user logs to update the feature pool.

[0109] In a possible implementation, the event monitoring script includes one or more of a Python script and a JavaScript script.

[0110] For example, most algorithm-side staff use Python to write programs, while most terminal-side staff use JavaScript. Due to the differences between Python and JavaScript, it is difficult for algorithm-side staff to independently complete terminal-side programming work.

[0111] The event monitoring script of the disclosed embodiment includes one or more of a Python script and a JavaScript script, that is, the event monitoring script can be written in any one of the Python language and the JavaScript language. In this case, the staff on the algorithm side can write the event monitoring script in Python, and the staff on the terminal side can write the event monitoring script in JavaScript, which is more friendly to the staff.

[0112] The user device may have different matching degrees with Python scripts and JavaScript scripts. If two scripts are pre-written, when loading the event monitoring script, you can load the script that is more compatible with the user device to improve the real-time monitoring performance.

[0113] Furthermore, if it is necessary to add new lists to the feature pool or reduce lists, the event monitoring script can be modified. According to the adjusted lists, the features to be updated in the feature update task can be adjusted without changing the rest of the video display process, which can reduce the workload of staff and reduce maintenance costs.

[0114] In a possible implementation, the user equipment includes a user database, the user database stores user logs, and the method further includes:

[0115] Update user logs based on user operations on the application;

[0116] In response to the application being started, all or part of the user log is read from the user database at every preset time period, and the feature pool is updated according to the read user log.

[0117] For example, in addition to using an event listening script to trigger a feature pool update, other methods can also be used to update the feature pool. For example, in response to the first application being started, all or part of the user log can be read from the user database at intervals of a preset time period (e.g., 30 seconds), and the feature pool can be updated based on the read user log. In this way, the feature pool can maintain a high degree of real-time performance, and the method of triggering the feature pool update is simpler.

[0118] In summary, the video display method disclosed in the present invention recommends videos that are more compatible with the user's interests to the user, which is conducive to extending the user's stay time on the first application and strengthening user stickiness. In addition, the recommendation algorithm can also adjust the advertising video delivery strategy according to the updated service parameters, so that the advertising video can be presented at a time when the user is more interested in the video and at a location that the user is more likely to notice, thereby improving the advertising video delivery effect. For example, due to the addition or deletion of some keywords in the updated service parameters, the advertising videos to be displayed included in the video to be displayed also do not contain advertising videos related to the deleted keywords, or contain advertising videos related to the added keywords, thereby improving the accuracy of advertising video delivery. The video display method disclosed in the present invention makes full use of the computing resources of the user's device, provides more real-time data for the server running the recommendation algorithm, greatly enhances the recommendation effect of the recommendation algorithm, and is conducive to the intelligence and personalization of video recommendations.

[0119] The method of the embodiment of the present application can be bound to a user account. For example, when a user logs in to an application, a service request is triggered, and the service request involves the use of real-time features. The features of the user's operations on the application can be obtained to update the service parameters and present the user with recommendation results based on the updated service parameters.

[0120] The method of the embodiment of the present application may not be bound to a user account. For example, when a user logs into an application, or when a user uses an application without logging in, a service request is triggered, and the service request involves the use of real-time features. Features of operations performed on the application by the user and other users may be obtained to update service parameters and present recommendation results based on the updated service parameters.

[0121] The disclosed embodiment also provides a video display device, Figure 5 A schematic diagram showing the structure of a video display device according to an embodiment of the present disclosure.

[0122] like Figure 5 As shown, in a possible implementation manner, the apparatus is applied to a user device, an application for displaying a video is run on the user device, and the apparatus includes:

[0123] A first acquisition module 51, configured to acquire configuration information of the service request in response to a service request of the application being triggered, wherein the configuration information indicates whether the service request involves the use of a real-time feature;

[0124] A first updating module 52 is used to update the service parameters in the service request when the service request involves the use of real-time features, and send the updated service request to the server, wherein the updated service parameters represent the characteristics of the operation performed by the user on the application, and the characteristics are related to the service request;

[0125] A receiving module 53, configured to receive a service response from a server, wherein the service response includes a plurality of videos to be displayed and a recommended order of the videos to be displayed that are related to the updated service parameters;

[0126] The display module 54 is used to display each video to be displayed in the recommended order.

[0127] In one possible implementation, the user device also includes a feature pool, which records the characteristics of the user's operations on the application; when the service request involves the use of real-time features, the service parameters in the service request are updated, including: when the service request involves the use of real-time features, obtaining characteristics related to the service request from the feature pool, and updating the service parameters in the service request based on the obtained characteristics.

[0128] In one possible implementation, the user device includes a user database, which stores user logs. The apparatus also includes: a second update module, which is used to update the user log according to the user's operation on the application; a loading module, which is used to load an event monitoring script in response to the application being started, and the event monitoring script is used to monitor events that reflect user interests; a third update module, which is used to read all or part of the user log from the user database when the event monitoring script monitors the event, and update the feature pool according to the read user log.

[0129] In a possible implementation, the event includes at least one of a click event and a playback end event not triggered by the user.

[0130] In a possible implementation, the event monitoring script includes one or more of a Python script and a JavaScript script.

[0131] In one possible implementation, the user device includes a user database, which stores user logs. The apparatus also includes: a fourth update module, which is used to update the user log according to the user's operation on the application; and a fifth update module, which is used to read all or part of the user log from the user database at every preset time period in response to the application being started, and update the feature pool according to the read user log.

[0132] In one possible implementation, the feature pool includes one or more of a list of series videos played by a user, a list of independent videos played by a user, a list of videos liked by a user, a list of video publishers followed by a user, a list of videos collected by a user, a list of videos shared by a user, and a list of videos searched by a user. The series video is a video that belongs to the same series as other videos, and the independent video is a video that does not belong to the same series as other videos.

[0133] In a possible implementation, the characteristics of the operation performed by the user on the application include characteristics of the operation collected within the latest preset time range.

[0134] In one possible implementation, when the service request involves the use of real-time features, it is triggered by at least one of the following operations of the user on the application: jumping to the video recommendation page, swiping up on the video recommendation page, and swiping down on the video recommendation page.

[0135] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0136] The embodiment of the present disclosure also provides a computer-readable storage medium on which computer program instructions are stored, and the computer program instructions implement the above method when executed by a processor. The computer-readable storage medium can be a volatile or non-volatile computer-readable storage medium.

[0137] An embodiment of the present disclosure further proposes an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0138] The embodiments of the present disclosure also provide a computer program product, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0139] Figure 6 1 is a block diagram of an electronic device 1900 according to an embodiment of the present disclosure. For example, the electronic device 1900 may be provided as a terminal device (such as the first device described above). Figure 6, the electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions executable by the processing component 1922, such as an application. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.

[0140] The electronic device 1900 may also include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output interface 1958 (I / O interface). The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server 2003. TM , Mac OS X TM , Unix TM ,Linux TM , FreeBSD TM or similar.

[0141] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions, which can be executed by the processing component 1922 of the electronic device 1900 to perform the above method.

[0142] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0143] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: 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), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0144] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0145] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of 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., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0146] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0147] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0148] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0149] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0150] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A video display method, characterized in that: The method is applied to a user device, and an application for displaying a video is run on the user device. The method includes: In response to a service request of the application being triggered, obtaining configuration information of the service request, the configuration information indicating whether the service request involves the use of a real-time feature; When the service request involves the use of a real-time feature, updating a service parameter in the service request, and sending the updated service request to the server, wherein the updated service parameter represents a feature of an operation performed by the user on the application, the feature being related to the service request; Receiving a service response from a server, wherein the service response includes a plurality of videos to be displayed and a recommended order of the videos to be displayed that are related to the updated service parameters; The videos to be displayed are displayed in the recommended order.

2. The method according to claim 1, characterized in that The user equipment further includes a feature pool, which records features of operations performed by the user on the application; When the service request involves the use of real-time features, updating the service parameters in the service request includes: When the service request involves the use of real-time features, features related to the service request are acquired from the feature pool, and service parameters in the service request are updated according to the acquired features.

3. The method according to claim 1, characterized in that The user equipment includes a user database, the user database stores user logs, and the method further includes: updating the user log according to the user's operation on the application; In response to the application being started, loading an event monitoring script, wherein the event monitoring script is used to monitor events reflecting user interests; When the event monitoring script monitors the event, it reads all or part of the user log from the user database, and updates the feature pool according to the read user log.

4. The method according to claim 3, characterized in that The event includes at least one of a click event and a playback end event not triggered by the user. 5 . The method according to claim 4 , wherein the event monitoring script comprises one or more of a Python script and a JavaScript script.

6. The method according to claim 1, characterized in that The user equipment includes a user database, the user database stores user logs, and the method further includes: updating the user log according to the user's operation on the application; In response to the application being started, all or part of the user log is read from the user database at intervals of a preset time period, and the feature pool is updated according to the read user log.

7. The method according to claim 1, characterized in that The feature pool includes one or more of a list of series videos played by the user, a list of independent videos played by the user, a list of videos liked by the user, a list of video publishers followed by the user, a list of videos collected by the user, a list of videos shared by the user, and a list of videos searched by the user. The series video is a video that belongs to the same series as other videos, and the independent video is a video that does not belong to the same series as other videos.

8. The method according to any one of claims 1 to 7, characterized in that The characteristics of the operation performed by the user on the application include the characteristics of the operation collected within the latest preset time range.

9. The method according to any one of claims 1 to 7, characterized in that: When the service request involves the use of real-time features, it is triggered by at least one of the following operations of the user on the application: jumping to the video recommendation page, swiping up on the video recommendation page, and swiping down on the video recommendation page.

10. A video display device, characterized in that: The apparatus is applied to a user device, and an application for displaying a video is run on the user device. The apparatus includes: A first acquisition module, configured to acquire configuration information of the service request in response to a service request of the application being triggered, wherein the configuration information indicates whether the service request involves the use of a real-time feature; A first updating module, configured to update a service parameter in the service request when the service request involves the use of a real-time feature, and send the updated service request to the server, wherein the updated service parameter represents a feature of an operation performed by a user on the application, the feature being related to the service request; A receiving module, configured to receive a service response from a server, wherein the service response includes a plurality of videos to be displayed and a recommended order of the videos to be displayed that are related to the updated service parameters; The display module is used to display each video to be displayed in the recommended order.

11. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the method described in any one of claims 1 to 9 when executing the instructions stored in the memory.

12. A non-volatile computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 9 is implemented.

13. A computer program product comprising computer readable code, or a non-volatile computer readable storage medium carrying computer readable code, characterized in that: When the computer readable code runs in a processor of an electronic device, the processor in the electronic device executes the method according to any one of claims 1 to 9.

Images