Display methods, devices, electronic devices, and computer-readable media

Abstract

The present application discloses a display method, apparatus, electronic device, and computer-readable medium. When a client is displaying a video playback page, the client can display several first candidate objects to the user. After the client receives a trigger operation on a target control within the video playback page, it displays an information recommendation page and displays a set of recommendation information corresponding to a reference object on the information recommendation page. The set of recommendation information includes account attribute information of a plurality of candidate accounts, and the display target objects under each candidate account all include a target display object. The object category of the target display object is the same as the object category corresponding to the set of recommendation information, and the object category corresponding to the set of recommendation information is also the same as the category of the reference object. Thus, these candidate accounts can provide the user with objects of the same type as the reference object, and in this way, the information browsing needs of the user can be better satisfied.

Description

Technical Field

[0001] This application claims the priority of a Chinese patent application filed with the China National Intellectual Property Administration on September 2, 2022, with an application number of 202211072095.9 and an application title of "Display Method, Device, Electronic Device, and Computer Readable Medium". This application further claims the priority of a Chinese patent application filed with the China National Intellectual Property Administration on September 2, 2022, with an application number of 202211075030.X and an application title of "Display Method, Device, Electronic Device, and Computer Readable Medium", and the entire content thereof is incorporated herein by reference.

[0002] This application relates to the technical field of the Internet, and particularly to a display method, device, electronic device, and computer readable medium.

Background Art

[0003] Live streaming is an information network distribution method with a two-way circulation process that creates and distributes information in synchronization with the occurrence and progress of an event on-site.

[0004] In some live streaming rooms, since the live streaming room can display several objects (such as products, etc.) to users, viewers in the live streaming room can not only understand these objects in the live streaming room, but also perform some interaction operations (such as interaction operations like favorites, transactions, etc.) on these objects.

[0005] In some cases, for viewers in a live streaming room, when the viewer browses an object of interest in the live streaming room, the viewer may want to browse some other objects related to the object (such as objects of the same type). Therefore, how to browse these other objects has become a technical problem that needs to be solved urgently.

Summary of the Invention

Means for Solving the Problems

[0006] To solve the above technical problems, this application provides a display method, apparatus, electronic device, and computer-readable medium.

[0007] To achieve the above objective, the technical solution relating to this application is as follows:

[0008] This application is, Steps to display the video playback page, The present invention provides a display method comprising the steps of displaying an information recommendation page in response to a trigger operation on a target control within the video playback page, wherein the information recommendation page displays a set of recommended information corresponding to a referenced object, the referenced object is determined according to the attention state representation information of at least one first candidate object corresponding to the video playback page, the set of recommended information includes account attribute information of multiple candidate accounts, each of the display target objects under each candidate account includes a target display object, the object category of the target display object is the same as the object category corresponding to the set of recommended information, and the object category corresponding to the set of recommended information is the same as the object category of the referenced object.

[0009] In one possible embodiment, the attention state representation information includes history operation action information and video commentary information. When the history operation activity information of the first target object among the at least one first candidate object satisfies the first preset condition, the referenced object is determined according to the first target object. If none of the history operation information for each of the first candidate objects satisfies the first preset condition, the referenced object is determined according to the video explanation information for at least one of the first candidate objects.

[0010] In one possible embodiment, if the history operation activity information of each of the first candidate objects does not satisfy the first preset condition, and the video description information of the second target object among the at least one first candidate object satisfies the second preset condition, the referenced object is determined according to the second target object.

[0011] In one possible embodiment, the history operation information includes the number of clicks, and the first preset condition is that the number of clicks on the first target object is greater than a preset count threshold.

[0012] In one possible embodiment, the second preset condition includes, as video commentary information for the second target object, that the second target object is in a commentary state within the video playback page, Or, The second preset condition includes, as video explanation information for the second target object, that the second target object is in an explanation completion state within the video playback page, and that the explanation completion time for the second target object is later than the explanation completion times for other objects that are in an explanation completion state within the video playback page.

[0013] In one possible embodiment, the attention state representation information includes history operation action information, After the step of displaying the video playback page, the method The process further includes updating the history operation information of the third target object in response to a trigger operation on the third target object, which is one of at least one first candidate objects corresponding to the video playback page.

[0014] In one possible embodiment, the recommendation information set further includes object display information for target display objects under each candidate account.

[0015] In one possible embodiment, the object to be classified is the referenced object or the target display object, The object category of the object to be classified is determined according to the object description information of the object to be classified and a pre-constructed object classification model, and the object classification model is used to perform classification processing on the object description information of the object to be classified.

[0016] In one possible embodiment, the video playback page is used to display a first live streaming video, and / or the information display page corresponding to the candidate account is used to display a second live streaming video.

[0017] This application is, A first display unit used to display a video playback page, The present invention further provides a display device comprising: a second display unit used to display an information recommendation page in response to a trigger operation on a target control within the video playback page, wherein the information recommendation page displays a set of recommendation information corresponding to a reference object, the reference object is determined according to attention state representation information of at least one first candidate object corresponding to the video playback page, the recommendation information set includes account attribute information of a plurality of candidate accounts, each of the display target objects under each candidate account includes a target display object, the object category of the target display object is the same as the object category corresponding to the recommendation information set, and the object category corresponding to the recommendation information set is the same as the object category of the reference object.

[0018] Compared to the prior art, this invention has at least the following advantages.

[0019] The technical solution according to the present invention allows a client used by a viewer of video data to display several first candidate objects to the viewer when the client is displaying a video playback page, and after the client receives a trigger operation on a target control within the video playback page, it can display an information recommendation page, and the information recommendation page can display a set of recommended information corresponding to a referenced object among these first candidate objects. The set of recommended information includes account attribute information of multiple candidate accounts, and each of the displayed objects under each candidate account includes a target display object, and the object category of the target display object is the same as the object category corresponding to the set of recommended information, and the object category corresponding to the set of recommended information is the same as the category of the referenced object, so that these candidate accounts can provide the viewer with several other objects (e.g., objects of the same type) related to the referenced object.

[0020] As can be seen from the above, since the referenced object is determined according to the attention state representation information of at least one first candidate object corresponding to the video playback page, the referenced object can represent the viewer's object of interest, thereby allowing us to infer that the viewer may be interested in other objects related to the referenced object (e.g., objects of the same type). Therefore, after recommending a set of recommended information corresponding to the referenced object to the viewer, the viewer can use the recommended information set to browse other objects related to the referenced object. In this way, the viewer's object browsing experience can be better satisfied, which is advantageous in improving the user experience.

[0021] This application is, The steps include: displaying a video playback page that includes target controls, responding to a trigger operation on the target control, and displaying an information recommendation page The information recommendation page includes a plurality of recommended information sets, and the object categories corresponding to each of the recommended information sets are all different. Each recommended information set includes account attribute information of a plurality of candidate accounts. Each display target object under each candidate account in the same recommended information set includes a target display object, and the object category of the target display object is the same as the object category corresponding to the recommended information set. A display method is provided.

[0022] In one possible embodiment, account attribute information of a target account among the plurality of candidate accounts is displayed on the information recommendation page, and the method further includes: responding to a trigger operation on the account attribute information of the target account, and displaying an information display page corresponding to the target account.

[0023] In one possible embodiment, each recommended information set further includes object display information of target display objects under a plurality of candidate accounts.

[0024] In one possible embodiment, the object display information includes at least one of text description information and picture description information.

[0025] In one possible embodiment, when object display information of a target display object under a target account among the plurality of candidate accounts is displayed on the information recommendation page, the method further includes: responding to a trigger operation on the object display information, displaying an information display page corresponding to the target account, and displaying an information display interface corresponding to the target display object under the target account on the information display page corresponding to the target account.

[0026] In one possible embodiment, the information recommendation page further includes a plurality of category tags, each of which has a one-to-one correspondence with a plurality of recommended information sets, and the recommended information set currently displayed on the information recommendation page is the recommended information set corresponding to the first tag among the plurality of category tags. The aforementioned method, The further step includes switching the set of recommended information displayed on the information recommendation page from the set of recommended information corresponding to the first tag to the set of recommended information corresponding to the second tag in response to a trigger operation on the second of the multiple category tags.

[0027] In one possible embodiment, at least one first candidate object corresponding to the video playback page has a target reference object that satisfies a preset condition, The object category corresponding to the aforementioned recommended information set is the same as the object category of the aforementioned target reference object.

[0028] In one possible embodiment, the preset condition is that the video commentary state within the video playback page of the target reference object satisfies the preset state condition, Or, The preset condition is that the history operation information of the target reference object satisfies the preset operation condition.

[0029] In one possible embodiment, the object category of the target display object is determined according to the object description information of the target display object and a pre-constructed object classification model, the object classification model being used to perform classification processing on the object description information of the target display object.

[0030] In one possible embodiment, the object classification model is trained using object description information of at least one referenced object and classification annotation information of the at least one referenced object.

[0031] In one possible embodiment, the video playback page is used to display a first live streaming video, and / or the information display page corresponding to the candidate account is used to display a second live streaming video.

[0032] In one possible embodiment, the account attribute information includes at least one of an identification icon corresponding to the candidate account and identification text corresponding to the candidate account.

[0033] This application is, A first display unit used to display a video playback page including target controls, The present invention further provides a display device comprising: a second display unit used to display an information recommendation page in response to a trigger operation on the target control, wherein the information recommendation page includes a plurality of recommendation information sets, each recommendation information set has a different object category, each recommendation information set includes account attribute information of a plurality of candidate accounts, each display target object under each candidate account in the same recommendation information set includes a target display object, and the object category of the target display object is the same as the object category corresponding to the recommendation information set.

[0034] Compared to the prior art, this invention has at least the following advantages.

[0035] In the technical solution relating to the present invention, when a client used by a viewer of a certain video data is displaying a video playback page, the client receives a trigger operation (e.g., a click operation) on a target control within the video playback page, and then displays an information recommendation page. The information recommendation page includes multiple recommendation information sets, each corresponding to a different object category, each recommendation information set includes account attribute information for multiple candidate accounts, and each display target object under each candidate account in the same recommendation information set includes a target display object, the object category of the target display object is the same as the object category corresponding to the recommendation information set.

[0036] As can be seen from the above, the information recommendation page contains multiple sets of recommended information, and each set of recommended information corresponds to a different object category. Therefore, the information recommendation page can provide users with sets of recommended information under several object categories, allowing users to view sets of recommended information under different object categories from the information recommendation page. In this way, the user's information viewing needs can be better met, which is advantageous for improving the user experience.

[0037] This application includes a processor and memory, The memory is used to store instructions or computer programs. The present invention further provides an electronic device used to execute the display method according to the present invention by executing the instructions or computer program in the memory.

[0038] The present invention further provides a computer-readable medium on which instructions or computer programs are stored, and which, when the instructions or computer programs are executed on the device, causes the device to execute the display method according to the present invention.

[0039] The present invention further provides a computer program product that includes a computer program installed on a non-temporary computer-readable medium, the computer program including program code for executing the display method relating to the present invention.

[0040] To more clearly illustrate the embodiments of this application or the technical solutions of the prior art, the drawings that may be used to describe the embodiments or the prior art are briefly described below. Clearly, the drawings described below are only a few embodiments of this application, and those skilled in the art can obtain other drawings based on these without any creative work. [Brief explanation of the drawing]

[0041] [Figure 1] Figure 1 is a flowchart of the display method according to an embodiment of the present application. [Figure 2] Figure 2 is a schematic diagram of a video playback page according to an embodiment of the present invention. [Figure 3] Figure 3 is a schematic diagram of another video playback page relating to an embodiment of the present invention. [Figure 4] Figure 4 is a schematic diagram of the configuration of a display device according to an embodiment of the present invention. [Figure 5] Figure 5 is a flowchart of the display method according to an embodiment of the present application. [Figure 6] Figure 6 is a schematic diagram of the configuration of a display device according to an embodiment of the present invention. [Figure 7] Figure 7 is a schematic diagram of the configuration of an electronic device according to an embodiment of the present application. [Modes for carrying out the invention]

[0042] Research has shown that, for video data viewers, if they are interested in an object displayed in the live stream video, they are likely to be interested in similar objects as well. However, in some related means, viewers can leave the current live stream video and traverse a large number of other live stream videos to find these similar objects from the objects displayed in these live stream videos, which requires a significant amount of the viewer's time to do so, resulting in a relatively low object browsing experience for the viewer.

[0043] Based on the above findings, and in order to solve the technical problems described in the background art, embodiments of the present application provide a display method that, for a client used by a viewer of video data, when the client is viewing a video playback page, the client displays several first candidate objects to the viewer, and after the client receives a trigger operation on a target control within the video playback page, displays an information recommendation page, and the information recommendation page displays a set of recommendation information corresponding to a referenced object among these first candidate objects. The set of recommendation information includes account attribute information of multiple candidate accounts, each of which displays a target display object, the object category of the target display object is the same as the object category corresponding to the set of recommendation information, and the object category corresponding to the set of recommendation information is the same as the category of the referenced object, so that these candidate accounts can provide the viewer with several other objects (e.g., objects of the same kind) related to the referenced object.

[0044] As can be seen from the above, since the referenced object is determined according to the attention state representation information of at least one first candidate object corresponding to the video playback page, the referenced object can represent the viewer's object of interest, thereby allowing us to infer that the viewer may be interested in other objects related to the referenced object (e.g., objects of the same type). Therefore, after recommending a set of recommended information corresponding to the referenced object to the viewer, the viewer can use the recommended information set to browse other objects related to the referenced object. In this way, the viewer's object browsing experience can be better satisfied, which is advantageous in improving the user experience.

[0045] Furthermore, in the embodiments of this application, the entity that implements the display method according to the embodiments of this application is not limited, and for example, the display method according to the embodiments of this application may be applied to a terminal device or a server. Alternatively, for example, the display method according to the embodiments of this application may be implemented by a data exchange process between a terminal device and a server. The terminal device may be a smartphone, a computer, a personal digital assistant (PDA), a tablet computer, etc. The server may be a standalone server, a cluster server, or a cloud server.

[0046] To enable those skilled in the art to better understand the means of the present application, the technical solutions of the embodiments of the present application will be described clearly and completely below with reference to the drawings of the embodiments of the present application, and it is clear that the embodiments described are only some, not all, embodiments of the present application. All other embodiments that a person skilled in the art can obtain without creative work based on the embodiments of the present application are within the scope of the protection of the present application.

[0047] To better understand the technical solution related to this application, the information display method related to this application will first be explained below with reference to several drawings.

[0048] As shown in Figure 1, the display method according to the embodiment of the present application may include the following S101-S102.

[0049] S101: Display the video playback page.

[0050] A video playback page is a playback area for a single video data. In other words, a single video data can occupy the entire area of ​​the video playback page for display. Furthermore, in the embodiments of this application, the video playback page is not limited and may be, for example, a live streaming video page (e.g., the live streaming video page 200 shown in Figure 2) or a short video page. As can be seen from the above, in one possible embodiment, the video playback page can be used to display a first live streaming video (e.g., a live streaming video displayed in page 200 in Figure 2). The first live streaming video is a live streaming video that is played on the video playback page.

[0051] Furthermore, the video playback page can be used to perform display processing on at least one first candidate object corresponding to the video playback page. The first candidate object is an object on which several operations (e.g., interaction operations such as browsing and trading) can be performed within the live streaming room represented by the video playback page. In other words, in the case of a live streaming room represented by the video playback page, viewers of the live streaming room can perform several interaction operations (e.g., interaction operations such as browsing and trading) on ​​the first candidate object within the live streaming room.

[0052] Furthermore, in the embodiments of the present application, the first candidate object is not limited. For example, if the video playback page is a live streaming video page (for example, the live streaming video page 200 shown in Figure 2), the first candidate object may be any product described in the live streaming video on the video playback page, any shopping product displayed by a specific operation (for example, by clicking the control 202 shown in Figure 2), or any showcase product displayed by a specific operation (for example, by clicking a certain control).

[0053] Furthermore, in the embodiments of this application, the shopping products are not limited; for example, the shopping products include at least two types of products, the first type of product may be the product described, and the second type of product may be a product other than the product described. Also, in the embodiments of this application, the showcase products are not limited; for example, they may be products displayed on a showcase display page corresponding to the live streaming video page. Also, in the embodiments of this application, the relationship between shopping products and showcase products is not limited; for example, there may be common parts between them, or there may be no common parts.

[0054] As can be seen from the related content of S101 above, for a client used by a viewer of a certain video data, when the client is displaying the video playback page, the client can display several first candidate objects to the viewer, thereby allowing the viewer to perform interaction operations such as browsing (or trading) on ​​one or more of these first candidate objects on the video playback page.

[0055] S102: In response to a trigger operation on a target control within the video playback page, an information recommendation page is displayed, the information recommendation page displays a set of recommended information corresponding to a referenced object, the referenced object is determined according to the attention state representation information of at least one first candidate object corresponding to the video playback page, the recommended information set includes account attribute information of multiple candidate accounts, each of the displayed objects under each candidate account includes a target display object, the object category of the target display object is the same as the object category corresponding to the recommended information set, and the object category corresponding to the recommended information set is the same as the object category of the referenced object.

[0056] The target control is used to trigger the information recommendation process, and in the embodiments of the present application, the target control is not limited and may be, for example, the control 201 shown in Figure 2.

[0057] The referenced object is the object of interest to the user among at least one first candidate object corresponding to the video playback page mentioned above.

[0058] Furthermore, the embodiments of the present application do not limit the process for determining the referenced object. For example, the referenced object may be determined based on attention status representation information of at least one first candidate object corresponding to the video playback page. The attention status representation information is used to represent the degree to which the first candidate object is attracting attention (i.e., the user's level of interest in the first candidate object).

[0059] Furthermore, the embodiments of the present application do not limit the embodiments of the attention state representation information described above, and can be implemented by employing, for example, any existing or future information that can express the user's level of interest in the first candidate object.

[0060] Research has shown that, in some cases, viewers of the video playback page may be interested in an object displayed on the video playback page and may trigger many operations on that object; however, in some other cases (for example, viewers of the video playback page rarely perform trigger operations on the first candidate object corresponding to the video playback page), they may be interested in an object that is being explained or has just been explained in the live-streamed video. Based on this, embodiments of the present application provide one possible embodiment of the attention state representation information, which may specifically include history operation information and video commentary information. The history operation information is used to represent operations that a user has triggered on the first candidate object on the video playback page. The video commentary information is used to represent the state of the first candidate object in the video data played on the video playback page (e.g., being explained, explained, not explained).

[0061] Based on the content of the preceding paragraph, the embodiments of the present application further provide one possible embodiment of the above step "determining the reference object in accordance with the attention state representation information of at least one first candidate object corresponding to the video playback page," which may specifically include steps 1-2.

[0062] Step 1: When the history operation activity information of the first target object among the at least one first candidate object satisfies the first preset condition, the reference object is determined according to the first target object.

[0063] The first target object is a first candidate object whose history operation information satisfies a first preset condition. In the embodiments of this application, the process for determining the first target object is not limited. For example, if the "at least one first candidate object" includes N first candidate objects, the process for determining the first target object can specifically involve obtaining the history operation information of the nth first candidate object, determining whether the history operation information of the nth first candidate object satisfies the first preset condition, and if it satisfies the first preset condition, determining that the viewer of the video playback page is interested in the nth first candidate object. This allows the nth first candidate object to be considered the first target object (i.e., the user's object of interest), and the information recommendation page may subsequently display an object of the same type as the nth first candidate object. n is a positive integer, n ≤ N, and N is a positive integer.

[0064] The first preset condition is used to describe the condition to which the history operation activity information of the user's object of interest is met. In the embodiments of the present application, the first preset condition is not limited; for example, if the history operation activity information includes the number of clicks (e.g., the total number of operation triggers), the first preset condition may specifically be that the number of clicks is greater than a preset count threshold. The preset count threshold can be set in advance.

[0065] Furthermore, the embodiments of the present application do not limit the process for acquiring the history operation information. For example, in order to better ensure the real-time nature of the history operation information, the embodiments of the present application further provide one possible embodiment of the display method, in which the display method may further include the following step 1 if the attention state representation information includes at least the history operation information. The execution time of step 1 is slower than the execution time of S101.

[0066] Step 1: In response to a trigger operation on the third target object, which is one of at least one first candidate objects corresponding to the video playback page mentioned above, update the history operation information of the third target object.

[0067] The third target object is a first candidate object on which a preset operation (e.g., click, favorite, add to cart, search, view, etc.) is performed. In the embodiments of this application, the third target object is not limited and may be any first candidate object. The preset operation can be set in advance and may include, for example, operations such as click, favorite, add to cart, search, view, etc.

[0068] Furthermore, in the embodiments of the present application, the "trigger operation on the third target object among at least one first candidate object" is not limited, and may be any operation that triggers on the third target object (e.g., click, favorite, add to cart, search, view, etc.).

[0069] Furthermore, in the embodiments of the present application, the "history operation information of the third target object" is not limited and may include, for example, the number of clicks on the third target object. The number of clicks can represent the level of attention the third target object receives, and thereby the number of clicks on the third target object can represent the level of interest of viewers of the video playback page in the third target object. The number of clicks is the total number of various operations (for example, clicks, favorites, add to cart, search, view, etc.) that are triggered on the third target object.

[0070] In the embodiments of this application, the update process for the "number of clicks on the third target object" is not limited and can be performed, for example, according to a pre-set update rule. This update rule can be set according to the application scenario. For ease of understanding, an example will be given below.

[0071] For example, if the above "at least one first candidate object" includes N first candidate objects, the process for determining the number of clicks for the N first candidate objects may specifically include the following steps 11-12.

[0072] Step 11: After opening the video playback page on the client (for example, after the client's viewers enter the live streaming room displayed on the video playback page), a pre-set initialization value (for example, 0) is determined as the number of clicks for the nth first candidate object. n is a positive integer, n ≤ N, and N is a positive integer.

[0073] Step 12: After the client receives a trigger operation for the nth first candidate object, update the click count of the nth first candidate object using the following equation (1), where n is a positive integer, n ≤ N, and N is a positive integer.

[0074]

number

[0075] As can be seen from the related content of steps 11 to 12 above, in one possible embodiment, if the third target object is the nth first candidate object and the history operation information of the third target object includes the number of clicks on the third target object, then step 1 may specifically update the history operation information of the third target object using formula (1) above in response to a trigger operation on the third target object.

[0076] As can be seen from the relevant content of Step 1 above, for a client used by a viewer of a certain video data, when the client is displaying a video playback page and at least one first candidate object is displayed on the video playback page, the client receives a trigger operation (e.g., click, favorite, add to cart, search, view, etc.) on a third target object among these first candidate objects, and then updates the click count of the third target object using the above formula (1), thereby better representing the viewer's interest in the third target object, and subsequently determines whether the viewer is interested in the third target object based on the click count.

[0077] Furthermore, in the embodiments of the present application, the embodiment of step 1, "determining the reference object according to the first target object," is not limited. For example, if there is only one first target object for at least one first candidate object, that first target object can be directly determined as the reference object. Also, for example, if there are multiple first target objects for at least one first candidate object, the first target object with the highest number of clicks among these first target objects can be determined as the reference object.

[0078] As can be seen from the related content of Step 1 above, for a client used by a viewer of a certain video data, when the client is displaying a video playback page, after the client receives a trigger operation (e.g., a click operation) on a target control within the video playback page, the client can determine whether there is a first target object in at least one first candidate object corresponding to the video playback page whose history operation information satisfies a first preset condition. If there is, the client can determine that the viewer is interested in the first target object, and therefore can determine a reference object according to the first target object, thereby allowing the reference object to represent the characteristics of the viewer's object of interest (e.g., which category it belongs to).

[0079] Step 2: If the history operation information of each first candidate object does not satisfy the first preset condition, the reference object is determined according to the video explanation information of at least one of the first candidate objects.

[0080] The video explanation information for the nth first candidate object is used to represent the state of that nth first candidate object (e.g., being explained, explained, not explained) in the live streaming video played on the video playback page mentioned above. n is a positive integer, n ≤ N.

[0081] Furthermore, in the embodiments of the present application, the embodiment of step 2, "determining the reference object in accordance with the video explanatory information of the at least one first candidate object," is not limited, and for the sake of clarity, one possible embodiment of step 2 will be described below with reference.

[0082] In one possible embodiment, S102 may specifically determine a reference object according to the second target object if the history operation information of each first candidate object does not satisfy the first preset condition, and the video commentary information of the second target object among the at least one first candidate object satisfies the second preset condition. The second target object is the first candidate object whose video commentary information satisfies the second preset condition. The second preset condition can be set in advance.

[0083] In fact, research has shown that viewers of the video playback page described above may also be interested in the objects described in the live-streamed video or objects that have just been described. Based on this, embodiments of the present application further provide two possible embodiments of the second preset condition described above, each of which is described below.

[0084] In one possible embodiment, the second preset condition may specifically indicate that the video data played on the video playback page is describing the second target object, as the "video description information for the second target object" (i.e., the "video description information for the second target object" means that the second target object is in a state of being described on the video playback page). As can be seen from the above, in some cases, the second target object for the video data played on the video playback page may be the object that the video data is describing.

[0085] In another possible embodiment, the second preset condition may specifically be, as the "video explanation information for the second target object," that the second target object is in an explanation-completed state within the video playback page, and the explanation completion time for the second target object is later than the explanation completion times for other objects in the video playback page that are in an explanation-completed state. As can be seen from the above, in some cases, the second target object for video data played on the video playback page may be the object that has just been explained by the video data.

[0086] Furthermore, in the embodiments of the present application, the embodiment of step 2, "determining the reference object according to the second target object," is not limited. For example, if there is only one second target object for at least one first candidate object, the second target object can be directly determined as the reference object. Also, for example, if there are multiple second target objects for at least one first candidate object, the second target object with the latest description start time among these second target objects can be determined as the reference object.

[0087] As can be seen from the related content of Step 2 above, for a client used by a viewer of a video data, when the client is displaying a video playback page, after the client receives a trigger operation (e.g., a click operation) on a target control within the video playback page, the client can determine whether there is a first target object in at least one first candidate object corresponding to the video playback page whose history operation information satisfies a first preset condition. If not, the client can infer that the viewer may be interested in an object that is described in or has just been described in the live-streamed video. Therefore, the client can use the video description information of these first candidate objects to determine a reference object from these first candidate objects, thereby allowing the reference object to represent the characteristics of the viewer's object of interest (e.g., which category it belongs to).

[0088] As can be seen from the related content of Steps 1 and 2 above, for a client used by a viewer of certain video data, when the client is displaying a video playback page, after the client receives a trigger operation (e.g., a click operation) on a target control within the video playback page, the client can first screen for reference objects according to the history operation information of at least one first candidate object corresponding to the video playback page, and after determining that the reference object cannot be screened, it can then screen for reference objects using the video explanation information of these first candidate objects. In this way, it can be ensured that the reference object represents as much as possible an object of interest to the viewer, and thereby the object category of the reference object can represent as much as possible an object category that the viewer is relatively interested in, which is advantageous in improving the accuracy of information recommendation.

[0089] The "recommended information set corresponding to the referenced object" refers to information that should be recommended, determined according to the object category of the referenced object, and the object category corresponding to the "recommended information set corresponding to the referenced object" is the same as the object category of the referenced object. For example, if the object category of the referenced object includes the category of retro women's clothing shown in Figure 3, the "recommended information set corresponding to the referenced object" will include recommended information under the category of retro women's clothing shown in Figure 3 (for example, related information for the first live streaming room).

[0090] Furthermore, regarding the statement that the object category corresponding to the "recommended information set corresponding to the referenced object" is the same as the object category of the referenced object, it may be partially the same or completely the same. Partially the same means that, if the referenced object has multiple object categories, and the object category corresponding to the "recommended information set corresponding to the referenced object" is the same as one of the object categories of the referenced object, then it can be concluded that the object category corresponding to the "recommended information set corresponding to the referenced object" is the same as the object category of the referenced object.

[0091] Furthermore, in the embodiments of the present application, the "object category of the referenced object" is not limited, and may include, for example, any classification information related to the referenced object.

[0092] In practice, research has shown that in some application scenarios, when a user becomes interested in an object, they may want to browse other objects that are relatively similar to that object, such as in the form of object classes, object attributes, or object topics. Based on this, embodiments of the present application further provide one possible embodiment of the "object category of the referenced object" described above, in which the "object category of the referenced object" can be used to represent the classification status of the referenced object in several forms (e.g., object class, object attributes, object topics, etc.). The object class is used to describe the category belonging status of one object (e.g., multi-level categories such as clothing / spring clothes / jackets / ...). The object attributes are used to describe the properties of one object (e.g., shape, color, smell, material, etc.). The object topics are used to describe the topic belonging status of one object (e.g., topics such as retro women's clothing).

[0093] Furthermore, in the embodiments of this application, the process for obtaining the "object category of the referenced object" is not limited, and can be implemented using any existing or future method that can obtain category information for a given object.

[0094] In practice, to better improve the accuracy of object categories, the object category of an object can be determined by a pre-built classification model. Based on this, the embodiments of the present application further provide one possible embodiment of the process for obtaining the "object category of the referenced object" and, for ease of understanding, the process for determining the object category of the object to be classified will be described below using an example. The object to be classified may be any object (for example, the referenced object or the target display object).

[0095] For example, the process for determining the object category of an object to be classified may involve determining the object category of the object to be classified based on the object description information of the object to be classified and a pre-constructed object classification model. The object classification model is used to perform classification processing on the object description information of the object to be classified, and in the embodiments of this application, the embodiment of the object classification model is not limited, and any existing or future model having classification functionality can be adopted and implemented, for example.

[0096] Furthermore, in order to further improve the classification effect, the embodiments of the present invention provide one possible embodiment of the above step "determining the object category of the object to be classified according to the object description information of the object to be classified and a pre-constructed object classification model," which may specifically include the following steps 31-32.

[0097] Step 31: Feature extraction processing is performed on the object description information of the object to be classified to obtain the feature extraction result of the object to be classified, thereby representing the characteristics of the object to be classified.

[0098] The object description information of the object to be classified is used to describe the object to be classified, and in the embodiments of the present application, the "object description information of the object to be classified" is not limited and may include, for example, video data (e.g., live streaming video), audio data (e.g., audio introduction data), text data (e.g., text introduction content, user reviews, etc.) for displaying the object to be classified.

[0099] Furthermore, the embodiments of the present application do not limit the embodiment of step 31, and can be implemented by employing, for example, any existing or future feature extraction method. For example, in one possible embodiment, step 31 may specifically involve first preprocessing the object description information of the object to be classified using several information processing techniques (e.g., techniques such as natural language processing (NLP), computer vision (CV), and automatic speech recognition (ASR)), obtaining the preprocessing results, and then performing a feature extraction process on the preprocessing results using a deep learning algorithm to obtain the feature extraction results of the object to be classified.

[0100] Step 32: Using a pre-built object classification model, the feature extraction results of the object to be classified are subjected to classification processing to obtain the object category of the object to be classified, thereby enabling the object category to represent the classification result of the object to be classified in at least one classification dimension (for example, three dimensions such as object class, object attributes, and object topics).

[0101] An object classification model is used to perform classification on the input data of the object classification model using at least one classification dimension (for example, three dimensions such as object class, object attribute, and object topic).

[0102] Furthermore, the object classification model may be pre-trained using object description information for at least one second candidate object and classification annotation information for that at least one second candidate object. The object description information for the second candidate object is used to describe the second candidate object, and is similar to the related content of "object description information for the object to be classified" described above, so for brevity, a detailed explanation is omitted here. The classification annotation information for the second candidate object is used to represent the classification status of the second candidate object in at least one classification dimension (for example, three dimensions such as object class, object attribute, and object topic), and in the embodiments of this application, the classification annotation information for the second candidate object is not limited and can be performed, for example, by a manual annotation method.

[0103] Furthermore, in the embodiments of the present invention, the training process of the object classification model is not limited. For example, specifically, the object classification model may first be trained by first performing a feature extraction process on the object description information of each second candidate object to obtain the feature extraction results for each second candidate object, and then using the feature extraction results of at least one second candidate object and the classification annotation information of at least one second candidate object. In this way, the trained object classification model can perform classification processing on the input data of the object classification model (e.g., the feature extraction results of a certain object) in at least one classification dimension.

[0104] In addition, the embodiments of the present invention do not limit the embodiment of the above step "training the object classification model using the feature extraction results of at least one second candidate object and the classification annotation information of at least one second candidate object," and can be carried out by employing any existing or future method of model training based on training data, for example.

[0105] Furthermore, the embodiment of step 31 described above, "performing feature extraction processing on the object description information of each second candidate object and obtaining the feature extraction results for each second candidate object," is similar to the embodiment of step 31 described above, so for the sake of brevity, a detailed explanation is omitted here.

[0106] As can be seen from the related content of steps 31 to 32 above, after obtaining the object description information of the object to be classified, first, feature extraction processing is performed on the object description information to obtain the feature extraction results of the object to be classified, and then the feature extraction results are input into a pre-constructed object classification model, and the object classification model can determine the object category of the object to be classified according to the feature extraction results, and the object category can represent the classification result of the object to be classified in at least one classification dimension (for example, three dimensions such as object class, object attribute, and object topic).

[0107] The process for determining the "object category of the referenced object" is similar to the process for determining the "object category of the classified object," and for brevity, a detailed explanation is omitted here. Similarly, the process for determining the "object category of the target display object" is similar to the process for determining the "object category of the classified object."

[0108] The "recommended information set corresponding to the referenced object" described above can be determined according to the object category of the referenced object. For example, if the object category of the referenced object includes the first category (e.g., retro women's clothing shown in Figure 3), the second category (e.g., clothing, shoes, and bags shown in Figure 3), ..., the Eth category (e.g., mother and child supplies and books shown in Figure 3), then the "recommended information set corresponding to the referenced object" may include the recommended information set under the first category, the recommended information set under the second category, ..., and the recommended information set under the Eth category. The information in the recommended information set under the eth category can be used to recommend some other objects under the eth category to the user. e is a positive integer, e ≤ E, and E is a positive integer.

[0109] Furthermore, in the embodiments of this application, the above-mentioned "recommended information set" is not limited, and for example, specifically, some The recommended information set may include account attribute information for the candidate accounts, and each displayed object under each candidate account includes a target display object, the object category of which is the same as the object category corresponding to which the recommended information set is. The displayed object is an object that can perform several operations (e.g., interaction operations such as viewing and trading) within the live streaming room corresponding to the candidate account. The account attribute information is used to describe the attributes of the candidate account (e.g., the avatar corresponding to the candidate account, the nickname corresponding to the candidate account, etc.). To make it easier to understand, an example will be given below.

[0110] For example, if the information display page corresponding to the candidate account is used to display the second live streaming video, the candidate account may also be the streaming account of the second live streaming video, the information display page corresponding to the candidate account may also be the playback page of the second live streaming video, the account attribute information of the candidate account may be used to describe the attributes of the streaming account of the second live streaming video (e.g., avatar, nickname), the display target object under the candidate account may be an object that can perform several operations (e.g., interaction operations such as browsing and trading) within the live streaming room corresponding to the candidate account, and the target display object under the candidate account is the same display target object as the object category corresponding to the recommended information set provided by the live streaming room corresponding to the candidate account.

[0111] As can be seen from the above, when the information in the "recommended information set" is used to describe a particular live streaming room, the objects provided by that live streaming room include display objects that are the same as the object categories corresponding to the recommended information set. For example, as shown in Figure 3, if the "recommended information set" includes the relevant content of the first live streaming room shown in area 302 in Figure 3 (e.g., avatar, nickname, etc.), the relevant content of the second live streaming room shown in Figure 3 (e.g., avatar, nickname, etc.), ... then these live streaming rooms can provide several items (e.g., the short skirt shown in Figure 3, the cool summer suspender skirt, ...) under the object category corresponding to the recommended information set (e.g., retro women's clothing).

[0112] Furthermore, the object category corresponding to the above recommended information set is the same as the object category of the above referenced object, and the object category of the above target display object is also the same as the object category corresponding to the recommended information set. Therefore, the object category of the target display object is also the same as the object category of the referenced object, and thus the target display object belongs to the same type as the referenced object. As can be seen from this, candidate accounts related to the above recommended information set can provide users with objects of the same type as the referenced object.

[0113] In the embodiments of this application, the specific meaning of "the object category of the target display object is the same as the object category of the referenced object" is not limited, and they may be partially the same or completely the same. Partially the same means that when the target display object has multiple object categories and the referenced object has multiple object categories, there is a common part between the object categories of the target display object and the object categories of the referenced object.

[0114] Furthermore, the embodiments of this application do not limit the embodiments of the recommended information set described above, and can be implemented using, for example, any existing or future information aggregation method.

[0115] For example, in order to further improve the user experience, the above-mentioned first object recommendation information can be implemented in the form of a ranking list. Based on this, an embodiment of the present application provides one possible embodiment of the recommendation information set in which, if the recommendation information set includes account attribute information of multiple candidate accounts, the recommendation information set can display the account attribute information of these candidate accounts in the form of a ranking list, which is similar to the ranking list shown in Figure 3, and in this way the recommendation information set can display the account attribute information of candidate accounts in a certain order.

[0116] Furthermore, in order to further improve the user experience, embodiments of the present application provide further possible embodiments of the recommendation information set described above, in which the recommendation information set may include not only account attribute information of multiple candidate accounts, but also object display information of target display objects under each candidate account. The object display information is used to describe the target display object, and embodiments of the present application do not limit the object display information to include, for example, some text data (e.g., the object name of the target display object similar to the string "short skirt") and / or some picture data (e.g., picture data for displaying the target display object).

[0117] Furthermore, to improve the user experience, a user can jump to an information display page corresponding to a candidate account by triggering an action (e.g., clicking) on ​​the account attribute information of a candidate account in the recommended information set, and the user can view the display objects (e.g., target display objects) provided by the candidate account on that information display page. In addition, to further improve the user experience, a user can jump to an information display page corresponding to a candidate account by triggering an action (e.g., clicking) on ​​the object display information of a target display object under a candidate account in the recommended information set, and the information display page can display the relevant content of the target display object (e.g., price, performance, attributes, campaigns, etc.), and the user can quickly view the relevant content of the target display object through the object display information of the target display object, thereby improving the user's browsing experience for objects of the same type as the referenced object. The information display page is used to display content related to the candidate account, and the information display page corresponding to the candidate account can be used to display the display objects under the candidate account.

[0118] Furthermore, in the embodiments of the present invention, the "information display page corresponding to the candidate account" is not limited to the above, and for example, in a live streaming scene, the information display page corresponding to the candidate account can be used to display related content of the live streaming room corresponding to the candidate account (e.g., a second live streaming video, comment information, etc.). The second live streaming video is video data that is played on the information display page corresponding to a certain candidate account (e.g., the target account).

[0119] Furthermore, in the embodiments of the present application, the process for obtaining the recommended information set is not limited. For example, specifically, the recommended information set corresponding to the referenced object may be determined according to the object category of the referenced object, and the object category corresponding to the "recommended information set corresponding to the referenced object" may be made the same as the object category of the referenced object.

[0120] In the embodiments of this application, the embodiment of the above step "determining a recommended information set corresponding to the referenced object according to the object category of the referenced object" is not limited. For example, a candidate information set corresponding to the object category of the referenced object may be searched from a pre-established mapping relationship and determined as the recommended information set. This mapping relationship is used to record a one-to-one correspondence between different object categories and different candidate information sets. The embodiment of the candidate information set is similar to the embodiment of the recommended information set.

[0121] Furthermore, the above candidate information set can be pre-built, and if the candidate information set is displayed in the form of a ranking list, the candidate information set can be built and updated in real time according to object-related information (similar to interaction operations such as transactions) corresponding to some of the accounts in the candidate information set, thereby improving the real-time nature of the ranking list of these accounts.

[0122] Furthermore, in the embodiments of this application, the process for constructing the candidate information set described above is not limited, and in order to make it easier to understand, the process for constructing the "recommended information set corresponding to the referenced object" described above will be explained below as an example.

[0123] For example, the above "recommended information set corresponding to the referenced object" is implemented in the form of a ranking list, and the "recommended information set corresponding to the referenced object" Object category If the target category is, the process of building the “recommended information set corresponding to the referenced object” may specifically include the following steps 41-44.

[0124] Step 41: Based on the object supply information of at least one candidate account, at least one target account is determined from that at least one candidate account, thereby using the object supply information of the target account to indicate that the object category of the fourth target object under that target account is the same as the object category of the "Recommended Information Set Corresponding to the Referenced Object" described above.

[0125] The "at least one candidate account" mentioned above refers to an account that needs to be used when constructing an information recommendation ranking list (for example, a live streaming account). In the embodiments of this application, the "at least one candidate account" is not limited to, for example, a streaming account for all live streaming videos stored in one or more video application programs.

[0126] Object supply information is used to describe the relevant content of objects supplied by an account. In the embodiments of the present application, the object supply information is not limited, and for example, if the account (e.g., the candidate account or the account used) is used to provide at least one third candidate object, the object supply information for the live streaming video may include the object categories of these third candidate objects. The third candidate object is an object that can perform several operations (e.g., interaction operations such as viewing and trading) within the live streaming room corresponding to the account, and the third candidate object is similar to the first candidate object, and for brevity, a detailed explanation is omitted here.

[0127] The above "at least one target account" is used to provide other objects under the target category other than the referenced object mentioned above.

[0128] The "fourth target object" mentioned above refers to an object under the target category provided by the account being used. As can be seen from the above, if the display page of the account being used can display M third candidate objects, it is possible to determine whether or not the target category exists in at least one object category of the mth third candidate object displayed on the display page. If the target category exists, it can be determined that the mth third candidate object belongs to the same type as the referenced target object mentioned above, and therefore the mth third candidate object can be considered as the fourth target object corresponding to the account being used. m is a positive integer, m ≤ M, and M is a positive integer.

[0129] As can be seen from the related content of step 41 above, after determining that there is a target category in the object category of the referenced object, it can be determined that it is necessary to construct an information recommendation ranking list corresponding to the target category using the target accounts that correspond to other objects under the target category other than the referenced object. Therefore, first, the target category is aggregated into all candidate accounts to obtain at least one target account, each of which can provide at least one object under the target category, and subsequently, these target accounts can be used to construct an information recommendation ranking list corresponding to the target category.

[0130] Step 42: Determine the recommended representation data for at least one target account based on the object interaction information of that at least one target account.

[0131] Object interaction information is used to describe interaction statuses (e.g., operation status and / or transaction status) triggered on objects under the target account, and in embodiments of the present application, such object interaction information is not limited and may include, for example, real-time object sales. Real-time object sales refers to the real-time sales of all objects under the target account.

[0132] The above-mentioned "Recommended Representation Data for the Target Account" is used to describe the likelihood that the target account will be recommended to the user. The larger the Recommended Representation Data for the target account, the greater the likelihood that the target account will be recommended to the user, and the smaller the Recommended Representation Data for the target account, the less likely the target account will be recommended to the user.

[0133] Furthermore, in the embodiments of the present application, the process for determining the "recommended representation data for the target account" is not limited. For example, if the object interaction information includes real-time object sales volume, the process for determining the "recommended representation data for the target account" may specifically involve determining the recommended representation data for the target account according to the real-time object sales volume of the target account, and making the recommended representation data for the target account proportional to the real-time object sales volume of the target account.

[0134] As can be seen from the relevant content of step 42 above, after obtaining at least one target account under the target category above, the recommendation representation data for each target account is determined according to the object interaction information of each target account (e.g., the total sales volume of all objects), so that the recommendation representation data for each target account can represent the likelihood that each target account is recommended to the user.

[0135] Step 43: Based on the recommended representation data of at least one target account, determine at least one display target account from that at least one target account that satisfies the preset recommendation criteria. The display target account is a target account that satisfies the preset recommendation criteria.

[0136] Preset recommendation conditions can be set in advance; for example, specifically, they may recommend the T target accounts with the largest number of representation data, where T is a positive integer.

[0137] As can be seen from the related content of step 43 above, for at least one target account under the target category, after obtaining the recommended expression data for each target account, these target accounts can be sorted according to their recommended expression data to obtain a sort result, which can represent the arrangement state when these target accounts are arranged in descending order of the recommended expression data, and furthermore, the T target accounts sorted to the top of the sort result can be considered as display target accounts (i.e., accounts whose information needs to be displayed in the ranking list), and a ranking list can be constructed subsequently based on these display target accounts.

[0138] Step 44: Based on the relevant information of at least one target account (e.g., account attribute information and / or object display information of the target display object under the target account) and the recommended representation data of the at least one target account, a set of recommendation information is constructed so that the set of recommendation information can display the relevant information of these target accounts in the form of a ranking list.

[0139] In the embodiments of the present invention, after obtaining at least one target account and recommendation expression data for said at least one target account, the relevant information for said target accounts can be arranged in descending order of the recommendation expression data according to the recommendation expression data of said target accounts to obtain the arrangement result, and further, a set of recommendation information corresponding to a target category can be constructed according to the arrangement result, thereby allowing the set of recommendation information to recommend these target accounts to the user according to the arrangement result.

[0140] As can be seen from the related content of steps 41 to 44 above, after determining that there is a target category in the object category of the referenced object, first, at least one target account under the target category is selected from a large number of candidate accounts using the target category, and then these target accounts are sorted according to the object interaction information of these target accounts to obtain a set of recommendation information corresponding to the target category, thereby the set of recommendation information can represent the object recommendation information under the target category.

[0141] The process for constructing the "candidate information set" described above is similar to the construction process shown in steps 41-44, and for brevity, a detailed explanation is omitted here.

[0142] As can be seen from the related content of the "Recommended Information Set" described above, for a client used by a viewer of a certain video data, when the client is displaying the video playback page, after the client receives a trigger operation (e.g., a click operation) on a target control within the video playback page, the client can first obtain the referenced object (i.e., the user's object of interest), and then obtain the recommended information set corresponding to the referenced object according to the object category of the referenced object. The object category corresponding to the recommended information set is made the same as the object category of the referenced object, so that the information in the recommended information set can describe the related content of several identical objects of the referenced object (e.g., account attribute information, object display information, etc.), and subsequently the viewer can view these identical objects using the information in the recommended information set.

[0143] The "recommended information page" described above is used to display a set of recommended information corresponding to the referenced object described above. In the embodiments of this application, the recommended information page is not limited; for example, the recommended information page may be the dropdown page 301 shown in Figure 3.

[0144] Furthermore, the embodiments of this application do not limit the display method of the information recommendation page, and can be implemented using any existing or future page display method. For example, to further improve the user experience, the information recommendation page can be directly displayed on the video playback page using a preset display method, thus allowing users to view the information recommendation page without leaving the video playback page. The preset display method can be set in advance and may be, for example, a dropdown page (for example, page 301 displayed in a dropdown page format on page 300 in Figure 3), or it may be implemented in a way that allows other pages to be displayed on the video playback page.

[0145] Furthermore, in the embodiments of this application, the method of displaying information on the information recommendation page is not limited, and any existing or future object recommendation method can be adopted for display. Also, for example, if the referenced object corresponds to multiple recommendation information sets, the client can, after receiving a trigger operation on the target control in the video playback page, display the information recommendation page, and directly display the first information set of these recommendation information sets (for example, the information set under the overall ranking tag shown in Figure 3) and several category tags (for example, the retro women's clothing tag, clothing, shoes, and bags tag shown in Figure 3) on the information recommendation page. Subsequently, in response to a trigger operation (for example, a click operation) on one of these category tags (for example, the retro women's clothing tag shown in Figure 3), the information recommendation page can display the recommendation information set corresponding to that category tag (for example, the information set under the retro women's clothing tag shown in Figure 3). In this way, the objective of providing the user with a different type of object than the referenced object can be achieved, thereby better meeting the user's information browsing needs, and thus is advantageous in improving the user experience.

[0146] As can be seen from the related content of S101 to S102 above, for a client used by a viewer of certain video data, when the client is displaying the video playback page, the client displays several first candidate objects to the viewer, and after the client receives a trigger operation on the target control within the video playback page, it displays an information recommendation page, and the information recommendation page can display a set of recommended information corresponding to the referenced object among these first candidate objects. The set of recommended information includes account attribute information of multiple candidate accounts, and each of the display target objects under each candidate account includes a target display object, and the object category of the target display object is the same as the object category corresponding to the set of recommended information, and the object category corresponding to the set of recommended information is the same as the category of the referenced object. Thus, these candidate accounts can provide the viewer with several other objects (for example, objects of the same type) related to the referenced object.

[0147] As can be seen from the above, since the referenced object is determined according to the attention state representation information of at least one first candidate object corresponding to the video playback page, the referenced object can represent the viewer's object of interest, thereby allowing us to infer that the viewer may be interested in other objects related to the referenced object (e.g., objects of the same type). Therefore, after recommending a set of recommendation information corresponding to the referenced object to the viewer, the viewer can browse other objects related to the referenced object using the recommended information set. In this way, the viewer's object browsing experience can be better satisfied, which is advantageous in improving the user experience.

[0148] In practice, to further improve the user experience, the embodiments of the present invention further provide one possible embodiment of the target control described above, in which the target control displays prompt information (for example, the information "Ranked 9th in retro women's clothing" as shown in Figure 2), and the prompt information can prompt the viewer of the video playback page to view the ranking list corresponding to their object of interest.

[0149] Furthermore, in order to further improve the user experience, the prompt information displayed on the target control changes in response to changes in the user's object of interest. Based on this, embodiments of the present application further provide another possible embodiment of the display method, in which, if the display method includes at least S101-S102, the display method further includes the following S103. The execution time of S103 is slower than the execution time of S101, and in embodiments of the present application, the execution time of S103 is not limited.

[0150] S103: After updating the referenced object using the attention state representation information of at least one first candidate object, the ranking list position description information of the account corresponding to the video playback page is updated, and the prompt information on the target control is updated using the ranking list position description information. The ranking list position description information is used to describe the sort position of the account attribute information of the account corresponding to the video playback page in the "recommended information set corresponding to the referenced object".

[0151] Furthermore, in the embodiment of this application, the ranking list position description information is not limited to the above, and may be, for example, information such as "Ranked 9th in retro women's clothing" as shown in Figure 2.

[0152] Furthermore, in the embodiments of the present application, the process for determining the ranking list position description information is not limited. For example, if the referenced object corresponds to one set of recommendation information, the sort position of the account attribute information of the account corresponding to the video playback page in the "recommended information set corresponding to the referenced object" can be directly determined as the ranking list position description information. Also, for example, if the referenced object corresponds to multiple sets of recommendation information, the ranking list position description information can be determined from the sort positions of the account attribute information of the account corresponding to the video playback page in these sets of recommendation information according to a pre-set rule (for example, different object categories correspond to different priorities), and the ranking list position description information can describe the sort position of the account corresponding to the video playback page in a particular set of recommendation information.

[0153] In the embodiments of this application, the timing of updating the referenced object is not limited; for example, it may be updated once at regular intervals. Alternatively, for example, an operation may be triggered once on an object within the video playback page, and then the update process for the referenced object may be executed immediately afterward.

[0154] As can be seen from the related content of S103 above, for a client used by a viewer of a certain video data, when the client is displaying the video playback page, after the update process of the referenced object is completed, the recommended information set corresponding to the referenced object is first updated by the object category of the referenced object, and further, the display content of the target control can be updated based on the sort position of the account corresponding to the video playback page in the recommended information set. In this way, the real-time nature of the display content of the target control can be ensured, which is advantageous for improving the user experience.

[0155] Based on the display method according to the embodiment of the present application, the embodiment of the present application further provides a display device, which will be interpreted and described below with reference to Figure 4. Figure 4 is a schematic diagram of the configuration of the display device according to the embodiment of the present application. For technical details of the display device according to the embodiment of the present application, please refer to the relevant content of the display method described above.

[0156] As shown in Figure 4, the display device 400 according to the embodiment of the present application is A first display unit 401 used to display a video playback page, A second display unit 402 used to display an information recommendation page in response to a trigger operation on a target control within the video playback page, wherein the information recommendation page displays a set of recommendation information corresponding to a reference object, the reference object is determined according to the attention state representation information of at least one first candidate object corresponding to the video playback page, the recommendation information set includes account attribute information of multiple candidate accounts, each of the display target objects under each candidate account includes a target display object, the object category of the target display object is the same as the object category corresponding to the recommendation information set, and the object category corresponding to the recommendation information set is the same as the object category of the reference object.

[0157] In one possible embodiment, the attention state representation information includes history operation action information and video commentary information. When the history operation activity information of the first target object among the at least one first candidate object satisfies the first preset condition, the referenced object is determined according to the first target object. If none of the history operation information for each of the first candidate objects satisfies the first preset condition, the referenced object is determined according to the video explanation information for at least one of the first candidate objects.

[0158] In one possible embodiment, if the history operation activity information of each of the first candidate objects does not satisfy the first preset condition, and the video description information of the second target object among the at least one first candidate object satisfies the second preset condition, the referenced object is determined according to the second target object.

[0159] In one possible embodiment, the history operation information includes the number of clicks, and the first preset condition is that the number of clicks on the first target object is greater than a preset count threshold.

[0160] In one possible embodiment, the second preset condition includes, as video commentary information for the second target object, that the second target object is in a commentary state within the video playback page, Or, The second preset condition includes, as video explanation information for the second target object, that the second target object is in an explanation completion state within the video playback page, and that the explanation completion time for the second target object is later than the explanation completion times for other objects that are in an explanation completion state within the video playback page.

[0161] In one possible embodiment, the attention state representation information includes history operation action information, The display device 400 is The system further includes an information update unit used to update the history operation information of the third target object in response to a trigger operation on the third target object, which is one of at least one first candidate objects corresponding to the video playback page.

[0162] In one possible embodiment, the recommendation information set further includes object display information for target display objects under each candidate account.

[0163] In one possible embodiment, the object to be classified is the referenced object or the target display object, The object category of the object to be classified is determined according to the object description information of the object to be classified and a pre-constructed object classification model, and the object classification model is used to perform classification processing on the object description information of the object to be classified.

[0164] In one possible embodiment, the video playback page is used to display a first live streaming video, and / or the information display page corresponding to the candidate account is used to display a second live streaming video.

[0165] As can be seen from the details of the display device 400 described above, in the case of the display device 400 according to the embodiment of the present application, when the display device 400 is displaying a video playback page, the display device 400 can display several first candidate objects to the viewer, and after the display device 400 receives a trigger operation on the target control in the video playback page, it displays an information recommendation page and displays a set of recommended information corresponding to the referenced object on the information recommendation page. The set of recommended information includes account attribute information of multiple candidate accounts, and each of the display target objects under each candidate account includes a target display object, and the object category of the target display object is the same as the object category corresponding to the set of recommended information, and the object category corresponding to the set of recommended information is the same as the category of the referenced object, so that these candidate accounts can provide the viewer with several other objects (for example, objects of the same type) related to the referenced object.

[0166] As can be seen from the above, since the referenced object is determined according to the attention state representation information of at least one first candidate object corresponding to the video playback page, the referenced object can represent the viewer's object of interest, thereby allowing us to infer that the viewer may be interested in other objects related to the referenced object (e.g., objects of the same type). Therefore, after recommending a set of recommendation information corresponding to the referenced object to the viewer, the viewer can browse other objects related to the referenced object using the recommended information set. In this way, the viewer's object browsing experience can be better satisfied, which is advantageous in improving the user experience.

[0167] Furthermore, research has shown that, in some cases, viewers of live streaming videos may want to view not only the objects provided by the live streaming room, but also several other objects besides those provided by the live streaming room. However, in some related means, viewers can leave the current live streaming video and then find and enter other live streaming videos through a series of operations, thereby continuously viewing the objects displayed in those live streaming videos. This makes the operation of viewing other objects relatively complex, and as a result, the object viewing experience for the viewer is relatively poor.

[0168] Based on the above findings, embodiments of the present application provide a display method that, for a client used by a viewer of video data, displays an information recommendation page after the client receives a trigger operation (e.g., a click operation) on a target control within the video playback page when the client is viewing the video playback page. The information recommendation page includes multiple recommendation sets, each corresponding to a different object category, each recommendation set includes account attribute information for multiple candidate accounts, and each display target object under each candidate account in the same recommendation set includes a target display object, the object category of the target display object being the same as the object category corresponding to the recommendation set.

[0169] As can be seen from the above, the information recommendation page contains multiple sets of recommended information, and each set of recommended information corresponds to a different object category. Therefore, the information recommendation page can provide users with sets of recommended information under several object categories, allowing users to view sets of recommended information under different object categories from the information recommendation page. In this way, the user's information viewing needs can be better met, which is advantageous for improving the user experience.

[0170] To better understand the technical solution related to this application, the display method related to this application will first be explained below with reference to several drawings.

[0171] As shown in Figure 1, the display method according to the embodiment of the present application includes the following S501-S502.

[0172] S501: Displays a video playback page that includes target controls.

[0173] A video playback page is a playback area for a single video data. In other words, a single video data can occupy the entire area of ​​the video playback page for display. Furthermore, in the embodiments of this application, the video playback page is not limited and may be, for example, a live streaming video page (e.g., the live streaming video page 200 shown in Figure 2) or a short video page. As can be seen from the above, in one possible embodiment, the video playback page can be used to display a first live streaming video (e.g., a live streaming video displayed in page 200 in Figure 2). The first live streaming video is a live streaming video that is played on the video playback page.

[0174] Furthermore, the video playback page can be used to perform display processing on at least one first candidate object corresponding to the video playback page. The first candidate object is an object on which several operations (e.g., interaction operations such as browsing and trading) can be performed within the live streaming room represented by the video playback page. In other words, in the case of a live streaming room represented by the video playback page, viewers of the live streaming room can perform several interaction operations (e.g., interaction operations such as browsing and trading) on ​​the first candidate object within the live streaming room.

[0175] Furthermore, in the embodiments of the present application, the first candidate object is not limited. For example, if the video playback page is a live streaming video page (for example, the live streaming video page 200 shown in Figure 2), the first candidate object may be any product described in the live streaming video on the video playback page, any shopping product displayed by a specific operation (for example, by clicking the control 202 shown in Figure 2), or any showcase product displayed by a specific operation (for example, by clicking a certain control).

[0176] Furthermore, in the embodiments of this application, the shopping products are not limited; for example, the shopping products include at least two types of products, the first type of product may be the product described, and the second type of product may be a product other than the product described. Also, in the embodiments of this application, the showcase products are not limited; for example, they may be products displayed on a showcase display page corresponding to the live streaming video page. Also, in the embodiments of this application, the relationship between shopping products and showcase products is not limited; for example, there may be common parts between them, or there may be no common parts.

[0177] Furthermore, target controls are located on the video playback page mentioned above. These target controls are used to trigger an information recommendation process, and in the embodiments of this application, the target controls are not limited to, for example, control 201 shown in Figure 2.

[0178] As can be seen from the related content of S501 above, for a client used by a viewer of a certain video data, when the client is displaying the video playback page, the client can display several first candidate objects to the viewer, thereby allowing the viewer to perform interaction operations such as browsing (or trading) on ​​one or more of these first candidate objects on the video playback page. Furthermore, if a target control (for example, control 201 shown in Figure 2) is displayed to the client, the viewer can use the target control to browse several other objects other than these first candidate objects (for example, other objects under the retro women's clothing shown in Figure 3).

[0179] S502: In response to a trigger operation on a target control, an information recommendation page is displayed, the information recommendation page contains multiple sets of recommendation information, each set of recommendation information corresponds to a different object category, each set of recommendation information contains account attribute information for multiple candidate accounts, each of the displayed objects under each candidate account in the same set of recommendation information contains a target display object, and the object category of the target display object is the same as the object category corresponding to the recommendation information set.

[0180] In the embodiments of the present application, the embodiment of the "trigger operation on the target control" is not limited, and may be, for example, a click operation.

[0181] The information recommendation page is used to display several recommended items (for example, several recommendations under the overall ranking shown in Figure 3, several recommendations under the category of retro women's clothing, several recommendations under the category of clothing, shoes, and bags).

[0182] Furthermore, the embodiments of this application do not limit the display method of the information recommendation page, and can be implemented using any existing or future page display method. For example, in order to further improve the user experience, the information recommendation page can be displayed on the video playback page according to a preset display method, and in this way, the information recommendation page can be viewed without leaving the video playback page. The preset display method can be set in advance and may be, for example, a dropdown page (for example, page 301 displayed in a dropdown page format on page 300 in Figure 3).

[0183] Furthermore, an information recommendation page may contain multiple sets of recommendation information, and each set of recommendation information may correspond to a different object category. In other words, the information recommendation page may contain sets of recommendation information corresponding to multiple object categories. For example, if the information recommendation page is page 300 shown in Figure 3, the information recommendation page may include a set of recommendation information corresponding to the overall ranking, a set of recommendation information corresponding to the category of retro women's clothing, a set of recommendation information corresponding to the category of clothing, shoes, and bags, a set of recommendation information corresponding to the category of mother and child products and books, and so on.

[0184] The above-mentioned "recommended information set" refers to an aggregated state of several recommended information sets. In the embodiments of this application, the recommended information sets are not limited; for example, each recommended information set may include account attribute information for multiple candidate accounts. Each display target object under each candidate account in the same recommended information set includes a target display object, and the object category of the target display object is the same as the object category corresponding to the recommended information set. The display target object is an object that can perform several operations (e.g., interaction operations such as viewing and trading) within the live streaming room corresponding to the candidate account. The account attribute information is used to describe the attributes of the candidate account (e.g., the avatar corresponding to the candidate account, the nickname corresponding to the candidate account, etc.).

[0185] In the embodiments of this application, the specific meaning of "the object category of the target display object is the same as the object category corresponding to the recommended information set" is not limited, and for example, it may be partially the same or completely the same. Partially the same means that, if the target display object has multiple object categories, and the object category corresponding to the recommended information set is the same as one of the object categories of the target display object, then the conclusion that "the object category of the target display object is the same as the object category corresponding to the recommended information set" can be reached.

[0186] To make the content of the above two paragraphs easier to understand, an example is provided below.

[0187] For example, regarding a set of recommendation information corresponding to a target category (for example, the category of retro women's clothing shown in Figure 3), the set of recommendation information may include account attribute information of at least one candidate account (for example, account attribute information of the account corresponding to the first live streaming room shown in Figure 3, account attribute information of the account corresponding to the second live streaming room, ...), and each of the displayable objects under each candidate account in the set of recommendation information includes target display objects belonging to the target category (for example, the short skirt, the cool summer suspender skirt shown in Figure 3, ...). The target category is any one object category, for example, the target category may be the category of retro women's clothing shown in Figure 3.

[0188] As can be seen from the above, when the information recorded in the "recommended information set" is used to describe a particular live streaming room, the objects provided by that live streaming room will include objects that are the same as the object categories corresponding to the recommended information set. For example, as shown in Figure 3, if the "recommended information set" includes the relevant content of the first live streaming room shown in Figure 3 (e.g., avatar, nickname, etc.), the relevant content of the second live streaming room (e.g., avatar, nickname, etc.), etc., then these live streaming rooms can provide several items (e.g., the short skirt shown in Figure 3, the cool summer suspender skirt, etc.) under the object category corresponding to the recommended information set (e.g., under the category of retro women's clothing).

[0189] Furthermore, the embodiments of the present application do not limit the embodiments of the account attribute information described above. For example, in one possible embodiment, for a given candidate account, the account attribute information of the candidate account may include at least one of an identification icon corresponding to the candidate account and an identification text corresponding to the candidate account. The identification icon is used to mark the candidate account with image data, and the embodiments of the present application do not limit the identification icon, and may be implemented, for example, in the same way as the "Avatar of the First Live Streaming Room" shown in area 302 in Figure 3. The identification text is used to mark the candidate account with text data, and the embodiments of the present application do not limit the identification text, and may be implemented, for example, in the same way as the "Nickname of the First Live Streaming Room" shown in area 302 in Figure 3.

[0190] In practice, to better improve the user experience, the above account attribute information can not only display relevant attributes of the candidate account to the user, but can also trigger the process of displaying the candidate account's information display page. Based on this, an embodiment of the present application provides one possible embodiment of the display method, in which the display method may further include the following step 51. The execution time of step 51 is slower than the execution time of S502.

[0191] Step 51: If the information recommendation page displays account attribute information for the target account among multiple candidate accounts, the system will display the information display page corresponding to the target account in response to a trigger operation on the account attribute information of that target account.

[0192] A target account is a candidate account selected by the user, as displayed on the information recommendation page (i.e., the account attribute information of the target account was triggered by an action performed by the user). For example, if the information recommendation page is page 301 shown in Figure 3, and these candidate accounts include an account corresponding to the first live streaming room, an account corresponding to the second live streaming room, etc., then after receiving a trigger operation (e.g., a click) on area 302, the client can determine that the account corresponding to the first live streaming room has been selected by the user, and therefore can display the information display page corresponding to the account corresponding to the first live streaming room, and the user can understand the relevant content of the first live streaming room from the information display page.

[0193] Furthermore, in the embodiments of the present invention, the "trigger operation on the account attribute information of the target account" is not limited, and may, for example, be a click operation within the display area of ​​the account attribute information of the target account.

[0194] The "information display page corresponding to the target account" described above is used to display content related to the target account, and the information display page corresponding to the target account can be used to display the display target objects under the target account. Furthermore, in the embodiments of the present application, the "information display page corresponding to the target account" is not limited, and for example, in a live streaming scene, the information display page corresponding to the target account can be used to display related content of the live streaming room corresponding to the target account (e.g., a second live streaming video, comment information, etc.). The second live streaming video is video data played on the information display page corresponding to a candidate account (e.g., the target account).

[0195] As can be seen from the related content of step 51 above, when a viewer of a video data uses a client that displays an information recommendation page (for example, page 301 shown in Figure 3), and that information recommendation page displays account attribute information for several candidate accounts (for example, the account corresponding to the first live streaming room shown in Figure 3, the account corresponding to the second live streaming room, etc.), the client receives a trigger operation on the account attribute information of the target account among these candidate accounts (for example, a click operation is triggered in area 302 in Figure 3), and then displays an information display page corresponding to the target account (for example, the live streaming video playback page for the first live streaming room shown in Figure 3), and the viewer can view information related to the target account (for example, live streaming room information, etc.) on that information display page. In this way, the viewer can directly enter other live streaming rooms and view some object information through the information recommendation page, and thus the viewer's information viewing experience can be effectively improved.

[0196] In practice, for any single set of recommendation information, the set can not only display account attribute information for several candidate accounts, but also display objects belonging to the target category under these candidate accounts. Based on this, embodiments of the present application further provide one possible embodiment of the set of recommendation information in which the set of recommendation information includes account attribute information for multiple candidate accounts, and if each of the displayed objects under each candidate account in the set of recommendation information includes a target display object, the set of recommendation information may further include object display information for the target display objects under these candidate accounts. The object display information is used to describe the target display object.

[0197] Furthermore, in the embodiments of the present application, the object display information of the target display object is not limited and may include, for example, at least one of the text description information and the picture description information of the target display object. The text description information is used to describe the target display object using several characters, and in the embodiments of the present application, the text description information is not limited and may include, for example, the object name of the target display object (similar to the string "short skirt" shown in area 302 in Figure 3). The picture description information is used to describe the target display object using image data, and in the embodiments of the present application, the picture description information is not limited and may include, for example, image data corresponding to the target display object (e.g., a product picture).

[0198] In practice, to better improve the user experience, the object display information of the target display object can not only display to the user content related to the target display object (e.g., object name, object picture, etc.), but can also trigger the information display process of the target display object. Based on this, embodiments of the present application further provide another possible embodiment of the display method, in which the display method further includes the following step 52. The execution time of step 52 is slower than the execution time of S502.

[0199] Step 52: If the above information recommendation page displays object display information for a target display object under a target account among multiple candidate accounts, in response to a trigger operation on the object display information of the target display object under that target account, the information display page corresponding to that target account is displayed, and the information display interface corresponding to the target display object under that target account is displayed on the information display page corresponding to that target account. The information display interface is used to display the relevant content of the target display object under that target account (e.g., object description, object interactive operations, object campaign status, etc.).

[0200] In addition, in the embodiments of this application, the phrase "in response to a trigger operation on the object display information of the target display object under the target account" is not limited, and may be, for example, a click operation. Furthermore, in the embodiments of this application, the embodiment of "displaying the information display interface corresponding to the target display object under the target account on the information display page corresponding to the target account" is not limited, and can be implemented by, for example, any existing or future interface display method (for example, a method of displaying an interface corresponding to a certain product on a live streaming page).

[0201] As can be seen from the related content of step 52 above, when a viewer of a video data uses a client and the client is displaying an information recommendation page (for example, page 301 shown in Figure 3), and the information recommendation page displays object display information for target display objects under several candidate accounts, after the client receives a trigger operation (for example, a click operation) for the object display information of a target display object under one of the target accounts, the client not only displays the information display page corresponding to the target account, but also directly displays the information display interface corresponding to the target display object under the target account on the information display page, allowing the viewer to directly locate and display the related content of the target display object the moment the information display page is opened. This allows the viewer to quickly view the related content of the target display object from the information display page, which is advantageous in improving the viewer's object viewing efficiency and, consequently, in improving the viewer's information viewing experience.

[0202] Furthermore, since the above information recommendation page may include a set of recommended information corresponding to multiple object categories, category tags corresponding to these object categories (for example, Figure) may be used to better improve the information display effect of the information recommendation page. 3 Displaying overall ranking tags , Toro women's clothing tag , clothing Category: Shoes, Bags Tags ,motherThe display process of recommended information sets corresponding to these object categories can be controlled by tags such as "children's items" and "books." Based on this, an embodiment of the present invention further provides one possible embodiment of the information recommendation page, in which the information recommendation page may include not only recommended information sets corresponding to multiple object categories, but also category tags corresponding to the multiple object categories, and the object categories corresponding to the category tags can be displayed on the category tags. In this way, these object categories are used as an intermediate medium to establish a one-to-one correspondence between these category tags and these recommended information sets, and the object categories corresponding to the recommended information sets are displayed on the category tags that correspond to the recommended information sets, and the display control of these recommended information sets can be realized by a subsequent control process for these category tags.

[0203] Based on this, the embodiments of the present application further provide yet another possible embodiment of the display method, in which the information recommendation page includes a plurality of recommendation information sets and a plurality of category tags, and there is a one-to-one correspondence between these category tags and these recommendation information sets, the display method may further include the following step 53. The execution time of step 53 is slower than the execution time of S502.

[0204] Step 53: If the set of recommended information currently displayed on the information recommendation page corresponds to the first of the multiple category tags (i.e., the information recommendation page displays the set of recommended information corresponding to the first of the multiple category tags), in response to a trigger operation for the second of the multiple category tags, the set of recommended information displayed on the information recommendation page is switched from the set of recommended information corresponding to the first tag to the set of recommended information corresponding to the second tag (for example, the information recommendation page displays the set of recommended information corresponding to the second tag and cancels the display of the set of recommended information corresponding to the first tag).

[0205] The first tag is a category tag that corresponds to the set of recommended information displayed on the recommended information page. For example, if the recommended information page is page 301 shown in Figure 3, the first tag is: 3 You could also use the category tag "retro women's clothing."

[0206] The second tag is a category tag selected by the user. For example, if the recommended information page is page 301 shown in Figure 3, the client will select the category tag within the recommended information page. Clothing, shoes, and bags tag area After receiving a trigger operation for the category tag shown, Figure 3 The category tags "Clothing, Shoes, and Bags" shown can be considered as a secondary tag.

[0207] As can be seen from the related content of step 53 above, for a client used by a viewer of a certain video data, the client is displaying an information recommendation page (for example, page 301 shown in Figure 3), and the first tag among multiple category tags on the information recommendation page (for example, Figure 301) 3 When displaying a set of recommended information corresponding to the category tag "Retro Women's Clothing," if the client receives a trigger operation (e.g., a click operation) for the second of these category tags, the set of recommended information displayed on the information recommendation page will change from the set of recommended information corresponding to the first tag to the set of recommended information corresponding to the second tag (e.g., Figure 3 By switching to the category tag shown (Clothing, Shoes, Bags), the objective of switching from one set of recommended information to another on the recommended information page can be achieved, thereby controlling the display process of the recommended information sets corresponding to these category tags, and further benefiting the viewer's flexibility in browsing recommended information under different object categories, thus benefiting the viewer's information browsing experience.

[0208] Furthermore, in the embodiments of this application, the process for determining the multiple sets of recommended information within the information recommendation page is not limited, and can be pre-set, for example, according to the application scene.

[0209] In practice, research has shown that for viewers of the video playback page described above, if they become interested in an object displayed on the page, they may want to see other objects of the same type (e.g., other objects under the same object class, other objects under the same object topic, other objects under the same object attribute, etc.). The object class is used to describe the categorical belonging of an object (e.g., multi-level categories such as clothing / spring wear / jackets / ...). The object attribute is used to describe the properties of an object (e.g., shape, color, smell, material, etc.). The object topic is used to describe the topical belonging of an object (e.g., a topic such as retro women's clothing).

[0210] Based on this, in order to further improve the user experience, embodiments of the present application further provide one possible embodiment of the process for determining multiple sets of recommended information within the information recommendation page, in which, if at least one first candidate object corresponding to the video playback page has a target reference object that satisfies preset conditions, these sets of recommended information are determined according to the object category of the target reference object, and the object category corresponding to these sets of recommended information is made the same as the object category of the target reference object, thereby these sets of recommended information are used to recommend other objects belonging to the same category as the target reference object. For ease of understanding, an example is given below.

[0211] For example, if the object categories of the target reference object include Category 1, Category 2, Category 3, ..., and Category P, then the recommended information sets corresponding to Category 1, Category 2, Category 3, ..., and Category P can be determined as multiple recommended information sets placed on the recommended information page, and subsequently, the user can view identical objects under Category 1, Category 2, ... of the target reference object through this recommended information page. P is a positive integer.

[0212] The "target reference object" mentioned above refers to the first candidate object among at least one first candidate object corresponding to the video playback page mentioned above that satisfies the preset conditions, thereby enabling the target reference object to represent the user's object of interest. These preset conditions can be set in advance, and two examples are given below to illustrate them for easier understanding.

[0213] Example 1: Research has shown that, for viewers of the above video playback page, if they become interested in an object displayed on the video playback page, they may trigger several actions on that object (e.g., click, favorite, add to cart, search, view, etc.). Based on this, embodiments of the present application provide one possible embodiment of the above preset condition, which may specifically include the historical action information of the target reference object satisfying the preset action condition. The historical action information is used to represent the actions (e.g., click, favorite, add to cart, search, view, etc.) that the user has triggered on the target reference object on the video playback page. The preset action condition can be set in advance, for example, specifically, the number of clicks on the target reference object (e.g., total number of action triggers) may reach a preset threshold.

[0214] As can be seen from the above, for a client used by a viewer of certain video data, when the client is displaying a video playback page, after the client receives a trigger operation (e.g., a click operation) on a target control within the video playback page, the client can determine whether there is at least one first candidate object corresponding to the video playback page whose history operation activity information satisfies the preset operation conditions. If there is, the client can determine that the viewer is interested in the "first candidate object whose history operation activity information satisfies the preset operation conditions," and therefore, the "first candidate object whose history operation activity information satisfies the preset operation conditions" can be considered as a target reference object, and thereby the target reference object can represent the characteristics of the viewer's object of interest (e.g., which category it belongs to).

[0215] Example 2: In some cases (for example, when viewers of the video playback page rarely trigger an action on the first candidate object corresponding to the video playback page), viewers of the video playback page may be interested in the object being described or recently described within the video playback page. Based on this, embodiments of the present application provide one possible embodiment of the preset condition, which may specifically include the video description state of the target reference object within the video playback page satisfying the preset state condition.

[0216] Preset state conditions can be set in advance. For example, the "video commentary state within the video playback page of the target reference object" can indicate that the video data played on the video playback page is commentating on the target reference object (i.e., the "video commentary state within the video playback page of the target reference object" indicates that the target reference object is in the commentary state within the video playback page), or that the "video commentary state within the video playback page of the target reference object" indicates that the commentary is complete within the video playback page, and the commentary completion time for the target reference object is later than the commentary completion time for other objects in the commentary completion state within the video playback page (i.e., the "video commentary state within the video playback page of the target reference object" indicates that the target reference object has just been commentated on within the video playback page).

[0217] As can be seen from the above two paragraphs, for a client used by a viewer of a certain video data, when the client is displaying a video playback page, after the client receives a trigger operation (e.g., a click operation) on a target control within the video playback page, the client can determine whether there is at least one first candidate object corresponding to the video playback page whose history operation activity information satisfies the preset operation conditions. If not, the client can screen these first candidate objects according to the video commentary state of these first candidate objects within the video playback page for first candidate objects whose video commentary state satisfies the preset state conditions, and can make the "first candidate object whose video commentary state satisfies the preset state conditions" the target reference object, thereby allowing the target reference object to represent the characteristics of the viewer's object of interest (e.g., which category it belongs to).

[0218] Furthermore, the embodiments of this application do not limit the process for determining the object category of an object (for example, the target display object or the target reference object), and can employ, for example, any existing or future object classification determination process.

[0219] Furthermore, in order to further improve the classification effect, the embodiments of the present application provide one possible embodiment of the "process for determining the object category of an object" described above, and for ease of understanding, the process for determining the object category of an object to be classified will be described below as an example. The object to be classified may be any one object (for example, the target display object or the target reference object described above).

[0220] For example, the process for determining the object category of an object to be classified may determine the object category of the object to be classified according to the object description information of the object to be classified and a pre-constructed object classification model. The object classification model is used to perform classification processing on the object description information of the object to be classified, and in the embodiments of the present application, the embodiment of the object classification model is not limited, and any existing or future model having classification functionality can be adopted and implemented, for example.

[0221] Furthermore, in order to further improve the classification effect, the embodiments of the present invention provide one possible embodiment of the above step "determining the object category of the object to be classified according to the object description information of the object to be classified and a pre-constructed object classification model," which may specifically include the following steps 61-62.

[0222] Step 61: Feature extraction processing is performed on the object description information of the object to be classified to obtain the feature extraction result of the object to be classified, thereby representing the characteristics of the object to be classified.

[0223] The object description information of the object to be classified is used to describe the object to be classified, and in the embodiments of the present application, the "object description information of the object to be classified" is not limited and may include, for example, video data (e.g., live streaming video), audio data (e.g., audio introduction data), text data (e.g., text introduction content, user reviews, etc.) for displaying the object to be classified.

[0224] Furthermore, the embodiments of the present application do not limit the embodiment of step 61, and can be implemented by employing, for example, any existing or future feature extraction method. For example, in one possible embodiment, step 61 may specifically involve first preprocessing the object description information of the object to be classified using several information processing techniques (e.g., techniques such as natural language processing (NLP), computer vision (CV), and automatic speech recognition (ASR)), obtaining the preprocessing results, and then performing a feature extraction process on the preprocessing results using a deep learning algorithm to obtain the feature extraction results of the object to be classified.

[0225] Step 62: The feature extraction results of the object to be classified are input into a pre-built object classification model, and the object category of the object to be classified is obtained from the object classification model, so that the object category can represent the classification result of the object to be classified in at least one classification dimension (for example, three dimensions such as object class, object attributes, and object topics).

[0226] An object classification model is used to perform classification on the input data of the object classification model using at least one classification dimension (for example, three dimensions such as object class, object attribute, and object topic).

[0227] Furthermore, the object classification model may be pre-trained using object description information of at least one referenced object and classification annotation information of that at least one referenced object. The object description information of the referenced object is used to describe the referenced object, and since the object description information of the referenced object is similar to the related content of "object description information of the object to be classified" described above, a detailed explanation is omitted here for brevity. The classification annotation information of the referenced object is used to represent the classification status of the referenced object in at least one classification dimension (for example, three dimensions such as object class, object attribute, and object topic), and in the embodiments of this application, the classification annotation information of the referenced object is not limited and can be implemented, for example, by a manual annotation method.

[0228] Furthermore, in the embodiments of the present invention, the training process of the object classification model is not limited. For example, specifically, the process may involve first performing a feature extraction process on the object description information of each referenced object to obtain the feature extraction results for each referenced object, and then training the object classification model using the feature extraction results of at least one referenced object and the classification annotation information of at least one referenced object. In this way, the trained object classification model can perform classification processing on the input data of the object classification model (e.g., the feature extraction results of a certain object) in at least one classification dimension.

[0229] In addition, the embodiments of the present invention do not limit the embodiment of the above step "training the object classification model using the feature extraction results of at least one reference object and the classification annotation information of at least one reference object," and can be carried out by employing any existing or future method of model training based on training data, for example.

[0230] Furthermore, the embodiment of step 61 described above, "performing feature extraction processing on the object description information of each referenced object and obtaining the feature extraction results for each referenced object," is similar to the embodiment of step 61 described above, so for the sake of brevity, a detailed explanation is omitted here.

[0231] As can be seen from the related content of steps 61 to 62 above, after obtaining the object description information of the object to be classified, first, a feature extraction process is performed on the object description information to obtain the feature extraction result of the object to be classified, and then the feature extraction result is input into a pre-constructed object classification model, and the object classification model can determine the object category of the object to be classified according to the feature extraction result, thereby the object category can represent the classification result of the object to be classified in at least one classification dimension (for example, three dimensions such as object class, object attribute, and object topic).

[0232] The process for determining the "object category of the target display object" is similar to the process for determining the "object category of the object to be classified," and for brevity, a detailed explanation is omitted here. Similarly, the process for determining the "object category of the target reference object" is similar to the process for determining the "object category of the object to be classified."

[0233] In practice, with respect to the set of recommended information placed within the above-mentioned information recommendation page, the present embodiment does not limit the information aggregation display method of the set of recommended information. For example, in order to better improve the user experience, the set of recommended information can be displayed in the form of a ranking list (for example, the ranking list format shown in Figure 3).

[0234] Furthermore, in the embodiments of this application, the acquisition process of the above step "determining these recommended information sets according to the object category of the target reference object" is not limited. For example, it may be specifically used to search for candidate information sets corresponding to the object category of the target reference object from pre-established mapping relationships and determine them as recommended information sets. These mapping relationships are used to record one-to-one correspondences between different object categories and different candidate information sets. The embodiments of the candidate information sets are similar to the embodiments of the recommended information sets described above.

[0235] Furthermore, the above candidate information set can be pre-built, and if the candidate information set is displayed in the form of a ranking list, the candidate information set can be built and updated in real time according to object-related information (similar to interaction operations such as transactions) corresponding to some of the accounts in the candidate information set, thereby improving the real-time nature of the ranking list of these accounts.

[0236] In this embodiment, the process for constructing the candidate information set is not limited, and for ease of understanding, the process for constructing the j-th recommended information set will be explained below as an example. j is a positive integer, j ≤ J, where J represents the number of recommended information sets placed on the information recommendation page.

[0237] For example, if the j-th recommendation information set is implemented in the form of a ranking list, and the object category corresponding to the j-th recommendation information set is the target category, the process for constructing the j-th recommendation information set may specifically include the following steps 71-74.

[0238] Step 71: Based on the object supply information of at least one candidate account, at least one target account is determined from the at least one candidate account, thereby using the object supply information of the target account to indicate that the object category of the target usage object under the target account is the same as the object category corresponding to the j-th recommended information set.

[0239] The "at least one candidate account" mentioned above refers to an account that needs to be used when constructing an information recommendation ranking list (for example, a live streaming account). In the embodiments of this application, the "at least one candidate account" is not limited to, for example, a streaming account for all live streaming videos stored in one or more video application programs.

[0240] Object supply information is used to describe the relevant content of objects supplied by an account. In the embodiments of the present application, the object supply information is not limited, and for example, if the account (e.g., the candidate account or the account used) is used to provide at least one second candidate object, the object supply information for the live streaming video may include the object categories of these second candidate objects. A second candidate object is an object that can perform several operations (e.g., interaction operations such as viewing and trading) within the live streaming room corresponding to the account. A second candidate object is similar to the first candidate object, and for brevity, a detailed explanation is omitted here.

[0241] The "eligible account" mentioned above refers to an account that can provide objects under the object category corresponding to the j-th recommended information set mentioned above.

[0242] The above-mentioned "target usage object" refers to an object under the object category corresponding to the j-th recommended information set provided by the target account. For example, if the object category corresponding to the j-th recommended information set is the target category, then the target usage object is an object under that target category provided by the target account. As can be seen from the above, if the display page of the target account can display M second-choice objects, it is possible to determine whether the object category of the m-th second-choice object displayed on the display page includes the target category. If the target category exists, it can be determined that the object category of the m-th second-choice object is the same as the object category corresponding to the j-th recommended information set, and therefore the m-th second-choice object can be considered the target usage object under the target account. m is a positive integer, m ≤ M, and M is a positive integer.

[0243] As can be seen from the related content of step 71 above, after obtaining the target reference object, if it is determined that there is a target category in the object category corresponding to the target reference object, it can be determined that it is necessary to construct an information recommendation ranking list corresponding to the target category using the target accounts that correspond to other objects under the target category other than the target reference object. Therefore, first, the target category is aggregated into all candidate accounts, and at least one target account is obtained, each target account being able to provide at least one object under the target category, and subsequently, the information recommendation ranking list corresponding to the target category can be constructed using these target accounts.

[0244] Step 72: Determine the recommended representation data for at least one target account based on the object interaction information of that at least one target account.

[0245] Object interaction information is used to describe interaction statuses (e.g., operation status and / or transaction status) triggered on objects under the target account, and in embodiments of the present application, such object interaction information is not limited and may include, for example, real-time object sales. Real-time object sales refers to the real-time sales of all objects under the target account.

[0246] The above-mentioned "Recommended Representation Data for the Target Account" is used to describe the likelihood that the target account will be recommended to the user. The larger the Recommended Representation Data for the target account, the greater the likelihood that the target account will be recommended to the user, and the smaller the Recommended Representation Data for the target account, the less likely the target account will be recommended to the user.

[0247] Furthermore, in the embodiments of the present application, the process for determining the "recommended representation data for the target account" is not limited. For example, if the object interaction information includes real-time object sales volume, the process for determining the "recommended representation data for the target account" may specifically involve determining the recommended representation data for the target account according to the real-time object sales volume of the target account, and making the recommended representation data for the target account proportional to the real-time object sales volume of the target account.

[0248] As can be seen from the relevant content of step 72 above, after obtaining at least one target account under the target category above, the recommendation representation data for each target account is determined according to the object interaction information of each target account (e.g., the total sales volume of all objects), so that the recommendation representation data for each target account can represent the likelihood that each target account is recommended to the user.

[0249] Step 73: Based on the recommended representation data of at least one target account, determine at least one display target account from that at least one target account that satisfies the preset recommendation criteria. The display target account is a target account that satisfies the preset recommendation criteria.

[0250] Preset recommendation conditions can be set in advance; for example, specifically, they may recommend the T target accounts with the largest number of representation data, where T is a positive integer.

[0251] As can be seen from the relevant content of step 73 above, for at least one target account under the target category, after obtaining the recommended expression data for each target account, these target accounts can be sorted according to their recommended expression data to obtain a sort result, which can represent the arrangement state when these target accounts are arranged in descending order of the recommended expression data, and furthermore, the T target accounts sorted to the top of the sort result can be considered as display target accounts (i.e., accounts whose information needs to be displayed in the ranking list), and a ranking list can be constructed subsequently based on these display target accounts.

[0252] Step 74: Construct a j-th set of recommendation information based on the relevant information of at least one target account (e.g., account attribute information and / or object display information of the target display object under the target account) and the recommendation representation data of the at least one target account, so that the j-th set of recommendation information can display the relevant information of these target accounts in the form of a ranking list.

[0253] In the embodiments of the present invention, after obtaining at least one target account and recommendation expression data for said at least one target account, the relevant information for said target accounts can be arranged in descending order of the recommendation expression data according to the recommendation expression data of said target accounts to obtain an arrangement result, and further, according to the arrangement result, a set of recommendation information corresponding to a target category (i.e., the j-th set of recommendation information) can be constructed, thereby allowing the set of recommendation information to recommend these target accounts to the user according to the arrangement result.

[0254] As can be seen from the related content of steps 71 to 74 above, after obtaining the target reference object, if it is determined that there is a target category in the object category corresponding to the target reference object, first, the target category is used to select at least one target account under that target category from a large number of candidate accounts, and then these target accounts are sorted according to the object interaction information of these target accounts to obtain a set of recommendation information corresponding to the target category, thereby the set of recommendation information can represent the object recommendation information under that target category.

[0255] The process for constructing the "candidate information set" described above is similar to the construction process shown in steps 71-74, and for brevity, a detailed explanation is omitted here.

[0256] As can be seen from the related contents of S501 to S502 above, in the display method according to the embodiment of the present invention, when a client is viewing a video playback page, the client receives a trigger operation (e.g., a click operation) on a target control within the video playback page and then displays an information recommendation page. The information recommendation page includes multiple recommendation information sets, each corresponding to a different object category, each recommendation information set includes account attribute information for multiple candidate accounts, and each display target object under each candidate account in the same recommendation information set includes a target display object, and the object category of the target display object is the same as the object category corresponding to the recommendation information set.

[0257] As can be seen from the above, the information recommendation page contains multiple sets of recommended information, and each set of recommended information corresponds to a different object category. Therefore, the information recommendation page can provide users with sets of recommended information under several object categories, allowing users to view sets of recommended information under different object categories from the information recommendation page. In this way, the user's information viewing needs can be better met, which is advantageous for improving the user experience.

[0258] In practice, to further improve the user experience, the embodiments of the present invention provide one possible embodiment of the target control described above, in which prompt information (for example, the information "Ranked 9th in retro women's clothing" as shown in Figure 2) is displayed on the target control, and the prompt information can prompt the viewer of the video playback page to view the ranking list corresponding to their object of interest.

[0259] Furthermore, in order to further improve the user experience, the prompt information displayed on the target control changes in response to changes in the user's object of interest. Based on this, embodiments of the present application further provide another possible embodiment of the display method, in which, if the display method includes at least S501, the display method further includes the following S503. The execution time of S503 is slower than the execution time of S501, and in embodiments of the present application, the execution time of S503 is not limited.

[0260] S503: After updating the target reference object, update the ranking list position description information for the account corresponding to the video playback page, and update the prompt information on the target control using the ranking list position description information. The ranking list position description information is used to describe the sort position in the recommendation information set corresponding to the target reference object for the account attribute information of the account corresponding to the video playback page.

[0261] Furthermore, in the embodiment of this application, the ranking list position description information is not limited to the above, and may be, for example, information such as "Ranked 9th in retro women's clothing" as shown in Figure 2.

[0262] Furthermore, in the embodiments of the present application, the process for determining the ranking list position description information is not limited. For example, if the target reference object has only one category in its object category, the target reference object can correspond to only one set of recommendation information. Therefore, the sort position of the account attribute information of the account corresponding to the video playback page in the "set of recommendation information corresponding to the target reference object" can be directly determined as the ranking list position description information. Alternatively, if the target reference object has multiple categories in its object category, the target reference object can correspond to multiple sets of recommendation information. Therefore, according to pre-set rules (for example, different object categories correspond to different priorities), the ranking list position description information can be determined from the sort positions of the account attribute information of the account corresponding to the video playback page in these sets of recommendation information. The ranking list position description information can then describe the sort position of the account corresponding to the video playback page in a particular set of recommendation information.

[0263] In the embodiments of this invention, the timing of updating the target reference object is not limited; for example, it may be updated once at regular intervals. Alternatively, for example, after triggering an operation once on an object within the video playback page, the update process for the target reference object may be executed immediately.

[0264] As can be seen from the related content of S503 above, for a client used by a viewer of a video data, when the client is displaying the video playback page, after the update process of the target reference object is completed, the recommended information set corresponding to the target reference object is first updated by the object category of the target reference object, and then the display content of the target control can be updated based on the sort position of the account corresponding to the video playback page in the recommended information set. In this way, the real-time nature of the display content of the target control can be ensured, which is advantageous for improving the user experience.

[0265] Based on the display method according to the embodiment of the present application, the embodiment of the present application further provides a display device, which will be interpreted and described below with reference to Figure 6. Figure 6 is a schematic diagram of the configuration of the display device according to the embodiment of the present application. For technical details of the display device according to the embodiment of the present application, please refer to the relevant content of the display method described above.

[0266] As shown in Figure 6, the display device 600 according to the embodiment of the present application is A third display unit 601 used to display a video playback page including target controls, It includes a fourth display unit 602 used to display an information recommendation page in response to a trigger operation on the target control, The aforementioned information recommendation page includes multiple recommendation information sets, each corresponding to a different object category, each recommendation information set includes account attribute information for multiple candidate accounts, each displayed object under each candidate account in the same recommendation information set includes a target display object, and the object category of the target display object is the same as the object category corresponding to the recommendation information set.

[0267] In one possible embodiment, the display device 600 is If the information recommendation page displays account attribute information for a target account among the multiple candidate accounts, the system further includes a fifth display unit used to display an information display page corresponding to the target account in response to a trigger operation on the account attribute information of the target account.

[0268] In one possible embodiment, each recommendation information set further includes object display information for target display objects under multiple candidate accounts.

[0269] In one possible embodiment, the object display information includes at least one of text description information and picture description information.

[0270] In one possible embodiment, the display device 600 is If the information recommendation page displays object display information for a target display object under a target account among the multiple candidate accounts, the system further includes a sixth display unit used to display an information display page corresponding to the target account in response to a trigger operation on the object display information, and to display an information display interface corresponding to the target display object under the target account on the information display page corresponding to the target account.

[0271] In one possible embodiment, the information recommendation page further includes a plurality of category tags, each of which has a one-to-one correspondence with a plurality of recommended information sets, and the recommended information set currently displayed on the information recommendation page is the recommended information set corresponding to the first tag among the plurality of category tags. The display device 600 is The system further includes a seventh display unit used to switch the set of recommended information displayed on the information recommendation page from the set of recommended information corresponding to the first tag to the set of recommended information corresponding to the second tag in response to a trigger operation on the second of the multiple category tags.

[0272] In one possible embodiment, at least one first candidate object corresponding to the video playback page has a target reference object that meets preset conditions, and the object category corresponding to the recommended information set is the same as the object category of the target reference object.

[0273] In one possible embodiment, the preset condition is that the video explanation state of the target reference object within the video playback page meets the preset state condition, or or the preset condition is that the historical operation information of the target reference object meets the preset operation condition.

[0274] In one possible embodiment, the object category of the target display object is determined according to the object description information of the target display object and a pre-constructed object classification model, and the object classification model is used to perform classification processing on the object description information of the target display object.

[0275] In one possible embodiment, the object classification model is trained using the object description information of at least one reference target object and the classification annotation information of the at least one reference target object.

[0276] In one possible embodiment, the video playback page is used to display a first live video, and / or the information display page corresponding to the candidate account is used to display a second live video.

[0277] In one possible embodiment, the account attribute information includes at least one of an identification icon corresponding to the candidate account and identification text corresponding to the candidate account.

[0278] As can be seen from the above description of the display device 600, in the case of the display device 600 according to the embodiment of the present application, when the display device 600 is displaying a video playback page, the display device 600 can display at least one first candidate product to the viewer, and after the display device 600 receives a trigger operation (e.g., a click operation) on a target control within the video playback page, it displays an information recommendation page. The information recommendation page is used to display at least one target live streaming video, and the at least one target live streaming video is determined according to the classification description information of the first target product among these first candidate products. The classification description information is used to describe the category attribution status of the first target product.

[0279] As can be seen from the above, since the history operation information of the first target product satisfies the first preset condition, it can be determined that the viewer is relatively interested in the first target product, and thus it can be estimated that the viewer is likely to be interested in other products related to the first target product (e.g., other products under the same product class, other products under the same product topics, other products under the same product attributes, etc.). Furthermore, at least one live streaming video to be displayed, determined based on the classification description information of the first target product, can provide the viewer with several other products related to the first target product. In this way, the products displayed in these live streaming videos can satisfy the viewer's product browsing needs as much as possible, which is advantageous in improving the viewer's browsing experience for other products related to the first target product, and thus advantageous in improving the user experience.

[0280] Furthermore, embodiments of the present application provide an electronic device comprising a processor and memory, wherein the memory is used to store instructions or computer programs, and the processor is used to cause the electronic device to execute any one embodiment of the display method according to embodiments of the present application by executing the instructions or computer programs in the memory.

[0281] As shown in Figure 7, a schematic diagram of the configuration of an electronic device 700 for realizing an embodiment of the present disclosure is provided. The terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. The electronic device shown in Figure 7 is merely an example and does not imply any limitation on the functions and scope of use of the embodiments of the present disclosure.

[0282] As shown in Figure 7, the electronic device 700 may include a processing unit (e.g., a central processing unit, graphics processor, etc.) 701, which can perform various appropriate operations and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage device 708 into a random access memory (RAM) 703. The RAM 703 further stores various programs and data necessary for the operation of the electronic device 700. The processing unit 701, ROM 702, and RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0283] Typically, devices that can be connected to the I / O interface 705 include input devices 706 such as touch panels, touchpads, keyboards, mice, cameras, microphones, accelerometers, and gyroscopes; output devices 707 such as liquid crystal displays (LCDs), speakers, and vibrators; storage devices 708 such as tapes and hard disks; and communication devices 709. The communication device 709 enables the electronic device 700 to communicate wirelessly or via wired connection with other devices to exchange data. Figure 7 shows an electronic device 700 with various devices, but it should be understood that it is not necessary to implement or include all of the devices shown. Instead, more or fewer devices may be implemented or included.

[0284] In particular, according to embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product which includes a computer program mounted on a non-temporary computer-readable medium, the computer program which includes program code for performing the method shown in the flowchart. In such embodiments, the computer program may be downloaded and installed from a network via a communication device 709, installed from a storage device 708, or installed from a ROM 702. When the computer program is executed by the processing unit 701, the above-described functions, limited to the methods of embodiments of the present disclosure, are performed.

[0285] The electronic devices according to the embodiments of this disclosure belong to the same inventive idea as the methods according to the above embodiments, and technical details not described in detail in these embodiments can be found in the above embodiments, and these embodiments have the same beneficial effects as the above embodiments.

[0286] Embodiments of the present application further provide a computer-readable medium on which instructions or computer programs are stored, and when the instructions or computer programs are assigned to a device, the device is made to execute one embodiment of the display method according to embodiments of the present application.

[0287] The computer-readable medium in this disclosure may be a computer-readable signal medium, a computer-readable storage medium, or any combination thereof. The computer-readable storage medium may be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage mediums may include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program, the program may be used by or in combination with an instruction execution system, apparatus, or device. In this disclosure, the computer-readable signal medium may include data signals propagated in the baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, and such computer-readable signal medium can transmit, propagate, or transmit programs for use by or in combination with instruction execution systems, apparatus, or devices. Program code contained in the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), or any suitable combination thereof.

[0288] In some embodiments, the client and server may communicate by any currently known or future-developed network protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with digital data communications (e.g., communication networks) in any form or medium. Examples of communication networks include local area networks ("LANs"), wide area networks ("WANs"), internetworks (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), and any currently known or future-developed networks.

[0289] The computer-readable medium described above may be included in the electronic device described above, or it may exist independently without being assembled into the electronic device.

[0290] The computer-readable medium described above contains one or more programs, and when the one or more programs are executed by the electronic device, the electronic device is made to execute the method described above.

[0291] Computer program code for performing the operations disclosed herein can be programmed in one or more programming languages, or a combination thereof, including, but not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as traditional procedural programming languages ​​such as "C" and similar programming languages. The program code may run entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. If a remote computer is involved, 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 it may be connected to an external computer (for example, connected via the Internet using an Internet service provider).

[0292] The flowcharts and block diagrams in the drawings illustrate the system architecture, functions, and operations achievable by the systems, methods, and computer program products of various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram can represent a module, program segment, or part of code that includes one or more executable instructions for implementing a given logic function. Note that in some alternative implementations, the functions indicated in the blocks may be performed in an order different from the order shown in the drawings. For example, two consecutively shown blocks may actually be executed substantially in parallel, and in some cases, may be executed in the reverse order depending on the related functions. Note that each block in the block diagram and / or flowchart, as well as combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing a given function or operation, or may be implemented by a combination of dedicated hardware and computer instructions.

[0293] The units described in the embodiments of the present disclosure may be implemented in the form of software or in the form of hardware. In some cases, the name of the unit / module does not limit the unit itself.

[0294] The functions described above in this specification may be at least partially executed by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that can be used include field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0295] In the context of this disclosure, a machine-readable medium may be a tangible medium containing or storing a program that can be used by, or in combination with, an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may be, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination thereof. More specific examples of machine-readable storage media may include one or more wire-based electrical connections, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0296] Each embodiment in this specification is described progressively, and the focus of each embodiment is on the differences from other embodiments. Similar or identical parts between embodiments should be referenced to one another. The systems or apparatus disclosed in the embodiments are relatively simple to describe as they correspond to the methods disclosed in the embodiments; relevant parts should be referred to the description in the method section.

[0297] In this application, it should be understood that "at least one" means one or more, and "multiple" means two or more. "And / or" is used to describe the relationship between related objects and indicates that there can be three types of relationships. For example, "A and / or B" represents the three cases of A only, B only, and the presence of both A and B, where A and B may be singular or plural. The letter " / " generally indicates that the preceding and succeeding related objects are in an "or" relationship. "At least one of the following" or similar expressions means any combination of these items, including any combination of one or more items. For example, at least one of a, b, or c could mean a, b, c, "a and b", "a and c", "b and c", or "a, b and c", where a, b, and c may be singular or plural.

[0298] Furthermore, in this specification, relational terms such as "first," "second," etc., are merely for distinguishing one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. The terms "include," "incorporate," or any other variation are intended to cover non-exclusive inclusion, thereby including not only those elements but also other elements not expressly enumerated, or elements specific to this process, method, article, or equipment. Unless otherwise specified, an element limited in the phrase "includes one..." does not preclude the presence of another identical element in a process, method, article, or equipment that includes the aforementioned element.

[0299] Steps of methods or algorithms described with reference to the embodiments disclosed herein may be carried out directly in hardware, in a software module executed by a processor, or in a combination of both. The software module may be stored in random access memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the art.

[0300] The above description of the disclosed embodiments will enable those skilled in the art to implement or use the present invention. Various modifications of these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Accordingly, the present invention is not limited to these embodiments shown herein, but conforms to the broadest scope consistent with the principles and novelty features disclosed herein.

Claims

1. A display method performed by an electronic device, Steps to display the video playback page, The step of displaying an information recommendation page in response to a trigger operation on a target control within the video playback page, wherein the information recommendation page displays a set of recommended information corresponding to a referenced object, the referenced object is determined according to the attention state representation information of at least one first candidate object corresponding to the video playback page, the attention state representation information includes history operation information and video commentary information, the recommended information set includes account attribute information of multiple candidate accounts, each of the display target objects under each candidate account includes a target display object, the object category of the target display object is the same as the object category corresponding to the recommended information set, and the object category corresponding to the recommended information set is the same as the object category of the referenced object, A display method in which, if the history operation activity information of a first target object among the at least one first candidate object satisfies a first preset condition, the referenced object is determined according to the first target object, the history operation activity information includes the number of clicks, the first preset condition includes the number of clicks of the first target object being greater than a preset count threshold, and if the history operation activity information of each of the first candidate objects does not satisfy the first preset condition, the referenced object is determined according to the video explanation information of the at least one first candidate object.

2. If none of the history operation information for each of the first candidate objects satisfies the first preset condition, and the video explanation information for the second target object among the at least one first candidate object satisfies the second preset condition, the reference object is determined according to the second target object. The method according to claim 1, wherein if there is one second target object, the second target object is determined to be the reference object, and if there are multiple second target objects, the second target object with the latest explanation start time among the multiple second target objects is determined to be the reference object.

3. The second preset condition includes, as video explanation information for the second target object, that the second target object is in an explanation state within the video playback page, Or, The method according to claim 2, wherein the second preset condition includes, as video explanation information for the second target object, that the second target object is in an explanation completion state within the video playback page, and the explanation completion time for the second target object is later than the explanation completion times for other objects that are in an explanation completion state within the video playback page.

4. After the step of displaying the video playback page, The method according to claim 1, further comprising the step of updating the history operation information of the third target object in response to a trigger operation on the third target object among at least one first candidate object corresponding to the video playback page.

5. The method according to claim 1, wherein the recommended information set further includes object display information for target display objects under each of the candidate accounts.

6. The object to be classified is the referenced object or the target display object, The object category of the object to be classified is determined according to the object description information of the object to be classified and a pre-constructed object classification model, and the object classification model is used to perform classification processing on the object description information of the object to be classified. Determining the object category of the object to be classified according to the object description information of the object to be classified and the pre-constructed object classification model is: The process involves performing a feature extraction process based on the object description information of the object to be classified, and obtaining the feature extraction results for the object to be classified. The method according to claim 1, further comprising performing a classification process on the feature extraction results of the object to be classified based on the object classification model, to obtain the object category of the object to be classified.

7. The method according to claim 1, wherein the video playback page is used to display a first live streaming video, and / or the information display page corresponding to the candidate account is used to display a second live streaming video.

8. A display device, A first display unit used to display a video playback page, A second display unit used to display an information recommendation page in response to a trigger operation on a target control within the video playback page, wherein the information recommendation page displays a set of recommended information corresponding to a reference target object, the reference target object is determined according to the attention state representation information of at least one first candidate object corresponding to the video playback page, the attention state representation information includes history operation information and video commentary information, the recommended information set includes account attribute information of multiple candidate accounts, each of the display target objects under each candidate account includes a target display object, the object category of the target display object is the same as the object category corresponding to the recommended information set, and the object category corresponding to the recommended information set is the same as the object category of the reference target object, the second display unit includes A display device in which, when the history operation activity information of a first target object among the at least one first candidate object satisfies a first preset condition, the referenced object is determined according to the first target object, the history operation activity information includes the number of clicks, the first preset condition includes the number of clicks of the first target object being greater than a preset count threshold, and when the history operation activity information of any of the first candidate objects does not satisfy the first preset condition, the referenced object is determined according to the video explanation information of the at least one first candidate object.

9. A display method performed by an electronic device, The steps include: displaying a video playback page that includes target controls, The step of displaying an information recommendation page in response to a trigger operation on the target control is included, The aforementioned information recommendation page includes multiple recommendation information sets, each corresponding to a different object category, each recommendation information set includes account attribute information for multiple candidate accounts, each displayed object under each candidate account in the same recommendation information set includes a target display object, and the object category of the target display object is the same as the object category corresponding to the recommendation information set. The aforementioned method, The step further includes determining a target reference object that satisfies a preset condition from at least one first candidate object corresponding to the video playback page, wherein the preset condition is that the video commentary state of the target reference object within the video playback page satisfies a preset state condition, or that the history operation information of the target reference object satisfies a preset operation condition, wherein the preset operation condition includes that the number of clicks on the target reference object reaches a preset threshold. A display method in which the object category corresponding to the aforementioned recommended information set is the same as the object category of the target reference object.

10. The aforementioned information recommendation page displays the account attribute information of the target account among the multiple candidate accounts. The method according to claim 9, further comprising the step of displaying an information display page corresponding to the target account in response to a trigger operation on the account attribute information of the target account.

11. The method according to claim 9, wherein each of the recommended information sets further comprises object display information of target display objects under the plurality of candidate accounts.

12. The method according to claim 11, wherein the object display information includes at least one of text description information and picture description information.

13. If the aforementioned information recommendation page displays object display information for the target display object under the target account among the multiple candidate accounts, The method according to claim 11, further comprising the steps of displaying an information display page corresponding to the target account in response to a trigger operation on the object display information, and displaying an information display interface corresponding to a target display object under the target account on the information display page corresponding to the target account.

14. The aforementioned information recommendation page further includes multiple category tags, each of which has a one-to-one correspondence with multiple recommended information sets, and the recommended information set currently displayed on the information recommendation page is the recommended information set corresponding to the first tag among the multiple category tags. The method according to claim 9, further comprising the step of switching the set of recommended information displayed in the information recommendation page from the set of recommended information corresponding to the first tag to the set of recommended information corresponding to the second tag in response to a trigger operation on the second tag among the plurality of category tags.

15. The object category of the target display object is determined according to the object description information of the target display object and a pre-constructed object classification model, the object classification model is used to perform classification processing on the object description information of the target display object, and the object classification model is trained using the object description information of at least one reference object and the classification annotation information of at least one reference object. Determining the object category of the target display object according to the object description information of the target display object and the pre-constructed object classification model is: The process involves performing a feature extraction process based on the object description information of the target display object, and obtaining the feature extraction result of the target display object. The method according to claim 9, further comprising performing a classification process on the feature extraction results of the target display object based on the object classification model to obtain the object category of the target display object.

16. The method according to claim 9, wherein the video playback page is used to display a first live streaming video, and / or the information display page corresponding to the candidate account is used to display a second live streaming video.

17. The method according to claim 9, wherein the account attribute information includes at least one of an identification icon corresponding to the candidate account and an identification text corresponding to the candidate account.

18. A display device, A first display unit used to display a video playback page including target controls, A second display unit used to display an information recommendation page in response to a trigger operation on the target control, wherein the information recommendation page includes multiple recommendation information sets, each corresponding to a different object category, each recommendation information set includes account attribute information of multiple candidate accounts, each display target object under each candidate account in the same recommendation information set includes a target display object, and the object category of the target display object is the same as the object category corresponding to the recommendation information set; The second display unit is used to determine a target reference object that satisfies preset conditions from at least one first candidate object corresponding to the video playback page, wherein the preset conditions are that the video commentary state of the target reference object within the video playback page satisfies a preset state condition, or that the history operation information of the target reference object satisfies a preset operation condition, the preset operation condition includes that the number of clicks on the target reference object reaches a preset threshold, and the object category corresponding to the recommended information set is the same as the object category of the target reference object.

19. An electronic device, including a processor and memory, The memory is used to store instructions or computer programs. The processor is an electronic device used to cause the electronic device to execute the method according to any one of claims 1-7 or the method according to any one of claims 9-17 by executing the instructions or computer program in the memory.

20. A computer-readable medium having instructions or computer programs stored in it, wherein when the instructions or computer programs are executed by a device, the device causes the device to execute the method according to any one of claims 1-7 or the method according to any one of claims 9-17.

21. A computer program to be mounted on a non-temporary computer-readable medium, the computer program comprising program code for performing the method according to any one of claims 1 to 7 or the method according to any one of claims 9 to 17.

Images