Method and device for determining playing content

Abstract

The invention provides a method and a device for determining playing content, and relates to the field of data processing, in particular to the field of artificial intelligence. According to the specific implementation scheme, in response to a monitored first page switching request of a user, a to-be-played video set is screened out from candidate videos, and the to-be-played video set comprises multiple to-be-played videos; obtaining candidate topic cards and delivery configuration parameters of each candidate topic card; obtaining user interaction portraits of the user for the candidate topic cards, and screening out a target topic card from the candidate topic cards based on the user interaction portraits and the delivery configuration parameters; and determining a to-be-played target content set based on the target topic card and the to-be-played video set.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing, particularly to the field of artificial intelligence, and specifically to a method and apparatus for determining playback content. Background Art

[0002] With the wide application of video recommendation systems, the personalized needs of users are increasing day by day, and the effectiveness of the recommendation system is crucial for user experience and platform activity. Most traditional video recommendation systems perform personalized recommendations through data such as historical viewing records and user interest tags. However, with the diversification of content types and themes, a single recommendation strategy can no longer meet the needs of all users. Against this background, the concept of exploration cards emerged to explore users' interests in different resource themes, such as music, novels, hot topics, short dramas, etc., to help the system better understand users' potential interest preferences. However, how to reasonably manage and allocate these exploration cards of different content types has become an important challenge for optimizing the recommendation system. Summary of the Invention

[0003] The present disclosure provides a method, apparatus, device, and storage medium for determining playback content.

[0004] According to one aspect of the present disclosure, a method for determining playback content is provided, including: in response to detecting a first page switching request of a user, screening out a set of videos to be played from candidate videos, where the set of videos to be played includes multiple videos to be played; obtaining candidate topic cards and the placement configuration parameters of each candidate topic card; obtaining the user interaction portrait of the user for the candidate topic cards, and screening out target topic cards from the candidate topic cards based on the user interaction portrait and the placement configuration parameters; determining a set of target content to be played based on the target topic cards and the set of videos to be played.

[0005] For the method for determining playback content proposed in this application, placement configuration parameters are configured for each candidate topic card, and the placement configuration parameters are easy to modify, which can greatly improve the management efficiency of each candidate topic card and can efficiently configure the automated online launch of a certain candidate topic card; after obtaining the set of videos to be played that the user is interested in, if a target topic card that the user is interested in can be matched, then a set of target content to be played is determined based on the target topic cards and the set of videos to be played, and recommended for playback to the user, which can enhance the user experience, help the user explore other themes besides videos, and improve user satisfaction; this application can recommend different sets of target content according to changes in user preferences, and recommend different sets of target content for different users, improving the personalization degree of content recommendation and increasing user stickiness.

[0006] According to another aspect of the present disclosure, there is provided a device for determining content to be played, including: a video screening module configured to screen out a set of videos to be played from candidate videos in response to detecting a first page switching request of a user, wherein the set of videos to be played includes a plurality of videos to be played; a parameter obtaining module configured to obtain candidate topic cards and the placement configuration parameters of each candidate topic card; a card screening module configured to obtain a user interaction portrait of the user with respect to the candidate topic cards, and screen out a target topic card from the candidate topic cards based on the user interaction portrait and the placement configuration parameters; and a content determining module configured to determine a set of target content to be played based on the target topic card and the set of videos to be played.

[0007] According to another aspect of the present disclosure, there is provided an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the above-mentioned method for determining content to be played.

[0008] According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the above-mentioned method for determining content to be played.

[0009] According to another aspect of the present disclosure, there is provided a computer program product, including a computer program which, when executed by a processor, implements the above-mentioned method for determining content to be played.

[0010] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. Description of the Drawings

[0011] The drawings are used to better understand the solution and do not constitute a limitation to the present disclosure. Among them:

[0012] Figure 1 is a schematic diagram of an exemplary implementation manner of the method for determining content to be played according to an exemplary embodiment of the present disclosure.

[0013] Figure 2 is a schematic diagram of a set of target content according to an exemplary embodiment of the present disclosure.

[0014] Figure 3 is a schematic diagram of a target topic card according to an exemplary embodiment of the present disclosure.

[0015] Figure 4Schematic diagram of an exemplary embodiment of a method for determining playback content according to an exemplary embodiment of the present disclosure.

[0016] Figure 5 Schematic diagram of an exemplary embodiment of a method for determining playback content according to an exemplary embodiment of the present disclosure.

[0017] Figure 6 Schematic diagram of an exemplary embodiment of a method for determining playback content according to an exemplary embodiment of the present disclosure.

[0018] Figure 7 Schematic diagram of a device for determining playback content according to an exemplary embodiment of the present disclosure.

[0019] Figure 8 Schematic diagram of an electronic device according to an exemplary embodiment of the present disclosure. Detailed implementation manners

[0020] The following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, descriptions of well-known functions and structures are omitted below for clarity and conciseness.

[0021] Artificial Intelligence (AI) is a discipline that studies how to make a computer simulate certain thinking processes and intelligent behaviors of humans (such as learning, reasoning, thinking, planning, etc.). It includes both hardware-level technologies and software-level technologies. Artificial intelligence hardware technologies generally include several aspects such as computer vision technology, speech recognition technology, natural language processing technology, machine learning / deep learning, big data processing technology, and knowledge graph technology.

[0022] In the technical solution of the present disclosure, the acquisition, storage, and application of user personal information involved all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0023] Figure 1 Schematic diagram of an exemplary embodiment of a method for determining playback content shown in the present application. As Figure 1 shown, the method for determining playback content includes the following steps:

[0024] S101. In response to detecting a first page switching request of a user, filter out a set of videos to be played from candidate videos, where the set of videos to be played includes multiple videos to be played.

[0025] In the present application, the first page switching request refers to an operation triggered during the user's video browsing process to determine the target content set to be played. For example, if the user is monitored to swipe up the playback page during the playback of the last content in the current content set (containing multiple contents), it is considered that the user has triggered the first page switching request.

[0026] In some embodiments, the user's video browsing preference is obtained, and after the user triggers the first page switching request, a video collection to be played that the user is interested in is screened from the candidate videos in the video library based on the user's video browsing preference combined with the video recommendation algorithm. For example, there are 10,000 candidate videos in total, and N videos to be played can be screened from the candidate videos based on the user's video browsing preference combined with the video recommendation algorithm and sorted in order to obtain a video collection to be played consisting of the N videos to be played.

[0027] Wherein, N is a positive integer greater than 1 and can be set according to actual conditions.

[0028] Taking the value of N as 4 as an example, the set of videos to be played selected from the candidate videos can be recorded as: {video 1 to be played, video 2 to be played, video 3 to be played, video 4 to be played}.

[0029] S102, obtaining candidate topic cards and delivery configuration parameters of each candidate topic card.

[0030] Among them, candidate topic cards refer to cards corresponding to other topics that users may be interested in, in addition to videos. For example, candidate topic cards may include music cards, audiobook cards, short play cards, news list cards, and other cards of various types.

[0031] Among them, for each candidate topic card, the delivery configuration parameters refer to the parameters used to match with users in the process of recommending cards to users. For example, the delivery configuration parameters can be used to limit the type of people a candidate topic card is suitable for, the recommendation priority of the candidate topic card, the exposure frequency of a candidate topic card, the position in which it is suitable for recommendation, and other parameters.

[0032] Different candidate topic cards may be configured with different delivery configuration parameters, and the delivery configuration parameters may be set according to the type of the candidate topic card.

[0033] S103, obtaining a user interaction portrait of the user for the candidate topic cards, and filtering out a target topic card from the candidate topic cards based on the user interaction portrait and the delivery configuration parameters.

[0034] Among them, the user interaction portrait of the candidate topic card can also be understood as a summary of the historical interaction data of the user with each candidate topic card. For example, the user interaction portrait can be represented by the following data, namely: topic card name, topic card type, topic card identifier, topic card first click time, topic card last click time, topic card first display time, topic card last display time, topic card total historical display times, topic card total historical positive click times, topic card total historical negative click times, topic card total historical stay duration, topic card historical display list, etc.; among them, the topic card historical display list is used to record the interaction data of the user with each historical display content included in the topic card. For example, the topic card historical display list may include parameters such as the content identifier of a single display content in the list, the content display timestamp, the content positive click times, the content negative click times, and the content page stay duration.

[0035] In this application, in response to detecting a user's first page switching request, candidate topic cards that the user may be interested in are selected from the candidate topic cards based on the user interaction portrait and the placement configuration parameters as the target topic cards.

[0036] S104, determine a target content set to be played based on the target topic cards and the set of videos to be played.

[0037] In some implementable ways, the determined target topic cards can be inserted into the set of videos to be played to obtain the final target content set. For example, if the determined target topic card is an audiobook card and its corresponding insertion position in the set of videos to be played is the 3rd position, and if the set of videos to be played is: {video to be played 1, video to be played 2, video to be played 3, video to be played 4}, then the target content set obtained after inserting the audiobook card into the set of videos to be played is: {video to be played 1, video to be played 2, audiobook card, video to be played 3, video to be played 4}.

[0038] An embodiment of the present application proposes a method for determining playback content, including: in response to detecting a first page switching request of a user, screening a set of videos to be played from candidate videos, where the set of videos to be played contains multiple videos to be played; obtaining candidate topic cards and the placement configuration parameters of each candidate topic card; obtaining the user interaction portrait of the user for the candidate topic cards, and screening out target topic cards from the candidate topic cards based on the user interaction portrait and the placement configuration parameters; determining a set of target content to be played based on the target topic cards and the set of videos to be played. In the present application, placement configuration parameters are configured for each candidate topic card, and the placement configuration parameters are easy to modify, which can greatly improve the management efficiency of each candidate topic card and can efficiently configure the automated online launch of a certain candidate topic card; after the present application obtains the set of videos to be played that the user is interested in, if a target topic card that the user is interested in can be matched, then a set of target content to be played is determined based on the target topic cards and the set of videos to be played and recommended for playback to the user, which can enhance the user experience, help the user explore other themes besides videos, and improve user satisfaction; the present application can recommend different sets of target content according to changes in user preferences, and recommend different sets of target content for different users, improving the personalization degree of content recommendation and increasing user stickiness.

[0039] Among them, if no target topic card is obtained after screening from the candidate topic cards, the set of videos to be played is directly used as the set of target content to be played, which means that no topic card needs to be inserted into the set of target content determined this time.

[0040] Among them, in the present application, a unified data collection service can be set for each candidate topic card. After the candidate topic card is accessed, the interaction data of each user for each candidate topic card is obtained and recorded in the database. Among them, the interaction data of the user for each candidate topic card may at least include the following data:

[0041] 1. Display data, including: user ID, display timestamp, card type, card content ID.

[0042] 2. Stay data, including: user ID, stay start timestamp, card type, card content ID, stay duration.

[0043] 3. Click data, including: user ID, click timestamp, card type, card content ID.

[0044] 4. Dislike data, including: user ID, Dislike timestamp, card type, card content ID, Dislike type (dislike, no longer recommend, etc.).

[0045] 5. Interactive data, including: user ID, interaction timestamp, card type, card content ID, interaction type (such as swap, view more, etc.).

[0046] For a specific user, based on the user ID corresponding to the user, obtain the user's historical interaction data for each candidate topic card from the database, and integrate and analyze the obtained historical interaction data to construct a user interaction portrait. By constructing the user interaction portrait, the user's needs and behavior patterns can be understood more deeply. The user interaction portrait can be applied to the subsequent process of screening target topic cards that the user is more interested in from the candidate topic cards.

[0047] Further, after determining the set of target content to be played, the first content in the set of target content can be directly displayed on the display interface without the user performing an operation for playing, so as to reduce the lag feeling of the user during video browsing.

[0048] Further, after the first content in the set of target content is displayed on the display interface, if a second page switching request of the user is detected, update the display content of the display interface based on the set of target content.

[0049] Among them, the second page switching request refers to a request for switching the content within the already determined set of target content, and the second page switching request does not involve the relevant algorithm operations for determining the set of target content.

[0050] For further introduction Figure 2 is a schematic diagram of a set of target content shown in this application. As Figure 2 shown, after detecting the user's first page switching request 1, determine the set of target content 1. The set of target content 1 is: {video to be played 1, video to be played 2, audiobook card, video to be played 3, video to be played 4}. After determining the set of target content 1, directly play the video to be played 1 on the display interface.

[0051] As Figure 2 shown, the second page switching request refers to a request for switching the content within the already determined set of target content. For example, during the process of playing the video to be played 1 on the display interface, if the user's second page switching request is detected, and if the second page switching request is used to request playing the next content (for example, the user's finger slides up on the display interface), then switch from playing the video to be played 1 on the display interface to playing the video to be played 2, and so on.

[0052] If, during the playback of the to-be-played video 2 on the display interface, a second page switching request of the user is detected, and if the second page switching request is used to request the playback of the next content (for example, the user's finger slides up on the display interface), then the display on the display interface switches from playing the to-be-played video 2 to showing an audiobook card; if, during the playback of the to-be-played video 2 on the display interface, a second page switching request of the user is detected, and if the second page switching request is used to request the playback of the previous content (for example, the user's finger slides down on the display interface), then the display on the display interface switches from playing the to-be-played video 2 to playing the to-be-played video 1, and so on.

[0053] As Figure 2 shown, since the last content in the currently determined target content set 1 is the to-be-played video 4, if the user requests to play the next video during the playback of the to-be-played video 4 on the display interface, then this request is taken as the first page switching request 2, and the target content set 2 is determined based on the first page switching request 2 according to the above idea.

[0054] Among them, both the first page switching request and the second page switching request can be the upward sliding operation of the user's finger on the display interface (used to request the playback of the next content). In this application, it is only divided into two types of requests based on whether the request involves the need to determine a new target content set.

[0055] Among them, Figure 3 is a schematic diagram of a target topic card shown in this application. As Figure 3 shown, the target topic card is used to display the card content that the user may be interested in. The user can click on the card content to trigger the further display of the card content. Among them, the target topic card interface can also be designed with a first control and a second control. Exemplarily, the first control can be designed as "switch", which is used to replace the specific content included in the card. Exemplarily, the second control can be designed as "enter the card interface". After the user clicks it, more content related to the target topic card can be displayed.

[0056] In summary, the design idea of this application is to determine a target content set at a time, and then play the content of the target content set according to the switching request of the user. Compared with performing an algorithm recall each time the user requests to play the next content to determine the content to be played, this solution can greatly reduce the calculation amount and relieve the calculation pressure.

[0057] Figure 4 is a schematic diagram of an exemplary embodiment of a method for determining playback content shown in this application. As Figure 4 shown, this method for determining playback content includes the following steps:

[0058] S401. In response to detecting a first page switching request of a user, filter out a set of videos to be played from candidate videos, where the set of videos to be played includes multiple videos to be played.

[0059] S402. Obtain candidate topic cards and the placement configuration parameters of each candidate topic card. The placement configuration parameters include a population matching tag and a card matching strategy.

[0060] Among them, the candidate topic card refers to a card corresponding to other themes that may interest the user except for videos. For example, the candidate topic card may include various theme types of cards such as music cards, audiobook cards, short drama cards, news list cards, etc.

[0061] Among them, for each candidate topic card, the placement configuration parameters may include a population matching tag and a card matching strategy.

[0062] Among them, the population matching tag refers to a card tag used to match the user's video preference tags. For example, if the candidate topic card is a short drama, since users who like to watch TV drama and movie content often show interest in short drama cards, the population matching tags corresponding to the short drama cards can be set as "TV drama" and "movie".

[0063] Among them, the card matching strategy refers to a strategy used to match with the user to determine whether to insert a topic card in the current set of videos to be played, or which topic card to insert.

[0064] Among them, the card matching strategy may include an entry strategy, an exit strategy, and an exposure control strategy.

[0065] Among them, for any candidate topic card, the entry strategy is used to represent the given brush times and positions where the candidate topic card can appear. For example, if the entry parameter is set to 2-1, it means that the candidate topic card can appear in the first position of the second brush. Among them, the second brush refers to the second first page switching request initiated, which can be understood as Figure 2 the first page switching request 2 shown in

[0066] Among them, for any candidate topic card, the exit strategy is used to represent the exit parameter of the candidate topic card after the user performs a dislike operation (such as the user quickly swipes away, or the user clicks no longer recommended, or the user clicks dislike). For example, if the exit setting is 1-3, it means that after the user performs a dislike operation, the candidate topic card will not be shown to the user again within 3 days.

[0067] Among them, for any candidate topic card, exposure control is used to represent the display limit of the candidate topic card. For example, if the exposure control parameter is set to 1-2, it means that this candidate topic card can be displayed to the same user at most 2 times within 1 day.

[0068] S403. Obtain the user interaction portrait of the candidate topic card for the user.

[0069] S404. Obtain the video preference tags of the user.

[0070] Among them, video preference tags can be labeled for the user according to the user's preferences for historical played videos. For example, if a user likes to watch TV dramas, movies, and music variety shows, the user's video preference tags can be set as: "TV drama", "movie", "music".

[0071] S405. Match the video preference tags with the population matching tags corresponding to each candidate topic card, and use the candidate topic cards with successful matches as the first pending topic cards.

[0072] Match the video preference tags with the population matching tags corresponding to each candidate topic card. If there is at least one video preference tag corresponding to the user in the population matching tags corresponding to a certain candidate topic card, it is determined that the candidate topic card has a successful match, and the candidate topic card is used as the first pending topic card.

[0073] S406. Screen out the target topic cards from the first pending topic cards based on the user interaction portrait and the card matching strategy.

[0074] Among them, the user interaction portrait will include parameters such as the timestamp of the user's last click behavior on each candidate topic card and the timestamp of the last dislike operation. Match according to the parameters included in the user interaction portrait and the above-set card matching strategy to determine whether the user is eligible to display the first pending topic card in the current target content set to be determined, and use the first pending topic card with the display eligibility obtained after matching as the target topic card.

[0075] S407. Determine the target content set to be played based on the target topic cards and the set of videos to be played.

[0076] As an achievable method, obtain the insertion position of the target topic card in the set of videos to be played; insert the target topic card into the set of videos to be played based on the insertion position to obtain the target content set. Among them, the insertion position of the target topic card in the set of videos to be played can be determined according to the above approach parameters.

[0077] Among them, if the target topic card is not obtained in the final result of the above matching, the set of videos to be played is directly used as the set of target content to be played, which means that no topic card needs to be inserted into the set of target content determined this time.

[0078] In the embodiments of the present application, delivery configuration parameters are configured for each candidate topic card. The delivery configuration parameters are easy to modify, can greatly improve the management efficiency of each candidate topic card, and can efficiently configure the automated online launch of a certain candidate topic card. The embodiments of the present application introduce in detail the determination process of the target topic card based on the population matching tags and card matching strategies included in the delivery configuration parameters, so that the determined target topic card can be more attractive to users and improve user satisfaction.

[0079] Figure 5 It is a schematic diagram of an exemplary embodiment of a method for determining playback content shown in the present application. As Figure 5 shown, the method for determining the playback content includes the following steps:

[0080] S501, in response to detecting a first page switching request of the user, screen out a set of videos to be played from the candidate videos, where the set of videos to be played includes multiple videos to be played.

[0081] S502, obtain candidate topic cards and the delivery configuration parameters of each candidate topic card, where the delivery configuration parameters include population matching tags and card matching strategies.

[0082] S503, obtain the user interaction portrait of the user for the candidate topic cards.

[0083] S504, obtain the video preference tags of the user.

[0084] S505, match the video preference tags with the population matching tags corresponding to each candidate topic card, and use the candidate topic cards with successful matches as the first pending topic cards.

[0085] For the specific implementation manners of steps S501 to S505, reference may be made to the specific introduction of the relevant parts in the above embodiments, and details will not be elaborated here.

[0086] S506, screen out second pending topic cards from the first pending topic cards based on the user interaction portrait and the card matching strategy, where the card matching strategy includes at least one of card entry parameters, card exit parameters, and card exposure parameters.

[0087] In the embodiments of the present application, the topic cards screened out from the first pending topic cards based on the user interaction portrait and the card matching strategy are used as the second pending topic cards for the next judgment.

[0088] S507. When the number of second pending topic cards is 1, determine the second pending topic card as the target topic card.

[0089] S508. When the number of second pending topic cards is more than one, obtain the card score of each second pending topic card.

[0090] In some embodiments, the card priority of each second pending topic card can be obtained; predict the estimated browsing duration of the user for each second pending topic card; calculate the card score of the second pending topic card based on the estimated browsing duration and the card priority. Among them, the formula for calculating the card score of the second pending topic card based on the estimated browsing duration and the card priority is:

[0091] score = playtime w1 ·priority w2

[0092] In the above formula, score represents the card score of the second pending topic card, playtime represents the estimated browsing duration of the second pending topic card, priority represents the card priority of the second pending topic card, and w1, w2 are adjustable hyperparameters.

[0093] Among them, for each candidate topic card, the card priority can also be configured in its corresponding placement configuration parameters, that is, the card priority belongs to the placement configuration parameters and can be obtained from the placement configuration parameters.

[0094] Among them, the method for determining the estimated browsing duration of the card is: pre-train an estimated browsing duration prediction model based on sample user characteristics, sample topic card characteristics, and interaction data of the sample user for the sample topic card, and then input the user-related characteristics corresponding to the user who currently initiates the first page switching request and the card characteristics of the second pending topic card into the estimated browsing duration prediction model to obtain the estimated browsing duration of the user for the second pending topic card.

[0095] S509. Determine the second pending topic card with the maximum card score as the target topic card.

[0096] Determine the second pending topic card with the maximum card score among the multiple second pending topic cards as the target topic card.

[0097] S510. Determine the target content set to be played based on the target topic card and the set of videos to be played.

[0098] As an implementable approach, obtain the insertion position of the target topic card in the set of videos to be played; insert the target topic card into the set of videos to be played based on the insertion position to obtain the target content set. Among them, the insertion position of the target topic card in the set of videos to be played can be determined according to the above-mentioned entry parameters.

[0099] As another implementable approach, determine the target card score of the target topic card (the card scores of each second pending topic card have been determined above, and there is no need to recalculate here, just look it up directly); if the target card score is greater than or equal to the preset card score threshold, obtain the insertion position of the target topic card in the set of videos to be played, and insert the target topic card into the set of videos to be played based on the insertion position to obtain the target content set. That is to say, it can be understood that the score of the target topic card is high enough to attract users, and here it is allowed to insert the target topic card into the set of videos to be played; if the target card score is less than the card score threshold, directly determine the set of videos to be played as the target content set. That is to say, it can be understood that the score of the target topic card is too low to attract users, and here the insertion of the target topic card into the set of videos to be played is not accepted, so as to avoid introducing topic cards that users are not interested in.

[0100] Among them, the insertion position of the target topic card in the set of videos to be played can be determined according to the above-mentioned entry parameters.

[0101] Among them, if no eligible target topic card is obtained in the above process, directly use the set of videos to be played as the target content set to be played, which means that no topic card needs to be inserted into the target content set determined this time.

[0102] The embodiment of the present application details the determination process of the target topic card based on the population matching label and the card matching strategy included in the placement configuration parameters, and introduces the idea of card score therein, so that under the condition of obtaining an eligible target topic card, only up to 1 target topic card is allowed to be inserted into the set of videos to be played, avoiding user disgust caused by excessive playing of cards.

[0103] Figure 6 It is a schematic diagram of an exemplary embodiment of a method for determining playback content shown in the present application. As Figure 6 shown, the method for determining the playback content includes the following steps:

[0104] S601, in response to detecting a user's first page switching request, screen out a set of videos to be played from the candidate videos, where the set of videos to be played contains multiple videos to be played.

[0105] S602. Obtain candidate topic cards and the placement configuration parameters for each candidate topic card. The placement configuration parameters include population matching tags, card matching strategies, and card priorities.

[0106] S603. Obtain the user interaction portrait of the user for the candidate topic cards.

[0107] S604. Obtain the video preference tags of the user.

[0108] S605. Match the video preference tags with the population matching tags corresponding to each candidate topic card, and use the candidate topic cards with successful matches as the first pending topic cards.

[0109] S606. Screen out the second pending topic cards from the first pending topic cards based on the user interaction portrait and the card matching strategy. The card matching strategy includes at least one of card entry parameters, card exit parameters, and card exposure parameters.

[0110] S607. In response to the number of the second pending topic cards being 1, determine the second pending topic card as the target topic card.

[0111] S608. In response to the number of the second pending topic cards being multiple, obtain the card priorities of each second pending topic card.

[0112] S609. Predict the estimated browsing duration of the user for each second pending topic card.

[0113] S610. Calculate the card scores of the second pending topic cards based on the estimated browsing duration of the cards and the card priorities.

[0114] S611. Determine the second pending topic card with the highest card score as the target topic card.

[0115] Regarding the specific implementation manners of steps S601 to S611, reference may be made to the specific introductions in the relevant parts of the above embodiments, and details will not be elaborated herein.

[0116] S612. Determine the target card score of the target topic card.

[0117] S613. Obtain the insertion position of the target topic card in the set of videos to be played, obtain the target video to be played at the insertion position in the set of videos to be played, and obtain the video score of the target video to be played.

[0118] Suppose the set of videos to be played is: {Video to be played 1, Video to be played 2, Video to be played 3, Video to be played 4}, and the insertion position of the target topic card in the set of videos to be played is the 3rd position. That is, Video to be played 3 is used as the target video to be played, so as to perform a score PK between Video to be played 3 and the target topic card subsequently.

[0119] In some embodiments, the steps of obtaining the video score of the target video to be played include: predicting the estimated browsing duration of the target video to be played by the user; determining the video score corresponding to the target video to be played according to the estimated browsing duration of the video.

[0120] Among them, the historical video behavior characteristics of the user and the video characteristics of the target video to be played can be input into a pre-trained video estimated browsing duration prediction model to obtain the estimated browsing duration of the target video to be played output by the model.

[0121] In some embodiments, a mapping table between the estimated browsing duration of the video and the video score can be set in advance, and the video score corresponding to the target video to be played can be obtained by querying this mapping table through the estimated browsing duration of the target video to be played by the user.

[0122] In some embodiments, the estimated browsing duration of the target video to be played by the user can be directly used as the video score corresponding to the target video to be played.

[0123] S614, in response to the target card score being greater than or equal to the video score, inserting the target topic card into the set of videos to be played based on the insertion position to obtain a target content set.

[0124] If the target card score is greater than or equal to the video score, it means that the target topic card is more attractive to the user than the target video to be played. Here, the set of videos to be played is allowed to accept the insertion of the target topic card.

[0125] Suppose the set of videos to be played is: {Video to be played 1, Video to be played 2, Video to be played 3, Video to be played 4}, and the insertion position of the target topic card in the set of videos to be played is the 3rd position. That is, Video to be played 3 is used as the target video to be played. If the target card score of the target topic card is greater than or equal to the video score of Video to be played 3, inserting the target topic card into the set of videos to be played based on the insertion position to obtain a target content set. The target content set is: {Video to be played 1, Video to be played 2, target topic card, Video to be played 3, Video to be played 4}.

[0126] Among them, the insertion mentioned in this application refers to inserting before the target video to be played at the corresponding position in the set of videos to be played, rather than deleting the target video to be played.

[0127] S615. Determine the set of videos to be played as the set of target content in response to the target card score being less than the video score.

[0128] If the target card score is less than the video score, it indicates that the target topic card is less attractive to the user than the target video to be played. There is no need to insert the target topic card at the corresponding position in the set of videos to be played. Instead, directly set the set of videos to be played as the set of target content.

[0129] In the embodiment of the present application, by having the target video to be played and the target topic card perform a score PK, and only allowing the target topic card to be inserted into the set of videos to be played if the PK is successful, it can ensure that users first come into contact with more attractive content, thereby enhancing the viewing experience and satisfaction. The present application can recommend different sets of target content according to changes in user preferences, as well as recommend different sets of target content for different users, improving the personalization degree of content recommendation and increasing user stickiness.

[0130] Figure 7 It is a schematic diagram of a device for determining playback content shown in the present application. As Figure 7 shown, the device 700 for determining playback content includes a video screening module 701, a parameter acquisition module 702, a card screening module 703, and a content determination module 704, where:

[0131] The video screening module 701 is configured to screen out a set of videos to be played from candidate videos in response to detecting a first page switching request of the user. The set of videos to be played contains multiple videos to be played.

[0132] The parameter acquisition module 702 is configured to acquire candidate topic cards and the placement configuration parameters of each candidate topic card.

[0133] The card screening module 703 is configured to acquire the user interaction portrait of the user for the candidate topic cards, and screen out the target topic cards from the candidate topic cards based on the user interaction portrait and the placement configuration parameters.

[0134] The content determination module 704 is configured to determine the set of target content to be played based on the target topic cards and the set of videos to be played.

[0135] This device configures delivery configuration parameters for each candidate topic card. The delivery configuration parameters are easy to modify, which can greatly improve the management efficiency of each candidate topic card and enable the efficient configuration of the automated online launch of a certain candidate topic card. After obtaining the set of videos to be played that the user is interested in, if a target topic card that the user is interested in can be matched, this application determines a set of target content to be played based on the target topic card and the set of videos to be played, and recommends and plays it to the user, which can enhance the user experience, help the user explore other topics besides videos, and improve user satisfaction. This application can recommend different sets of target content according to changes in user preferences, and recommend different sets of target content for different users, improving the personalization of content recommendation and increasing user stickiness.

[0136] Further, the delivery configuration parameters include a population matching tag and a card matching strategy. The card screening module 703 is further configured to: obtain the video preference tag of the user; match the video preference tag with the population matching tag corresponding to each candidate topic card, and use the candidate topic cards with successful matches as the first set of pending topic cards; screen out the target topic cards from the first set of pending topic cards based on the user interaction portrait and the card matching strategy.

[0137] Further, the card screening module 703 is further configured to: screen out a second set of pending topic cards from the first set of pending topic cards based on the user interaction portrait and the card matching strategy, and the card matching strategy includes at least one of a card entry parameter, a card exit parameter, and a card exposure parameter; in response to the number of the second set of pending topic cards being 1, determine the second set of pending topic cards as the target topic cards.

[0138] Further, the card screening module 703 is further configured to: in response to the number of the second set of pending topic cards being multiple, obtain the card score of each second set of pending topic cards; determine the second set of pending topic cards with the highest card score as the target topic cards.

[0139] Further, the delivery configuration parameters further include a card priority. The card screening module 703 is further configured to: obtain the card priority of each second set of pending topic cards; predict the estimated browsing duration of the user for each second set of pending topic cards; calculate the card score of the second set of pending topic cards based on the estimated browsing duration and the card priority.

[0140] Further, the content determination module 704 is further configured to: obtain the insertion position of the target topic card in the set of videos to be played; insert the target topic card into the set of videos to be played based on the insertion position to obtain the set of target content.

[0141] Further, the content determination module 704 is further configured to: determine the target card score of the target topic card; in response to the target card score being greater than or equal to a preset card score threshold, obtain the insertion position of the target topic card in the set of videos to be played, and insert the target topic card into the set of videos to be played based on the insertion position to obtain a target content set; in response to the target card score being less than the card score threshold, determine the set of videos to be played as the target content set.

[0142] Further, the content determination module 704 is further configured to: determine the target card score of the target topic card; obtain the insertion position of the target topic card in the set of videos to be played, obtain the target video to be played at the insertion position in the set of videos to be played, and obtain the video score of the target video to be played; in response to the target card score being greater than or equal to the video score, insert the target topic card into the set of videos to be played based on the insertion position to obtain a target content set; in response to the target card score being less than the video score, determine the set of videos to be played as the target content set.

[0143] Further, the content determination module 704 is further configured to: predict the estimated browsing duration of the user for the target video to be played; determine the video score corresponding to the target video to be played according to the estimated browsing duration of the video.

[0144] Further, the card screening module 703 is further configured to: obtain the historical interaction data of the user for the candidate topic card; construct a user interaction portrait based on the historical interaction data.

[0145] Further, the content determination module 704 is further configured to: display the first content in the target content set on the display interface.

[0146] Further, the content determination module 704 is further configured to: in response to detecting a second page switching request of the user, update the display content of the display interface based on the target content set.

[0147] According to an embodiment of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium, and a computer program product.

[0148] Figure 8FIG. shows a schematic block diagram of an exemplary electronic device 800 that may be used to implement embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as, for example, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as, personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely exemplary and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0149] As Figure 8 shown, the device 800 includes a computing unit 801 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0150] A plurality of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a magnetic disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0151] The computing unit 801 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 executes the various methods and processes described above, such as the method for determining the playback content. For example, in some embodiments, the method for determining the playback content can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the method for determining the playback content described above can be executed. Alternatively, in other embodiments, the computing unit 801 can be configured to execute the method for determining the playback content by any other suitable means (e.g., by means of firmware).

[0152] Various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGA), application-specific integrated circuits (ASIC), application-specific standard products (ASSP), systems-on-a-chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0153] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing devices, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program codes can be executed entirely on the machine, partially on the machine, as an independent software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0154] In the context of this disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0155] To provide for interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can also be used to provide for interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic, speech, or tactile input).

[0156] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0157] A computer system can include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The client-server relationship is generated by computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

[0158] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and no limitations are imposed herein.

[0159] The above specific embodiments do not constitute a limitation on the protection scope of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub - combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the protection scope of this disclosure.

Claims

1. A method for determining playback content, comprising: In response to monitoring a first page switching request of a user, screening a set of videos to be played from candidate videos, wherein the set of videos to be played includes a plurality of videos to be played; Obtain candidate topic cards and delivery configuration parameters of each candidate topic card; Obtaining a user interaction portrait of the user with respect to the candidate topic card, and filtering out a target topic card from the candidate topic cards based on the user interaction portrait and the delivery configuration parameters; A target content set to be played is determined based on the target topic card and the set of videos to be played.

2. The method according to claim 1, wherein: The delivery configuration parameters include a crowd matching tag and a card matching strategy, and the step of selecting a target topic card from the candidate topic cards based on the user interaction portrait and the delivery configuration parameters includes: Obtaining the video preference tag of the user; Matching the video preference tag with the crowd matching tag corresponding to each candidate topic card, and using the successfully matched candidate topic card as the first pending topic card; The target topic card is selected from the first pending topic cards based on the user interaction portrait and the card matching strategy.

3. The method according to claim 2, wherein: The step of selecting the target topic card from the first pending topic cards based on the user interaction portrait and the card matching strategy includes: Filtering a second pending topic card from the first pending topic card based on the user interaction portrait and the card matching strategy, wherein the card matching strategy includes at least one of a card entry parameter, a card exit parameter, and a card exposure parameter; In response to the number of the second pending topic card being 1, the second pending topic card is determined as the target topic card.

4. The method according to claim 3, wherein: The method further comprises: In response to the number of the second pending topic cards being plural, obtaining a card score of each of the second pending topic cards; The second undetermined topic card with the largest card score is determined as the target topic card.

5. The method according to claim 4, wherein: The delivery configuration parameters also include card priority, and obtaining the card score of each second pending topic card includes: Obtain the card priority of each of the second pending topic cards; Predicting an estimated browsing time of each second undetermined topic card by the user; The card score of the second undetermined topic card is calculated based on the estimated browsing time of the card and the card priority.

6. The method according to any one of claims 1 to 5, wherein: The step of determining a target content set to be played based on the target topic card and the set of videos to be played includes: Obtaining the insertion position of the target topic card in the set of videos to be played; The target topic card is inserted into the to-be-played video set based on the insertion position to obtain the target content set.

7. The method according to claim 5, wherein: The step of determining a target content set to be played based on the target topic card and the set of videos to be played includes: Determining a target card score for the target topic card; In response to the target card score being greater than or equal to a preset card score threshold, obtaining an insertion position of the target topic card in the to-be-played video set, and inserting the target topic card into the to-be-played video set based on the insertion position to obtain the target content set; In response to the target card score being less than the card score threshold, the to-be-played video set is determined to be the target content set.

8. The method according to claim 5, wherein: The step of determining a target content set to be played based on the target topic card and the set of videos to be played includes: Determining a target card score for the target topic card; Obtaining an insertion position of the target topic card in the set of videos to be played, obtaining a target video to be played located at the insertion position in the set of videos to be played, and obtaining a video score of the target video to be played; In response to the target card score being greater than or equal to the video score, inserting the target topic card into the to-be-played video set based on the insertion position to obtain the target content set; In response to the target card score being less than the video score, the to-be-played video set is determined to be the target content set.

9. The method according to claim 8, wherein: The step of obtaining the video score of the target video to be played includes: Predicting the estimated browsing time of the target video to be played by the user; The video score corresponding to the target video to be played is determined according to the estimated browsing time of the video.

10. The method according to claim 1, wherein: The obtaining of the user interaction portrait of the user with respect to the candidate topic card includes: Obtaining historical interaction data of the user with respect to the candidate topic card; The user interaction portrait is constructed based on the historical interaction data.

11. The method according to claim 1, wherein: The method further comprises: The first content in the target content set is displayed on a display interface.

12. The method according to claim 11, wherein: After displaying the first content in the target content set on the display interface, the method further includes: In response to monitoring a second page switching request of the user, the display content of the display interface is updated based on the target content set.

13. A device for determining playback content, comprising: A video screening module, configured to screen a set of videos to be played from candidate videos in response to detecting a first page switching request from a user, wherein the set of videos to be played includes a plurality of videos to be played; A parameter acquisition module, used to acquire candidate topic cards and delivery configuration parameters of each candidate topic card; A card screening module, used to obtain a user interaction portrait of the user with respect to the candidate topic card, and screen a target topic card from the candidate topic cards based on the user interaction portrait and the delivery configuration parameters; The content determination module is used to determine a target content set to be played based on the target topic card and the video set to be played.

14. An electronic device comprising: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 12.

15. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-12.

16. A computer program product comprising a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 12.

Images