Video unlocking watching method and related device

Abstract

The invention provides a video unlocking watching method and a related device, and relates to the technical field of software, and the method comprises the steps: obtaining a video unlocking configuration which comprises an advertisement unlocking condition and an interaction style configuration under the condition that a playing authentication result of a user to a target video is unauthorized; if the target video meets the advertisement unlocking condition, acquiring a video watching record of the user, and predicting a member opening probability and an advertisement watching probability of the user according to the video watching record; and determining a target interaction style matched with the member opening probability and the advertisement watching probability based on the interaction style configuration, wherein the target interaction style is used for guiding the user to unlock and watch the target video in a manner of opening the member or watching the incentive advertisement. According to the method, the user is guided to unlock and watch the video by predicting the selection degree of the user to open the member and watch the advertisement based on the video watching record, so that the conversion value of the user can be improved, and meanwhile, the user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of software technology, and in particular to a method for unlocking and viewing a video and a related device. Background Art

[0002] Video platforms generally offer two payment methods: free and membership. After becoming a member, users can watch member videos during their membership period. Currently, some video platforms allow free users to watch incentivized ads to gain access to member videos for a limited period of time. These platforms also provide a fixed entry point for unlocking videos by watching incentivized ads, such as an icon or banner below the member video player window.

[0003] Since all non-member users see the same video unlocking entrance and use a fixed unlocking strategy, this can easily lead to: 1) users who originally intended to open a membership may give up purchasing a membership because they can watch the rewarded ad unlocking video, which may result in the revenue generated by the rewarded ad being lower than the revenue from opening a membership; 2) users who are willing to open a membership may become disgusted after seeing the rewarded ad entrance multiple times, affecting the user experience and even reducing their willingness to open a membership, thereby affecting membership benefits. Summary of the Invention

[0004] In view of the above problems, this application provides a video unlocking viewing method and related devices to achieve the purpose of predicting the user's preference for membership activation and advertisement viewing to guide the user to unlock and watch videos. The specific solution is as follows:

[0005] A first aspect of the present application provides a method for unlocking and viewing a video, the method comprising:

[0006] If the user is not authorized to play the target video, obtain a video unlock configuration, wherein the video unlock configuration includes an advertisement unlock condition and an interaction style configuration;

[0007] If the target video meets the ad unlocking condition, obtain the user's video viewing history, and predict the user's membership activation probability and ad viewing probability based on the video viewing history;

[0008] A target interaction style that matches the membership activation probability and the advertisement viewing probability is determined based on the interaction style configuration, and the target interaction style is used to guide the user to unlock and watch the target video by activating a membership or watching an incentive advertisement.

[0009] In a possible implementation, predicting the user's membership activation probability and advertisement viewing probability based on the video viewing history includes:

[0010] Extracting original user portrait features from the video viewing record;

[0011] Extracting a first portrait feature for member activation prediction and a second portrait feature for advertisement viewing prediction from the original portrait features respectively;

[0012] The first portrait feature is input into a first prediction model, and the membership activation probability is output through the first prediction model; and the second portrait feature is input into a second prediction model, and the advertisement viewing probability is output through the second prediction model.

[0013] In one possible implementation, the original portrait features include at least one of the following: user activity, advertising tolerance, payment behavior characteristics, price sensitivity characteristics, time sensitivity, content preference characteristics, associated behavior sequence characteristics for characterizing the association between advertising viewing behavior and membership activation behavior, and economic ability characteristics.

[0014] In a possible implementation, the interaction style configuration includes a first membership activation threshold and a first advertisement viewing threshold;

[0015] The determining, based on the interaction pattern configuration, a target interaction pattern that matches the membership activation probability and the advertisement viewing probability includes:

[0016] If the membership activation probability is greater than or equal to the first membership activation threshold, and the advertisement viewing probability is less than the first advertisement viewing threshold, the first interaction pattern for indicating membership activation is used as the target interaction pattern;

[0017] If the membership activation probability is less than the membership activation threshold and the advertisement viewing probability is greater than or equal to the first advertisement viewing threshold, the second interaction pattern for indicating viewing of the incentive advertisement is used as the target interaction pattern.

[0018] In one possible implementation, the interaction style configuration further includes at least one of a mandatory membership activation configuration and a mandatory advertisement viewing configuration, the mandatory membership activation configuration includes a first portrait condition and a second membership activation threshold, the second membership activation threshold is smaller than the first membership activation threshold, and the mandatory advertisement viewing configuration includes a second portrait condition and a second advertisement viewing threshold, the second advertisement viewing threshold is smaller than the first advertisement viewing threshold;

[0019] The determining of a target interaction pattern that matches the membership activation probability and the advertisement viewing probability based on the interaction pattern configuration further includes:

[0020] In a case where the mandatory membership activation configuration is included in the interaction style configuration, if the user meets the first profile condition and the membership activation probability is greater than or equal to the second membership activation threshold, the first interaction style is used as the target interaction style;

[0021] In a case where the interaction style configuration includes the forced advertisement viewing configuration, if the user meets the second portrait condition and the advertisement viewing probability is greater than or equal to the second advertisement viewing threshold, the second interaction style is used as the target interaction style.

[0022] In one possible implementation, the method further includes:

[0023] If the target video does not meet the advertisement unlocking condition, an original interaction style is output, where the original interaction style is used to guide the user to unlock and watch the target video by becoming a member or paying a fee.

[0024] A second aspect of the present application provides a video unlocking and viewing device, comprising:

[0025] An unlock configuration acquisition module, configured to acquire a video unlock configuration when the user's playback authentication result for the target video is unauthorized, wherein the video unlock configuration includes an advertisement unlock condition and an interaction style configuration;

[0026] A probability prediction module is used to obtain the user's video viewing history if the target video meets the advertisement unlocking condition, and predict the user's membership activation probability and advertisement viewing probability based on the video viewing history;

[0027] An interaction style determination module is used to determine a target interaction style that matches the membership activation probability and the advertisement viewing probability based on the interaction style configuration, and the target interaction style is used to guide users to unlock and watch the target video by activating a membership or watching an incentive advertisement.

[0028] A third aspect of the present application provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the video unlocking and viewing method of the first aspect or any implementation of the first aspect.

[0029] A fourth aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0030] The memory is used to store computer programs;

[0031] The processor is used to execute the computer program so that the electronic device can implement the video unlocking and viewing method of the first aspect or any implementation method of the first aspect.

[0032] In a fifth aspect, the present application provides a computer storage medium carrying one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the video unlocking and viewing method in the first aspect or any implementation method of the first aspect.

[0033] By means of the above technical solution, the present application provides a method for unlocking and viewing a video and a related device, including: when the user's playback authentication result for the target video is unauthorized, obtaining a video unlocking configuration, the video unlocking configuration including an advertisement unlocking condition and an interaction style configuration; if the target video meets the advertisement unlocking condition, obtaining the user's video viewing record, and predicting the user's membership activation probability and advertisement viewing probability based on the video viewing record; determining a target interaction style that matches the membership activation probability and advertisement viewing probability based on the interaction style configuration, the target interaction style is used to guide the user to unlock and view the target video by activating a membership or watching an incentive advertisement. Since different non-member users have different intentions to activate a membership and watch advertisements, the present application predicts the user's degree of choice for activating a membership and watching advertisements based on the video viewing record to guide the user to unlock and view the video, which can improve the user's conversion value and enhance the user's experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale.

[0035] Figure 1 A flowchart of a method for unlocking and viewing a video provided in an embodiment of the present application;

[0036] Figure 2 A partial flow chart of a method for unlocking and viewing a video provided in an embodiment of the present application;

[0037] Figure 3 An example diagram of a target interaction style provided in an embodiment of the present application;

[0038] Figure 4 Another example diagram of a target interaction style provided in an embodiment of the present application;

[0039] Figure 5 Another example diagram of a target interaction style provided in an embodiment of the present application;

[0040] Figure 6 A schematic diagram of the structure of a video unlocking and viewing device provided in an embodiment of the present application;

[0041] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] The following describes the embodiments of the present application in conjunction with the accompanying drawings. The terms used in the implementation methods of the present application are only used to explain the specific embodiments of the present application and are not intended to limit the present application.

[0043] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0044] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, and this is merely a way of distinguishing the objects of the same attributes when describing them in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0045] Existing video platforms generally support membership subscription strategies, where users can unlock video content by purchasing a membership. In addition, some platforms also support ad unlocking, adopting a dual-track system of "membership subscription + ad unlocking". The dual-track unlocking system of "membership subscription + ad unlocking" on video platforms provides fixed entrances for membership activation and ad unlocking respectively. When non-member users enter videos available to members, they will be prompted at a fixed location to activate membership or watch an incentivized ad before they can continue to watch the video content. Different people see the same interface. Since all non-member users see the same video unlocking entrance and use a fixed unlocking strategy, this can easily lead to:

[0046] 1) Users who originally intended to become members may give up purchasing membership because they can watch incentive ads to unlock videos, which may result in the revenue generated by incentive ads being lower than the revenue from becoming a member. 2) Users who are willing to become members may become disgusted after seeing the incentive ad entrance multiple times, which affects the user experience and may even reduce their willingness to become a member, thereby affecting membership revenue.

[0047] In response to the above issues, this application has found through research that different groups of people have different acceptance of incentive ads and membership activation rates, and the click-through rates of different screen materials displayed to users will also be different. Combined with the above data features, this application can calculate user characteristics based on user behavior data, advertising data, etc., and predict the user's acceptance of membership activation and viewing incentive ads to decide whether to highlight the unlocking entrance of membership activation or incentive ads for different users, thereby improving membership conversion rate and incentive advertising revenue.

[0048] To address the aforementioned issues, the present invention provides a video unlocking viewing method that uses video viewing history to predict a user's preference for membership activation and ad viewing. This method determines which content should be highlighted for the user, providing a content unlocking selection interface that better meets the user's preferences and increases user conversion value. The following describes the video unlocking viewing method in detail with reference to the accompanying figures.

[0049] See also Figure 1 , Figure 1 This is a flow chart of a method for unlocking and viewing a video provided in an embodiment of the present application. Figure 1 As shown, a video unlocking and viewing method provided in an embodiment of the present application can be applied to the back end, including steps S101 to S103, and these steps are described in detail below.

[0050] S101: When the user's playback authentication result for the target video is unauthorized, obtain a video unlocking configuration, where the video unlocking configuration includes an advertisement unlocking condition and an interaction style configuration.

[0051] In an embodiment of the present application, when a user at the front end enters the video playback page and the target video starts playing, the user needs to be authenticated for playback first to determine whether the user has the right to play the target video. To this end, the back end generates a corresponding playback authentication result based on the user's rights record and rights configuration. If the user's playback authentication result for the target video is authorized, the back end obtains and returns the video playback address of the target video from the existing CDN (Content Delivery Network) system, so that when the front end receives the authorized playback authentication result, it can use the video playback address of the target video to play the target video. It should be noted that the back end's video playback authentication, CDN system, etc. are services that already exist on general video platforms, and this application will not elaborate on them.

[0052] If the user's playback authentication result for the target video is unauthorized, the front-end can initialize the unlock guidance function upon receiving the unauthorized playback authentication result, and the back-end obtains the video unlock configuration, which includes the advertising unlock conditions and interaction style configuration. Among them, the advertising unlock conditions include the conditions for unlocking different videos using watching rewarded ads, and the interaction style configuration includes an interaction style that focuses on opening a membership and an interaction style for testing watching rewarded ads. For example, the advertising unlock conditions may include the following:

[0053] 1) The total number of times you can unlock using rewarded ads. Limiting the number of times can make users cherish the number of unlocks more.

[0054] 2) The number of times each user can unlock memberships using rewarded ads and the effective duration of the unlocking function each day. This can, to a certain extent, avoid a reduction in membership activations due to watching rewarded ad unlocking videos.

[0055] 3) The scope of programs that support ad unlocking: select some programs that can support unlocking by watching incentive ads, and exclude series that only members can watch in advance to ensure differentiated member benefits.

[0056] 4) Different programs support the number of episodes unlocked by ads. For example, the last three episodes of a popular TV series cannot be watched and can be unlocked with incentive ads to ensure differentiated member benefits.

[0057] 5) Different programs can set the viewing time for advertising unlocking. For example, a popular movie can be configured to unlock the last 10 minutes with incentivized advertising, ensuring differentiated member benefits.

[0058] S102: If the target video meets the advertisement unlocking condition, obtain the user's video viewing history, and predict the user's membership activation probability and advertisement viewing probability based on the video viewing history.

[0059] In an embodiment of the present application, if the target video meets the advertising unlocking conditions, it means that the target video supports both watching incentive ads and opening a membership. The user's page browsing, content playback, paid purchases, ad viewing and other behaviors in the video platform will have relevant data reported to the backend, and the backend will form a corresponding video viewing record. In this regard, the backend can obtain the video viewing records formed by the user watching videos in historical time. For example, the video viewing record can include user attributes, behavioral data, consumption data, and advertising data. Among them, user attributes can include region (region can be associated through IP library service), device type, device brand, device model, behavioral data can include viewing records, viewing time, search records, incentive advertising unlocking records, etc., consumption data can include membership purchase records, coupon usage, etc., and advertising data can include click-through rate, skip rate, video ad completion rate, etc.

[0060] After obtaining the user's video viewing history, the backend can pre-process and classify the video viewing history to predict the probability that the user will activate a membership and unlock the target video (i.e., the membership activation probability) and the probability that the user will unlock the target video by watching an incentive ad (i.e., the ad viewing probability).

[0061] In one possible implementation, the probability of membership activation and ad viewing can be accurately predicted through feature extraction and model prediction. Figure 2 , Figure 2 This is a partial flow chart of a method for unlocking and viewing a video provided in an embodiment of the present application. Figure 2 As shown, the embodiment of the present application provides a method for unlocking and viewing videos, wherein step S102 "predicting the user's membership activation probability and advertisement viewing probability based on the video viewing record" includes steps S201 to S203, and these steps are described in detail below.

[0062] S201, extracting the user's original portrait features from the video viewing history.

[0063] In the embodiment of the present application, the backend can use feature engineering technology to generate user portrait features (i.e., raw portrait features) based on video viewing records. The raw portrait features can describe the user's advertising viewing behavior, membership activation behavior, etc. on the video platform to a certain extent.

[0064] In one possible implementation, the original portrait features include at least one of the following: user activity, advertising tolerance, payment behavior characteristics, price sensitivity characteristics, time sensitivity, content preference characteristics, associated behavior sequence characteristics used to characterize the association between advertising viewing behavior and membership activation behavior, and economic ability characteristics.

[0065] The following describes user activity, advertising tolerance, payment behavior characteristics, price sensitivity characteristics, time sensitivity, content preference characteristics, correlation behavior sequence characteristics used to characterize the correlation between ad viewing behavior and membership activation behavior, and economic ability characteristics. Specifically:

[0066] 1) User activity. User activity can be expressed as the frequency of user logins, defined using an activity model, and comprehensively scored based on the most recent active time and the average number of active days per week. Among them, the most recent active time = (current date - most recent active date) × number of days, and the average number of active days per week = the number of active days within 30 days / the number of weeks corresponding to 30 days. Therefore, user activity (percentage system) = 40 × (1 - most recent active time / 30) + 60 × average number of active days per week / 7. It should be noted that 40 and 60 are the weights of the most recent active time and the average number of active days per week, respectively. In actual application, they can be adjusted according to the actual scenario, and this embodiment of the application does not limit this.

[0067] 2) Ad tolerance. Ad tolerance is calculated based on ad click-through rate, ad skip rate, and ad completion rate. Here, ad click-through rate = number of ad clicks / number of ad exposures, ad skip rate = number of ad skips / number of ad exposures, and ad completion rate = number of video ad completions / number of ad exposures. The ad click-through rate, ad skip rate, and ad completion rate are standardized (normalized to the range of [0,1]), and then the standardized ad click-through rate, ad skip rate, and ad completion rate are multiplied by their weights and added together to obtain the final ad tolerance. Ad tolerance = standardized ad click-through rate × 0.3 + (1-standardized ad skip rate) × 0.4 + standardized ad completion rate × 0.3. It should be noted that 0.3, 0.4, and 0.3 are the weights of the ad click-through rate, ad skip rate, and ad completion rate, respectively. These can be adjusted according to the actual scenario during actual application, and this embodiment of the present application does not limit this.

[0068] 3) Payment behavior characteristics. These include membership purchase history, payment frequency, last payment date, and member loyalty. If a member has previously purchased a membership, the purchase record is marked as 1; otherwise, it is marked as 0. Payment frequency (average monthly payments) = total number of purchases / number of months registered. Last payment date (in days) = current date - last purchase date. Member loyalty = cumulative membership days / registration days.

[0069] 4) Price Sensitivity. This characteristic represents the response rate to promotional offers. Users with a high historical response rate to promotional offers are more likely to pay and respond again. This includes coupon reliance, price sensitivity, and recent coupon usage. Coupon reliance = number of coupons used / total number of orders; price sensitivity = total coupon discount rates / total number of orders; and recent coupon usage (in days) = current date - date of last coupon use.

[0070] 5) Time sensitivity. This indicates whether users are eager to watch a video immediately after it's released. This can be measured using the first-day view rate. First-day view rate = number of views within 24 hours of the video's release / total number of views within 24 hours of the video's release.

[0071] 6) Content preference features. This feature indicates the video content that users frequently watch. Users are more willing to pay for and unlock content for frequently watched content. This feature includes user preference scores for different content types. The preference score for a content type is calculated by dividing the number of times a user has watched that content type by the total number of times the user has viewed all content types.

[0072] 7) Associated Behavior Sequence Features. If a user activates a membership after viewing n incentivized ads, the likelihood of subsequent activation can be inferred based on the characteristics of past activations. This feature quantifies the relationship between the number of times a user views incentivized ads and subsequent activations, revealing the impact of viewing incentivized ads on membership conversion. This includes the time window, ad view threshold, and membership conversion rate. The time window is the interval between viewing an incentivized ad and activation; the ad view threshold is the number of times a user views an incentivized ad before activation; and the membership conversion rate is the percentage of users who activate membership when the number of ad views reaches the threshold.

[0073] Based on different users' video viewing records, we can mark the number of times different users have viewed ads and whether they have activated membership. We can also query the number of times different users have viewed incentive ads before activation, and perform distribution statistics on ad viewing thresholds and membership conversion rates. The following Table 1 illustrates the membership conversion rates corresponding to different ad viewing thresholds.

[0074] Table 1

[0075]

[0076] 8) Economic Ability: This can be scored based on a combination of device model and regional consumption levels. Users who use high-end devices or live in high-consumption areas have higher economic capabilities and are more likely to become members. The device model score can be referenced by the corresponding price on the e-commerce platform, while the regional consumption level score can be referenced by per capita GDP data from the National Bureau of Statistics.

[0077] It should be noted that the above briefly describes the relevant features in the original portrait features. In actual application, the number of features and feature selection can be selected according to the needs of the scene, and the embodiments of the present application do not limit this.

[0078] S202, extracting a first portrait feature for member activation prediction and a second portrait feature for advertisement viewing prediction from the original portrait features.

[0079] In the embodiment of the present application, since the prediction targets of member activation prediction and advertisement viewing prediction are different, the portrait features required for the two are also different. The portrait features for member activation prediction (i.e., the first portrait features) and the portrait features for advertisement viewing prediction (i.e., the second portrait features) can be extracted from the original portrait features.

[0080] For example, the first portrait features may include user activity, payment behavior features, price sensitivity features, time sensitivity, content preference features, associated behavior sequence features, and economic ability features; the second portrait features may include user activity, advertising tolerance, price sensitivity features, time sensitivity, content preference features, and associated behavior sequence features.

[0081] S203, inputting the first portrait feature into the first prediction model, and outputting the membership activation probability through the first prediction model; and inputting the second portrait feature into the second prediction model, and outputting the advertisement viewing probability through the second prediction model.

[0082] In an embodiment of the present application, the first portrait feature and the second portrait feature obtained in step S202 are respectively input into the first prediction model and the second prediction model. The first prediction model is used to classify and predict the first portrait feature to obtain the probability of membership activation, and the second prediction model is used to classify and predict the second portrait feature to obtain the probability of advertising viewing.

[0083] The first prediction model and the second prediction model can be obtained in advance based on machine learning algorithm training. For example, the first prediction model and the second prediction model can be trained using Logistic Regression in a supervised learning algorithm. The following briefly describes the training process of the first prediction model and the second prediction model:

[0084] The video viewing records of users serving as samples on the video platform are collected, and after data cleaning, the corresponding original portrait features are extracted from them. Based on the calculation frequency and data real-timeness, the extraction of original portrait features can be divided into two parts: offline calculation and real-time calculation. Offline calculation is to perform batch feature calculations based on historical data on a regular basis, mainly calculating the characteristics of long-term behaviors, such as user activity, payment behavior characteristics, price sensitivity characteristics, time sensitivity, content preference characteristics, economic ability characteristics, etc.; real-time calculation is to calibrate the features obtained by offline calculation in real time based on real-time data, and can mainly perform real-time calculations on short-term behavioral characteristics, such as advertising tolerance. The original portrait features are vectorized and stored, and a storage medium that can be read quickly, such as memory storage, is selected so that the algorithm model can quickly obtain relevant portrait features.

[0085] For different users serving as samples, the first portrait feature used for membership activation prediction and the second portrait feature used for advertisement viewing prediction are extracted from their original portrait features, and then the first portrait feature and the second portrait feature are respectively labeled as samples.

[0086] When labeling samples of the first portrait feature, the labeling can be based on the user's membership activation behavior data. Specifically, when the front-end displays the [Activate Membership] related interactive interface, data is reported, including user ID, session ID, IP, model, etc. When the user successfully activates the membership, order data will be generated, and the session ID and user ID information of the storage source will be associated with the order data. In the member order data, the report record displayed on the [Activate Membership] interface is associated with the session ID. The report record of successfully activated membership is marked as a positive sample, otherwise it is marked as a negative sample.

[0087] When labeling samples of the second portrait feature, labeling can be performed based on the user's advertising exposure data. Specifically, each time the advertising content is displayed, an exposure report will be made, and the reporting content includes the user ID, exposure unique ID, IP, model, etc.; when the user clicks on the advertising content, a click report will be made, and the reporting content includes the user ID, exposure unique ID, IP, model, etc.; for rewarded video ads, when the user finishes watching the rewarded ad, a completion report will be made, and the reporting content includes the user ID, exposure unique ID, IP, model, etc.; in the ad click and completion data, the ad exposure record is associated with the exposure unique ID, and the ad exposure record with ad clicks or completions is marked as a positive sample, otherwise it is marked as a negative sample.

[0088] The user samples are randomly divided into training and test sets in an M1:N1 ratio. The first profile features and their annotations corresponding to the training set are input into the base model corresponding to the first prediction model. The AUC (Area Under the ROC Curve) of the test set is used to measure model performance and adjust hyperparameters. The offline model is saved for real-time prediction. Similarly, the user samples are randomly divided into training and test sets in an M2:N2 ratio. The second profile features and their annotations corresponding to the training set are input into the base model corresponding to the second prediction model. The AUC (Area Under the ROC Curve) of the test set is used to measure model performance and adjust hyperparameters. The offline model is saved for real-time prediction. Based on the offline-trained first and second prediction models, prediction results can be obtained in real time by calling the API (Application Program Interface).

[0089] This training process yields the first and second prediction models. The first prediction model predicts the probability of a user becoming a member, ranging from 0 to 1. A value closer to 1 indicates a higher probability of the user becoming a member. The second prediction model predicts the probability of a user viewing an ad, ranging from 0 to 1. A value closer to 1 indicates a higher probability of the user viewing an incentivized ad. The first and second prediction models have different prediction objectives and utilize different profile features. Consequently, the weights assigned to similar profile features are also different. Table 2 illustrates the weights assigned to different profile features by the first and second prediction models.

[0090] Table 2

[0091]

[0092] S103: Determine a target interaction style that matches the membership activation probability and the advertisement viewing probability based on the interaction style configuration. The target interaction style is used to guide the user to unlock and watch the target video by activating a membership or watching an incentive advertisement.

[0093] In an embodiment of the present application, after obtaining the user's membership activation probability and advertisement viewing probability, the backend can determine whether the membership activation probability meets the membership activation conditions and whether the advertisement viewing probability meets the advertisement viewing conditions based on the interaction style configuration.

[0094] If the membership activation probability meets the membership activation conditions, it means that the user is inclined to activate the membership. In this case, the target interaction style is used to indicate activation of the membership. Figure 3 , Figure 3 This is an example diagram of a target interaction style provided in an embodiment of the present application. Figure 3 As shown, an embodiment of the present application provides a target interaction style that highlights the membership activation entrance for activating membership, and highlights reminders if there is a discount activity or the user has available coupons. At the same time, a smaller position is provided to display an advertisement viewing entrance for watching incentive advertisements.

[0095] If the ad viewing probability meets the ad viewing condition, it means that the user is inclined to watch rewarded ads. In this case, the target interaction style is used to indicate watching rewarded ads. Figure 4 , Figure 4 This is another example diagram of a target interaction style provided by an embodiment of the present application. Figure 4 As shown, an embodiment of the present application provides a target interaction style that highlights an advertisement viewing entrance for watching incentive advertisements, while providing a smaller position to display a membership activation entrance for activating membership.

[0096] In addition, if the membership activation probability meets the membership activation conditions and the ad viewing probability also meets the ad viewing conditions, it means that the user has the same acceptance of membership activation and watching incentive ads. At this time, the target interaction style can use areas of the same size to display the membership activation entrance and the ad viewing entrance without any prominent display. Figure 5 This is another example diagram of a target interaction style provided by an embodiment of the present application. Figure 5 As shown, in the target interaction style, the membership opening entrance and the advertisement viewing entrance are of similar size, and users can choose to unlock and watch the target video by opening a membership or watching an incentive advertisement.

[0097] The backend returns the target interaction style to the frontend, which then renders the target interaction style to present the unlocking guidance interface to the user. Additionally, if the target interaction style indicates watching an incentivized ad, the incentivized ad can automatically play if the user remains on the unlocking guidance interface for a certain period of time without performing any action. After the incentivized ad plays, the user automatically gains access to the unlocked video. This feature can also be selectively enabled or disabled through configuration.

[0098] When the user selects the relevant unlocking method in the unlocking guide interface, the corresponding unlocking process is entered, including several situations:

[0099] 1) Select "Activate Membership" to unlock the target video. A payment window will pop up. After the user successfully pays, the front-end calls the back-end rights service, which writes the user's membership rights into the user rights record for subsequent playback authentication.

[0100] 2) Selecting to watch an incentivized ad unlocks the target video. A pop-up window displays the incentivized ad, along with a description of the incentive conditions (e.g., watching or clicking on the ad). Once the user meets the incentive conditions, the frontend reports the data and calls the backend's rights service. The backend then writes the user's ad rights into the user rights record for subsequent playback authentication.

[0101] In one possible implementation, a membership activation threshold (i.e., a first membership activation threshold) and an ad viewing threshold (i.e., a first ad viewing threshold) can be directly set in the interaction style configuration to match the target interaction style. In this regard, an embodiment of the present application provides a method for unlocking and viewing a video, wherein the interaction style configuration includes a first membership activation threshold and a first ad viewing threshold. In this regard, step S103, "determining a target interaction style that matches the membership activation probability and ad viewing probability based on the interaction style configuration," may include the following steps:

[0102] If the membership activation probability is greater than or equal to the first membership activation threshold, and the advertisement viewing probability is less than the first advertisement viewing threshold, the first interaction pattern for indicating the activation of the membership is used as the target interaction pattern;

[0103] If the membership activation probability is less than the membership activation threshold and the advertisement viewing probability is greater than or equal to the first advertisement viewing threshold, the second interaction pattern for indicating viewing the incentive advertisement is used as the target interaction pattern.

[0104] In the embodiment of the present application, the first member activation threshold is 0.5 and the first advertisement viewing threshold is 0.5 as an example. If the member activation probability is greater than or equal to 0.5 and the advertisement viewing probability is less than 0.5, Figure 3 The interaction style shown (i.e., the first interaction style) is used as the target interaction style. If the member activation probability is less than 0.5 and the ad viewing probability is greater than or equal to 0.5, Figure 4 The shown interaction style (ie, the second interaction style) is used as the target interaction style.

[0105] In addition, if the member activation probability is greater than or equal to 0.5, and the ad viewing probability is greater than or equal to 0.5, Figure 5 The interaction style shown is used as the target interaction style.

[0106] In one possible implementation, different mandatory matching mechanisms can be set for activating a membership or watching an incentive advertisement. When the mandatory matching mechanism for activating a membership is met, the target interaction style is used to indicate the activation of a membership, and when the mandatory matching mechanism for watching an incentive advertisement is met, the target interaction style is used to indicate the viewing of an incentive advertisement. In this regard, an embodiment of the present application adopts a method for unlocking and viewing a video, wherein the interaction style configuration further includes at least one of a mandatory membership activation configuration and a mandatory advertisement viewing configuration, the mandatory membership activation configuration includes a portrait condition (i.e., a first portrait condition) for indicating mandatory membership activation and a corresponding member activation threshold (i.e., a second member activation threshold), the second member activation threshold being less than the first member activation threshold, the mandatory advertisement viewing configuration includes a portrait condition (i.e., a second portrait condition) for indicating mandatory viewing of an incentive advertisement and a corresponding advertisement viewing threshold (i.e., a second advertisement viewing threshold), the second advertisement viewing threshold being less than the first advertisement viewing threshold.

[0107] For example, the first portrait condition in the mandatory membership activation configuration is "high paying ability" and the second membership activation threshold is 0.3, or the first portrait condition is "users with high user activity and historical consumption records" and the second membership activation threshold is 0.3; the second portrait condition in the mandatory advertising viewing configuration is "users with high advertising click-through rate and low advertising skip rate" and the second advertising viewing threshold is 0.3.

[0108] In this regard, step S103 of "determining a target interaction style that matches the member activation probability and the advertisement viewing probability based on the interaction style configuration" may further include the following steps:

[0109] When the interaction style configuration includes a mandatory membership activation configuration, if the user meets the first profile condition and the membership activation probability is greater than or equal to the second membership activation threshold, the first interaction style is used as the target interaction style;

[0110] When the interaction style configuration includes a mandatory advertisement viewing configuration, if the user meets the second portrait condition and the advertisement viewing probability is greater than or equal to the second advertisement viewing threshold, the second interaction style is used as the target interaction style.

[0111] In the embodiment of the present application, if the interaction style configuration includes a mandatory membership activation configuration, the original portrait features are extracted from the user's video viewing history to determine whether the user meets the first portrait condition. For example, the first portrait condition is "high paying ability" and the second membership activation threshold is 0.3. If the user is determined to meet the first portrait condition based on the payment behavior characteristics and the membership activation probability is greater than or equal to 0.3, then Figure 3 The interaction style shown (ie, the first interaction style) is used as the target interaction style.

[0112] If the interaction style configuration includes a forced advertising configuration, the original portrait features are extracted from the user's video viewing history to determine whether the user meets the second portrait condition. For example, if the second portrait condition is "a user with high ad click-through rate and low ad skip rate" and the second ad viewing threshold is 0.3, if the user meets the second portrait condition based on the ad click-through rate and ad skip rate in the ad tolerance, and the ad viewing probability is greater than or equal to 0.3, then Figure 4 The shown interaction style (ie, the second interaction style) is used as the target interaction style.

[0113] It should be noted that if the interaction style configuration includes both mandatory ad viewing configuration and mandatory ad configuration, when the user meets the first profile condition and the membership activation probability is greater than or equal to the second membership activation threshold, and also meets the second profile condition and the ad viewing probability is greater than or equal to the second ad viewing threshold, then Figure 5 The interaction style shown is used as the target interaction style.

[0114] It should also be noted that if the interaction style configuration includes both forced ad viewing configuration and forced ad configuration, the user does not meet the first portrait condition, or the membership activation probability is less than the second membership activation threshold, and does not meet the second portrait condition, or the ad viewing probability is less than the second ad viewing threshold, then the target interaction style is determined based on the above-mentioned first membership activation threshold and the first ad viewing threshold.

[0115] Furthermore, if the target video does not meet the ad unlocking conditions, indicating that the target video does not support the unlocking method of watching rewarded ads, the backend can output the original interaction style and return it to the frontend. This original interaction style is used to guide the user to unlock and watch the target video by opening a membership or paying. For example, the target video can only be played after paying, or the target video is only available to members.

[0116] As described above, the video unlocking viewing method of the embodiment of the present application predicts the user's membership activation probability and advertisement viewing probability to determine the interaction style, rendering a more attractive user interaction interface, and increasing membership and incentive advertising revenue. It has the following advantages:

[0117] 1) Flexibility and diversity: Intelligent decision-making videos unlock interactive styles, eliminating the traditional fixed-style display interaction interface and can be tailored to each individual.

[0118] 2) Maximize revenue: Increase advertising revenue without affecting member revenue, and even stimulate greater member revenue, maximizing both member and advertising revenue.

[0119] 3) Dynamic Adjustment: Dynamically adjust configurations based on real-time data to maximize returns while also keeping relevant data indicators within a controllable range.

[0120] 4) User-friendly interface: Provide an interactive interface that is more acceptable to users based on their preferences, making user interaction more friendly.

[0121] The above describes a video unlocking and viewing method provided by an embodiment of the present application. The following describes a device for executing the above video unlocking and viewing method.

[0122] See also Figure 6 , Figure 6 This is a structural diagram of a video unlocking and viewing device provided in an embodiment of the present application. Figure 6 As shown, an embodiment of the present application provides a video unlocking viewing device, comprising:

[0123] The unlock configuration acquisition module 601 is used to acquire the video unlock configuration when the user's playback authentication result for the target video is not authorized. The video unlock configuration includes the advertisement unlock condition and the interaction style configuration;

[0124] Probability prediction module 602, for obtaining the user's video viewing history if the target video meets the ad unlocking condition, and predicting the user's membership activation probability and ad viewing probability based on the video viewing history;

[0125] The interaction style determination module 603 is used to determine a target interaction style that matches the membership activation probability and the advertisement viewing probability based on the interaction style configuration. The target interaction style is used to guide users to unlock and watch the target video by activating a membership or watching an incentive advertisement.

[0126] In one possible implementation, the probability prediction module 602 for predicting a user's membership activation probability and advertisement viewing probability based on video viewing history is specifically configured to:

[0127] Extract the user's original portrait features from the video viewing history; extract the first portrait features for membership activation prediction and the second portrait features for advertisement viewing prediction from the original portrait features; input the first portrait features into the first prediction model, and output the membership activation probability through the first prediction model; and input the second portrait features into the second prediction model, and output the advertisement viewing probability through the second prediction model.

[0128] In one possible implementation, the original portrait features include at least user activity, advertising tolerance, payment behavior characteristics, price sensitivity characteristics, time sensitivity, content preference characteristics, associated behavior sequence characteristics used to characterize the association between advertising viewing behavior and membership activation behavior, and economic ability characteristics.

[0129] In a possible implementation, the interaction style configuration includes a first membership activation threshold and a first advertisement viewing threshold;

[0130] The interaction style determination module 603 is configured to determine a target interaction style that matches the membership activation probability and the advertisement viewing probability based on the interaction style configuration, specifically to:

[0131] If the probability of member activation is greater than or equal to the first member activation threshold, and the probability of ad viewing is less than the first ad viewing threshold, the first interaction style used to indicate membership activation will be used as the target interaction style; if the probability of member activation is less than the member activation threshold, and the probability of ad viewing is greater than or equal to the first ad viewing threshold, the second interaction style used to indicate viewing of incentive ads will be used as the target interaction style.

[0132] In one possible implementation, the interaction style configuration further includes at least one of a mandatory membership activation configuration and a mandatory advertisement viewing configuration, the mandatory membership activation configuration includes a first portrait condition and a second membership activation threshold, the second membership activation threshold being smaller than the first membership activation threshold, and the mandatory advertisement viewing configuration includes a second portrait condition and a second advertisement viewing threshold, the second advertisement viewing threshold being smaller than the first advertisement viewing threshold;

[0133] The interaction style determination module 603 is configured to determine a target interaction style that matches the membership activation probability and the advertisement viewing probability based on the interaction style configuration, and is further configured to:

[0134] When the interaction style configuration includes a mandatory membership activation configuration, if the user meets the first portrait condition and the membership activation probability is greater than or equal to the second membership activation threshold, the first interaction style will be used as the target interaction style; when the interaction style configuration includes a mandatory advertisement viewing configuration, if the user meets the second portrait condition and the advertisement viewing probability is greater than or equal to the second advertisement viewing threshold, the second interaction style will be used as the target interaction style.

[0135] In a possible implementation, the interaction style determination module 603 is further configured to:

[0136] If the target video does not meet the ad unlocking conditions, the original interaction style is output. The original interaction style is used to guide the user to unlock and watch the target video by opening a membership or paying.

[0137] It should be noted that the detailed functions of each module in the embodiment of the present application can be found in the corresponding public part of the above-mentioned embodiment of the video unlocking and viewing method, and will not be repeated here.

[0138] An electronic device is also provided in an embodiment of the present application. Figure 7 , Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device in the embodiment of the present application may include, but is not limited to, fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Figure 7 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0139] like Figure 7 As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 701, which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 702 or programs loaded from a storage device 708 into a random access memory (RAM) 703. When the electronic device is powered on, the RAM 703 also stores various programs and data required for the operation of the electronic device. The processing device 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0140] Typically, the following devices may be connected to the I / O interface 705: an input device 706 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 707 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 708 including, for example, a memory card, a hard disk, etc.; and a communication device 709. The communication device 709 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Figure 7 The electronic device is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0141] An embodiment of the present application also provides a computer program product including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any one of the video unlocking and viewing methods provided in the embodiments of the present application.

[0142] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any one of the video unlocking and viewing methods provided in the embodiment of the present application.

[0143] It should also be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided in this application, the connection relationship between the modules indicates that there is a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines.

[0144] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course can also be implemented by special hardware including application-specific integrated circuits, special CPUs, special memories, special components, etc. In general, all functions performed by computer programs can be easily implemented with corresponding hardware, and the specific hardware structures used to implement the same function can also be diverse, such as analog circuits, digital circuits or special circuits, etc. However, for the present application, software program implementation is a better implementation method in most cases. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer's floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk or optical disk, etc., and includes a number of instructions to enable a computer device (which can be a personal computer, training equipment, or network equipment, etc.) to execute the methods described in each embodiment of the present application.

[0145] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0146] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, a computer, a training device or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website, a computer, a training device or a data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

Claims

1. A video unlocking and viewing method, characterized in that: The method comprises: If the user is not authorized to play the target video, obtain a video unlock configuration, wherein the video unlock configuration includes an advertisement unlock condition and an interaction style configuration; If the target video meets the ad unlocking condition, obtain the user's video viewing history, and predict the user's membership activation probability and ad viewing probability based on the video viewing history; A target interaction style that matches the membership activation probability and the advertisement viewing probability is determined based on the interaction style configuration, and the target interaction style is used to guide the user to unlock and watch the target video by activating a membership or watching an incentive advertisement.

2. The video unlocking and viewing method according to claim 1, characterized in that: The predicting of the user's membership activation probability and advertisement viewing probability based on the video viewing history includes: Extracting original user portrait features from the video viewing record; Extracting a first portrait feature for member activation prediction and a second portrait feature for advertisement viewing prediction from the original portrait features respectively; The first portrait feature is input into a first prediction model, and the membership activation probability is output through the first prediction model; and the second portrait feature is input into a second prediction model, and the advertisement viewing probability is output through the second prediction model.

3. The video unlocking and viewing method according to claim 2, characterized in that: The original portrait features include at least one of the following: user activity, advertising tolerance, payment behavior characteristics, price sensitivity characteristics, time sensitivity, content preference characteristics, associated behavior sequence characteristics used to characterize the association relationship between advertising viewing behavior and membership activation behavior, and economic ability characteristics.

4. The video unlocking and viewing method according to claim 1, characterized in that: The interaction style configuration includes a first membership activation threshold and a first advertisement viewing threshold; The determining, based on the interaction pattern configuration, a target interaction pattern that matches the membership activation probability and the advertisement viewing probability includes: If the membership activation probability is greater than or equal to the first membership activation threshold, and the advertisement viewing probability is less than the first advertisement viewing threshold, the first interaction pattern for indicating membership activation is used as the target interaction pattern; If the membership activation probability is less than the membership activation threshold and the advertisement viewing probability is greater than or equal to the first advertisement viewing threshold, the second interaction pattern for indicating viewing of the incentive advertisement is used as the target interaction pattern.

5. The video unlocking and viewing method according to claim 3, characterized in that: The interaction style configuration further includes at least one of a mandatory membership activation configuration and a mandatory advertisement viewing configuration, wherein the mandatory membership activation configuration includes a first portrait condition and a second membership activation threshold, wherein the second membership activation threshold is smaller than the first membership activation threshold, and the mandatory advertisement viewing configuration includes a second portrait condition and a second advertisement viewing threshold, wherein the second advertisement viewing threshold is smaller than the first advertisement viewing threshold; The determining of a target interaction pattern that matches the membership activation probability and the advertisement viewing probability based on the interaction pattern configuration further includes: In a case where the mandatory membership activation configuration is included in the interaction style configuration, if the user meets the first profile condition and the membership activation probability is greater than or equal to the second membership activation threshold, the first interaction style is used as the target interaction style; In a case where the interaction style configuration includes the forced advertisement viewing configuration, if the user meets the second portrait condition and the advertisement viewing probability is greater than or equal to the second advertisement viewing threshold, the second interaction style is used as the target interaction style.

6. The video unlocking and viewing method according to claim 1, characterized in that: The method further comprises: If the target video does not meet the advertisement unlocking condition, an original interaction style is output, where the original interaction style is used to guide the user to unlock and watch the target video by becoming a member or paying a fee.

7. A video unlocking and viewing device, characterized in that: The device comprises: An unlock configuration acquisition module, configured to acquire a video unlock configuration when the user's playback authentication result for the target video is unauthorized, wherein the video unlock configuration includes an advertisement unlock condition and an interaction style configuration; A probability prediction module is used to obtain the user's video viewing history if the target video meets the advertisement unlocking condition, and predict the user's membership activation probability and advertisement viewing probability based on the video viewing history; An interaction style determination module is used to determine a target interaction style that matches the membership activation probability and the advertisement viewing probability based on the interaction style configuration, and the target interaction style is used to guide users to unlock and watch the target video by activating a membership or watching an incentive advertisement.

8. A computer program product, characterized in that The device comprises computer-readable instructions, which, when executed on an electronic device, enable the electronic device to implement the video unlocking and viewing method according to any one of claims 1 to 6.

9. An electronic device, characterized in that: comprising at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is configured to execute the computer program so that the electronic device can implement the video unlocking and viewing method according to any one of claims 1 to 6.

10. A computer storage medium, characterized in that The storage medium carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the video unlocking and viewing method according to any one of claims 1 to 6.

Images