Page jumping method and device, equipment, medium and product

Abstract

The invention discloses a page jumping method and device, equipment, a medium and a product, and relates to the technical field of application jumping. The method comprises the following steps: displaying a content recommendation page provided by a content recommendation application, wherein the content recommendation page comprises a jump link for jumping to a live broadcast application; equipment information of the terminal is sent to a server of the live broadcast application in response to a trigger request of the jump link, the server is used for generating live broadcast recommendation data based on a user portrait matched with the equipment information, and the live broadcast recommendation data comprises a live broadcast room identifier of a first live broadcast room recommended to the terminal; receiving live broadcast recommendation data sent by the server of the live broadcast application; and displaying a live broadcast room page corresponding to the first live broadcast room based on a live broadcast room identifier indicated by the live broadcast recommendation data. According to the method, the personalized touch in the cross-application jump process can be realized, so that the cross-application jump result can better meet the live / new pull requirement of the live broadcast service scene, and the retention rate and conversion effect of the user after the cross-application jump can be improved.

Description

Technical Field

[0001] This application relates to the technical field of application jump, and in particular to a page jump method, device, equipment, medium and product. Background Art

[0002] Pulling up the application interface across applications is the key to realizing page jump in the advertising drainage scenario.

[0003] In the related art, the application page of the target application is usually pulled up through a deep link (DeepLink). Among them, the application page pulled up and displayed is the specified page corresponding to the DeepLink link parameter predefined in the configuration file.

[0004] However, due to the limited information that the DeepLink link parameter can carry, it cannot meet the requirements of complex business scenarios. Summary of the Invention

[0005] Embodiments of this application provide a page jump method, device, equipment, medium and product. The technical solution is as follows:

[0006] On the one hand, a page jump method is provided. The method is executed by a terminal, and the method includes:

[0007] Display a content recommendation page provided by a content recommendation application. The content recommendation page includes a jump link to a live broadcast application;

[0008] In response to a trigger request for the jump link, send device information of the terminal to the server of the live broadcast application. The server is used to generate live broadcast recommendation data based on a user portrait matching the device information. The live broadcast recommendation data includes a live broadcast room identifier of a first live broadcast room recommended to the terminal;

[0009] Receive the live broadcast recommendation data sent by the server of the live broadcast application;

[0010] Based on the live broadcast room identifier indicated by the live broadcast recommendation data, display the live broadcast room page corresponding to the first live broadcast room.

[0011] On the other hand, a page jump device is provided. The device is configured in a terminal, and the device includes:

[0012] A display module, configured to display a content recommendation page provided by a content recommendation application. The content recommendation page includes a jump link to a live broadcast application;

[0013] A sending module, configured to send device information of the terminal to a server of the live streaming application in response to a trigger request for the jump link, where the server is configured to generate live streaming recommendation data based on a user profile matching the device information, and the live streaming recommendation data includes a live streaming room identifier of a first live streaming room recommended to the terminal;

[0014] A receiving module, configured to receive the live streaming recommendation data sent by the server of the live streaming application;

[0015] The display module is further configured to display a live streaming room page corresponding to the first live streaming room based on the live streaming room identifier indicated by the live streaming recommendation data.

[0016] In some alternative embodiments, the apparatus further includes:

[0017] A starting module, configured to start the live streaming application in response to a trigger request for the jump link;

[0018] An obtaining module, configured to obtain the device information of the terminal through the live streaming application;

[0019] The sending module is further configured to send the device information to the server of the live streaming application through the live streaming application.

[0020] In some alternative embodiments, the obtaining module is further configured to obtain a platform identifier of the content recommendation application when the terminal meets a user acquisition requirement, where the platform identifier is used to identify an advertising platform corresponding to the content recommendation application;

[0021] The sending module is further configured to send the device information and the platform identifier to the server of the live streaming application through the live streaming application;

[0022] Wherein, the server is configured to determine the advertising platform based on the platform identifier, and obtain a user profile matching the device information from the advertising platform.

[0023] In some alternative embodiments, the user acquisition requirement includes at least one of the following:

[0024] The live streaming application in the terminal is not logged in;

[0025] There is no matching second account in the live streaming application for the registration information of a first account logged in to the content recommendation application in the terminal;

[0026] There is no matching second account in the live streaming application for the identification number associated with the terminal.

[0027] In some alternative embodiments, the server is configured to determine a second account logged in by the terminal in the live streaming application based on the device information; and obtain the user profile corresponding to the second account.

[0028] In some alternative embodiments, the server is configured to input the device information into a pre-trained profile generation model to obtain the user profile, where the device information includes at least one of hardware information, network information, software information, and identification information;

[0029] wherein the pre-trained profile generation model is configured to generate the user profile matching the device information from at least one value dimension according to the device information;

[0030] The at least one value dimension includes at least one of a consumption ability dimension associated with the hardware information, a technology preference dimension associated with the hardware information, a scenario-based content dimension associated with the network information, an interest graph dimension associated with the software information, and a cross-platform profile dimension associated with the identification information.

[0031] In some alternative embodiments, the server is configured to obtain candidate device information corresponding to multiple candidate accounts respectively, where the candidate accounts are user accounts in the live streaming application that meet a preset condition, and the candidate accounts correspond to candidate user profiles; compare the candidate device information with the device information, and determine the target device information with the highest similarity to the device information from the candidate device information; and use the candidate user profile of the candidate account corresponding to the target device information as the user profile corresponding to the terminal.

[0032] In some alternative embodiments, the live streaming recommendation data further includes home page content data matching the user profile, and the home page content data is used to recommend multiple candidate live streaming rooms matching the user profile to the terminal;

[0033] The display module is further configured to, in response to receiving an exit operation for the first live streaming room, display the application home page of the live streaming application based on the home page content data, where the application home page includes live streaming room entrances of the multiple candidate live streaming rooms.

[0034] In some alternative embodiments, the display module is further configured to, in response to receiving a selection operation for a second live streaming room among the multiple candidate live streaming rooms, jump to and display the live streaming room page corresponding to the second live streaming room;

[0035] The sending module is further configured to send the reach information corresponding to the second live broadcast room to the server, where the reach information includes the terminal identifier corresponding to the terminal and the live broadcast room identifier corresponding to the second live broadcast room, and the server is configured to update the user profile corresponding to the terminal based on the reach information.

[0036] In some alternative embodiments, the receiving module is further configured to, in response to receiving an interaction operation within the live broadcast room page of the first live broadcast room, generate the reach information corresponding to the first live broadcast room based on the interaction operation, where the reach information includes the terminal identifier corresponding to the terminal, the live broadcast room identifier corresponding to the first live broadcast room, and the operation information corresponding to the interaction operation;

[0037] The sending module is further configured to send the reach information corresponding to the first live broadcast room to the server, and the server is configured to update the user profile corresponding to the terminal based on the reach information.

[0038] In some alternative embodiments, the jump link is implemented as a deep link, and a protocol and an address that support the deep link jump are configured in the configuration file of the live broadcast application.

[0039] On the other hand, a computer device is provided, where the computer device includes a processor and a memory, and at least one instruction, at least one program, a code set, or an instruction set is stored in the memory, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the page jump method as described in any one of the above embodiments of the present application.

[0040] On the other hand, a computer-readable storage medium is provided, where at least one instruction, at least one program, a code set, or an instruction set is stored in the storage medium, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the page jump method as described in any one of the above embodiments of the present application.

[0041] On the other hand, a computer program product or a computer program is provided, where the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the page jump method as described in any one of the above embodiments.

[0042] The technical solution provided by the present application at least includes the following beneficial effects:

[0043] In the process of implementing cross - application jump, when the jump link to the live application is triggered on the content recommendation page provided by the content recommendation application, the terminal sends the device information of the terminal to the server of the live application, so that the live application server can recommend the first live room to the terminal based on the user portrait matching the device information, and after successfully jumping to the live application, directly enter the live room page corresponding to the first live room, thereby realizing personalized reach in the cross - application jump process, enabling the cross - application jump result to better meet the requirements of activating / pulling in new users in the live business scenario, and improving the retention rate and conversion effect of users after cross - application jump. Brief Description of the Drawings

[0044] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following - described drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0045] Figure 1 is the structural block diagram of a computer system provided by an exemplary embodiment of the present application;

[0046] Figure 2 is the flowchart of a page jump method provided by an exemplary embodiment of the present application;

[0047] Figure 3 is the interface schematic diagram of a page jump provided by an exemplary embodiment of the present application;

[0048] Figure 4 is the flowchart of a page jump method provided by an exemplary embodiment of the present application;

[0049] Figure 5 is the flowchart of a page jump method provided by an exemplary embodiment of the present application;

[0050] Figure 6 is the interface schematic diagram of a page jump provided by an exemplary embodiment of the present application;

[0051] Figure 7 is the data - processing flowchart of the application - side corresponding to the content recommendation application provided by an exemplary embodiment of the present application;

[0052] Figure 8 is the data - processing flowchart of the application - side corresponding to the live application provided by an exemplary embodiment of the present application;

[0053] Figure 9 is the structural block diagram of a page jump device provided by an exemplary embodiment of the present application;

[0054] Figure 10 It is a block diagram of a page jump device provided by an exemplary embodiment of the present application;

[0055] Figure 11 It is a block diagram of a terminal provided by an exemplary embodiment of the present application. Detailed implementation manners

[0056] To make the objectives, technical solutions and advantages of the present application clearer, the following will further describe the embodiments of the present application in detail with reference to the accompanying drawings. Obviously, the described embodiments are some but not all of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the scope of protection of the present application.

[0057] In the present application, terms such as "first" and "second" are used to distinguish identical or similar items with basically the same functions and effects. It should be understood that there is no logical or chronological dependency between "first" and "second", nor are the quantity and execution order limited.

[0058] First, a brief introduction is made to the nouns involved in the embodiments of the present application.

[0059] DeepLink: It is a technology that allows users to directly jump to the internal pages of mobile applications or web applications through external links.

[0060] User profile: It is a virtual character model constructed based on multi-dimensional data such as users' behavioral data, preference information, and demographic characteristics. By analyzing information such as users' age, region, consumption habits, and hobbies, it can accurately understand users' needs, realize personalized recommendations, precision marketing, and product optimization, thereby improving the user experience and business conversion rate.

[0061] Figure 1 It shows a block diagram of a computer system provided by an exemplary embodiment of the present application. The computer system 100 includes: a terminal 120 and a server 140.

[0062] The terminal 120 installs and runs an application program. The application program can be any one of a game application program, a video application program, an e-commerce application program, a social application program, an advertising application program, a music application program, etc.

[0063] The device types of the terminal 120 include at least one of a game console, a desktop computer, a smart phone, a tablet computer, an e-book reader, a Moving Picture Experts Group Audio Layer III (MP3) player, a Moving Picture Experts Group Audio Layer IV (MP4) player, and a laptop computer. In the following embodiments, the device is taken as a desktop computer for illustration.

[0064] The terminal 120 is connected to the server 140 through a wireless network or a wired network.

[0065] Those skilled in the art can know that the number of the above devices can be more or less. For example, the above devices can be only one, or there can be dozens or hundreds of the above devices, or even more. The embodiments of the present application do not limit the number and types of the devices.

[0066] The server 140 includes at least one of a server, multiple servers, a cloud computing platform, and a virtualization center. The server 140 is used to provide background services for the application programs running on the terminal 120. Optionally, the server 140 undertakes the main computing work, and the terminal 120 undertakes the secondary computing work; or, the server 140 undertakes the secondary computing work, and the terminal 120 undertakes the main computing work; or, a distributed computing architecture is adopted between the server 140 and the terminal 120 for collaborative computing.

[0067] It should be noted that the above server 140 can be implemented as a physical server or as a cloud server in the cloud. Among them, cloud technology refers to a hosting technology that unifies a series of resources such as hardware, software, and network within a wide area network or a local area network to achieve data computing, storage, processing, and sharing. Cloud technology is the general term for network technology, information technology, integration technology, management platform technology, application technology, etc. based on the cloud computing business model, which can form a resource pool, be used on demand, and be flexible and convenient. In some embodiments, the above server 140 can also be implemented as a node in a blockchain system.

[0068] In an embodiment of the present application, a content recommendation application and a live broadcast application are both installed in the terminal 120. During the process of the terminal 120 displaying the content recommendation page provided by the content recommendation application, when a trigger request is received for the jump link in the content recommendation page, the terminal 120 sends the device information of the terminal 120 to the server 140 of the live broadcast application. The server 140 determines a matching user profile based on the device information of the terminal 120, and generates corresponding live broadcast recommendation data according to the user profile. The live broadcast recommendation data includes the live broadcast room identifier of the first live broadcast room. The server 140 sends the live broadcast recommendation data to the terminal 120, and the terminal 120 displays the live broadcast room page corresponding to the first live broadcast room according to the live broadcast room identifier indicated by the live broadcast recommendation data.

[0069] Combined with the above noun introduction and application scenario, the page jump method provided by the present application is described. Taking the example that this method is executed by the terminal, as Figure 2 shown, this method includes the following steps 210 to 240.

[0070] Step 210, display the content recommendation page provided by the content recommendation application.

[0071] In an embodiment of the present application, a content recommendation application runs in the terminal. Among them, the content recommendation application is an application program with content recommendation functions. In one example, the content recommendation function is implemented as an advertising function. It should be noted that the content recommendation function can be implemented as the main function of the content recommendation application or as an auxiliary function of the content recommendation application, that is, the content recommendation application includes application programs with content recommendation functions. For example, video application programs, e-book application programs, social application programs, e-commerce application programs, game application programs, etc. with content recommendation functions are not limited here.

[0072] Schematically, the content recommendation page provided by the content recommendation application includes a jump link to the live broadcast application, and this jump link is used to reach the application page of the live broadcast application. Optionally, the above jump link can be implemented as at least one of DeepLink, App Linking, Universal Links for IOS, and App Links for Android, which is not limited here.

[0073] In some embodiments, the content recommendation page includes recommendation content for the live broadcast application. Optionally, the above recommendation content includes at least one of picture content, text content, video content, and voice content.

[0074] In some embodiments, the above-mentioned jump link is set in the recommended content for recommending the live application on the content recommendation page. Optionally, the above-mentioned jump link can be implemented as a visual link, for example, a hyperlink; optionally, the above-mentioned jump link can also be implemented as a non-visual link, for example, configured in a jump control, which is not limited herein.

[0075] Step 220, in response to a trigger request for the jump link, send the device information of the terminal to the server of the live application.

[0076] In the embodiments of the present application, a live application is also installed in the terminal, and the live application is an application program capable of implementing the live function. It should be noted that the live function can be implemented as the main function of the live application or as an auxiliary function of the live application, that is, the live application includes application programs with live functions, such as video application programs, e-book application programs, social application programs, e-commerce application programs, game application programs, etc. with live functions, which are not limited herein.

[0077] In some embodiments, when the jump link is implemented as a visual link, in response to a trigger operation received by the jump link, it is determined that a trigger request for the jump link is received.

[0078] In other embodiments, when the jump link is implemented as a non-visual link, in response to a trigger operation received by the trigger medium corresponding to the jump link, it is determined that a trigger request for the jump link is received. In one example, when the above-mentioned trigger medium is implemented as a trigger control, in response to the trigger control receiving a trigger operation, it is determined that a trigger request for the jump link is received. In another example, when the above-mentioned trigger medium is implemented as a gesture operation, in response to the terminal detecting a preset gesture associated with the jump link, it is determined that a trigger request for the jump link is received. For example, when the terminal detects a shaking gesture, the jump link is triggered to jump to the live application.

[0079] Schematically, the device information of the terminal refers to attributes and / or parameters related to the device. Optionally, the device information of the terminal includes at least one of the following: hardware information, such as device model, operating system version, screen resolution, memory capacity, etc.; network information, such as network type, Internet Protocol (IP) address, network signal strength, etc.; software information, such as device language, time zone information, installed application list, etc.; identification information, such as device unique identifier (International Mobile Equipment Identity (IMEI), Identifier for Advertisers), identification number (mobile phone number), etc.

[0080] In some embodiments, when the content recommendation application has the permission to establish a communication connection with the server of the live broadcast application, in response to a trigger request for a jump link, the content recommendation application obtains the device information of the terminal, and the content recommendation application sends the device information of the terminal to the server of the live broadcast application. For example, the content recommendation application and the live broadcast application are different application programs provided by the same enterprise. Alternatively, in response to a trigger request for a jump link, the content recommendation application obtains the device information of the terminal, and the content recommendation application sends the device information to the live broadcast application through the jump link, and the live broadcast application sends the device information obtained through the jump link to the server of the live broadcast application.

[0081] In other embodiments, when the content recommendation application does not have the permission to establish a communication connection with the server of the live broadcast application, in response to a trigger request for a jump link, the live broadcast application is started, the live broadcast application obtains the device information of the terminal, and the live broadcast application sends the device information to the server of the live broadcast application.

[0082] In the embodiments of the present application, the server of the live broadcast application is used to generate live broadcast recommendation data based on a user profile matching the device information. The live broadcast recommendation data includes a live broadcast room identifier of a first live broadcast room recommended to the terminal, where the live broadcast room identifier is used to uniquely represent the first live broadcast room.

[0083] Optionally, the determination method of the user profile matching the device information is implemented as at least one of the following:

[0084] First, the server determines a second account logged in to the terminal in the live broadcast application based on the device information, and obtains the user profile corresponding to the second account.

[0085] Schematically, a mapping relationship between the device information and the second account is stored in the server. In response to the server receiving the device information, the corresponding second account is found according to the above mapping relationship, and the user profile corresponding to the second account is obtained.

[0086] In one example, the device information includes an identification number (mobile phone number) of the terminal, and the server obtains the user profile corresponding to the second account by querying the second account registered corresponding to the identification number.

[0087] In another example, the device information includes a unique device identifier of the terminal, and the server queries at least one second account logged in on the device according to the unique device identifier to obtain the user profile corresponding to the second account. When the server queries multiple second accounts logged in on the device, optionally, the user profile corresponding to the second account that was most recently logged in is selected, or the user profile of the second account with the longest historical login duration on the device is selected, or the user profile corresponding to the second account is randomly selected.

[0088] Second, the server generates a matching user profile based on device information.

[0089] Schematically, a pre-trained profile generation model is set in the server. The profile generation model is used to generate a matching user profile according to the input device information, that is, the server inputs the device information into the pre-trained profile generation model to obtain the user profile.

[0090] Optionally, the profile generation model can generate a user profile from at least one value dimension reflected by the device information. That is, the pre-trained profile generation model is used to generate a user profile matching the device information from at least one value dimension.

[0091] Optionally, the value dimensions reflected by the above device information include at least one of the following:

[0092] · Consumption ability dimension or technology preference dimension associated with hardware information: For example, the device signal is mapped to the price range. Users of flagship models show high-net-worth characteristics, and users of mid-range models are more concerned about cost performance. Another example is that the screen resolution is mapped to the visual experience. Users with a high screen resolution have a higher click-through rate on high-definition live rooms. For example, the memory capacity is mapped to the usage behavior. The higher the memory capacity of the user's device, the higher the average daily duration of the device, and it can support complex interactive live rooms (such as Augmented Reality (AR) makeup try-on).

[0093] · Scenario-based content dimension associated with network information: For example, for 5G / Wi-Fi6 devices, 4K ultra-high-definition and multi-camera live broadcasts can be preferentially recommended. Another example is that for devices with mobile network fluctuations, live broadcast rooms with short, flat, and fast content (such as 30-second product explanations) can be preferentially recommended. For example, live broadcast rooms around the geographical location corresponding to the IP address are preferentially recommended.

[0094] · Interest graph dimension associated with software information: For example, clustering analysis is performed on the installed applications in the device information to determine the interest degree of the end user in different classified contents. Another example is to match live broadcast rooms in the corresponding language or live broadcast time according to the device language or time zone information.

[0095] · Cross-platform profile dimension associated with identification information: For example, the click data of the content recommendation application is fed back to the profile generation model. Another example is to establish a social relationship chain through the identification number and generate a user profile based on the social relationship chain.

[0096] Optionally, the above-mentioned pre-trained portrait generation model can be implemented by neural network models such as Convolutional Neural Networks (CNN), Feedforward Neural Network (FNN), Residual Network (ResNet), Transformer, Graph Neural Network (GNN), Graph Convolutional Network (GCN), etc., which are not specifically limited herein.

[0097] In some embodiments, the training process of the portrait generation model is implemented as follows: obtaining a sample pair formed by sample device information and a sample user portrait, inputting the sample device information into the portrait generation model to be trained to obtain a predicted user portrait, determining a first loss value between the predicted user portrait and the sample user portrait through a first loss function, and iteratively adjusting the model parameters of the portrait generation model to be trained according to the first loss value until convergence, thereby obtaining the portrait generation model.

[0098] Optionally, the above-mentioned first loss function can be implemented as at least one of a Cross-Entropy Loss function, a Mean Squared Error Loss (MSE) function, a logarithmic loss function, a Least Absolute Deviations Loss (L1 Loss) function, etc., which are not limited herein.

[0099] In some embodiments, before the device information is input into the pre-trained portrait generation model, data preprocessing is first performed to obtain preprocessed device information, and the preprocessed device information is input into the pre-trained portrait generation model to obtain a matching user portrait.

[0100] Optionally, the above-mentioned data preprocessing includes at least one of data cleaning, feature engineering, etc.

[0101] Data cleaning is the process of removing or correcting errors, duplicates, and missing values in data. Among them, removing duplicate values is implemented by checking whether there are duplicate records in the dataset and deleting the duplicate data; correcting incorrect data is implemented by identifying and correcting errors or outliers in the data. For example, correcting incorrectly formatted or unreasonable data points (unreasonable maximum values, minimum values, etc.); missing values are a common problem in datasets. Ways to handle missing values include deleting records containing missing values (suitable for cases with fewer missing values), filling in missing values (e.g., using the mean, median, mode, or filling by interpolation methods), and using models to predict missing values (e.g., K-nearest neighbor algorithm, regression model, etc.).

[0102] Feature engineering is the process of selecting, constructing, and transforming the features of data. Optionally, feature engineering includes at least one of feature preprocessing, feature extraction, feature selection, feature construction, etc. Feature preprocessing includes operations such as data normalization, data discretization, and data encoding.

[0103] Data normalization is used to indicate that the data is scaled to a specified interval, for example, [0, 1] or [-1, 1]. The purpose of data normalization is to accelerate the speed of gradient descent and solve quickly.

[0104] Data discretization refers to the process of dividing continuous numerical data into a finite number of intervals or categories, thereby converting continuous variables into discrete variables. The purpose of data discretization is to increase the nonlinearity of the model and improve the generalization ability of the model. Optionally, data discretization methods include equal-interval discretization, equal-frequency discretization, clustering-based discretization, information-theory-based discretization, etc.

[0105] Data encoding refers to the process of converting data from one format or representation to another. The purpose of data encoding is to convert non-numerical data (such as categorical variables, text data) into numerical data so that it can be processed by machine learning algorithms. Optionally, data encoding methods include one-hot encoding, label encoding, target encoding, etc.

[0106] Feature extraction is the process of extracting useful information from raw data, which is usually used to reduce the data dimension or transform the data format. Optionally, feature extraction can be performed through Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), Autoencoder, Word Embeddings extraction, Term Frequency-Inverse Document Frequency (TF-IDF) vector extraction, etc.

[0107] Thirdly, the server determines, from multiple candidate accounts in the live application, a candidate account whose candidate device information has a high similarity to the device information of the terminal, and uses the user profile corresponding to the candidate account as the user profile corresponding to the terminal.

[0108] Schematically, the server obtains the candidate device information corresponding to each of the multiple candidate accounts. The candidate accounts are user accounts in the live application that meet a preset condition, and each candidate account corresponds to a candidate user profile. The server compares the candidate device information with the device information, and determines the target device information with the highest similarity to the device information from the candidate device information. The server uses the candidate user profile of the candidate account corresponding to the target device information as the user profile corresponding to the terminal.

[0109] Optionally, the preset condition corresponding to the above candidate account can be implemented as at least one of the following:

[0110] · A user account whose account activity reaches a preset activity threshold;

[0111] · A user account whose account level reaches a preset level threshold;

[0112] · A user account whose account weight ranks in the top preset percentage within the live application;

[0113] · A user account that has a friendship relationship with a second account logged in to the live application of the terminal.

[0114] In some embodiments, when screening candidate accounts, multiple target device information can also be determined according to the similarity between the candidate device information and the device information. The candidate user profiles of the candidate accounts corresponding to the multiple target device information are fused, and the fused user profile obtained by the fusion is used as the user profile corresponding to the terminal.

[0115] Schematically, after the server obtains the user profile that matches the device information, it determines a first live room from the live rooms that are currently in the live state according to the user profile, and generates live recommendation data according to the live room identifier of the first live room.

[0116] In some embodiments, a live room pool is maintained in the server. The live room pool stores the live room identifiers of the live rooms that are currently in the live broadcast state. That is, when there is a newly launched live room, the live room identifier of the newly launched live room is stored in the live room pool. When there is a live room that has newly ended the broadcast, the live room identifier of the live room that has newly ended the broadcast is deleted from the live room pool.

[0117] Schematically, the server queries from the live room pool to obtain at least one first live room that matches the user profile. In some embodiments, in order to improve the screening and matching efficiency of the live rooms, the live broadcast types that the user is interested in are determined according to the user profile, and multiple live rooms that match the live broadcast types are obtained from the live room pool. The live room information of the multiple live rooms and the user profile are input into a pre-trained two-tower model, and the first live room that best matches the user profile is output through the two-tower model.

[0118] Among them, the above-mentioned pre-trained two-tower model is a pre-trained machine learning model. The two-tower model includes a live room side feature tower and a user side feature tower. The live room feature representation is obtained by extracting the live room information, the user feature representation is obtained by extracting the user profile, and the first live room is determined from multiple live rooms through the vector similarity between the live room feature representation and the user feature representation.

[0119] Optionally, the live room information includes the live room title, the live room barrage, the basic information of the anchor, the live room category information, the historical live broadcast information of the anchor, etc.

[0120] Optionally, the above-mentioned pre-trained two-tower model can be implemented by neural network models such as convolutional neural networks, feedforward neural networks, residual networks, transformers, graph neural networks, graph convolutional networks, etc., and no specific limitation is made here.

[0121] In some embodiments, the training process of the two-tower model is implemented as follows: obtaining a sample pair formed by the sample live room information of the sample live room and the sample user profile. The sample pair corresponds to annotation information, and the annotation information indicates the degree of interest of the sample user corresponding to the sample user profile in the sample live room. The sample live room information and the sample user profile are input into the two-tower model to be trained to obtain a predicted degree of interest. The second loss value between the predicted degree of interest and the annotation information is determined through a second loss function. The model parameters of the two-tower model to be trained are iteratively adjusted according to the second loss value until convergence, and the two-tower model is obtained.

[0122] Optionally, the above-mentioned second loss function can be implemented as at least one of a cross-entropy loss function, a mean squared error loss function, a logarithmic loss function, a least absolute deviation loss function, etc., and no limitation is made here.

[0123] In some embodiments, in response to a trigger request for a jump link, the terminal detects whether the live application requested to jump by the jump link has been installed. If it has been installed, step 220 is executed. If not, the terminal displays a jump failure, or the terminal displays a download page for the live application, which can be implemented as a page provided by the application store in the terminal or as a page provided by the browser.

[0124] In some embodiments, in response to the terminal downloading and installing the live application, the terminal automatically launches the live application and sends device information to the server of the live application.

[0125] Step 230, receive the live recommendation data sent by the server of the live application.

[0126] In the embodiments of the present application, the live recommendation data includes the live room identifier of the first live room.

[0127] Optionally, the live recommendation data further includes buffer data corresponding to the first live room. The terminal can quickly build and load the live room page of the first live room through the buffer data. Optionally, the above buffer data includes live room title information, live room introduction information, live room cover, live streaming media data corresponding to the current moment, etc.

[0128] Optionally, the data transmission format adopted by the live recommendation data includes at least one of the following: JavaScript Object Notation (JSON), Extensible Markup Language (XML), Protocol Buffers, etc., which are not limited herein.

[0129] Optionally, the data transmission method adopted by the live recommendation data includes at least one of the following:

[0130] · Data transmission is performed through a HyperText Transfer Protocol (HTTP) / HyperText Transfer Protocol Secure (HTTPS) request;

[0131] · Data transmission is performed through a WebSocket;

[0132] · Data transmission is performed through a Long Polling technology.

[0133] Step 240, based on the live room identifier indicated by the live recommendation data, display the live room page corresponding to the first live room.

[0134] Schematically, after receiving the live recommendation data, the terminal parses the live recommendation data to obtain the live room identifier of the first live room.

[0135] After the terminal obtains the live room identifier of the first live room, it constructs a live room page according to the live room identifier of the first live room. Schematically, the terminal sends a live data acquisition request to the server. The live data acquisition request includes the live room identifier. The server sends the live streaming media data of the first live room to the terminal according to the live data acquisition request. The terminal renders and displays the live room page through the live streaming media data.

[0136] In one example, the terminal sends an HTTP GET request to the server. The HTTP GET request includes the live room identifier of the first live room. The HTTP GET request is sent according to the live request address in the server. For example, the live request address is "https: / / api.example.com / live / {live_id}", where "{live_id}" is the live room identifier of the first live room. After receiving the HTTP GET request, the server returns the live data of the first live room according to the live room identifier of the first live room. The live data includes the live stream address. After receiving the live data, the terminal loads the live video stream of the first live room according to the live stream address indicated in the live data, embeds the live video stream into the live room page, and at the same time renders and displays the live room information associated with the first live room in the live room page, such as the anchor information, the interactive area information, the live room title, etc.

[0137] In some embodiments, the terminal records and reports the reach information generated during the display process of the live room page of the first live room. Schematically, in response to receiving an interaction operation within the live room page of the first live room, a reach information corresponding to the first live room is generated based on the interaction operation. The reach information includes the terminal identifier corresponding to the terminal, the live room identifier corresponding to the first live room, and the operation information corresponding to the interaction operation. The reach information corresponding to the first live room is sent to the server, and the server is used to update the user profile corresponding to the terminal based on the reach information.

[0138] In some embodiments, after the server updates the user profile corresponding to the terminal according to the reach information, when jumping to the live application through the content recommendation application next time, a matching live room is obtained according to the updated user profile.

[0139] Such as Figure 3As shown, it shows a schematic diagram of the interface for page jump provided by an exemplary embodiment of the present application. In the content recommendation page 310 provided by the content recommendation application, a jump control 311 for the live broadcast application is displayed. When the jump control 311 receives a trigger operation, the terminal sends the device information of the terminal to the server of the live broadcast application. The server returns the live broadcast room identifier of the first live broadcast room according to the user portrait matching the device information. The terminal loads the live video stream from the server through the live broadcast room identifier and renders the live broadcast room page 320 corresponding to the first live broadcast room.

[0140] In summary, in the process of implementing cross-application jump, when the jump link to the live broadcast application in the content recommendation page provided by the content recommendation application is triggered, the terminal sends the device information of the terminal to the server of the live broadcast application, so that the live broadcast application server can recommend the first live broadcast room to the terminal through the user portrait matching the device information, and after successfully jumping to the live broadcast application, directly enter the live broadcast room page corresponding to the first live broadcast room, thereby realizing personalized reach in the process of cross-application jump, making the cross-application jump result better meet the requirements of pulling live / new users in the live broadcast business scenario, and improving the retention rate and conversion effect of users after cross-application jump.

[0141] In some optional embodiments, when the device information is used to directly retrieve the user portrait of the corresponding account in the server of the live broadcast application, there are some situations where the device information is not recorded in the server of the live broadcast application. For example, the live broadcast application in the terminal is not logged in to an account, or the user of the terminal has not registered the live broadcast application, etc. In these cases, the live broadcast application needs to acquire new users. Schematically, please refer to Figure 4 , which shows a flowchart of the page jump method provided by an exemplary embodiment of the present application. The method includes steps 410 to 460.

[0142] Step 410, display the content recommendation page provided by the content recommendation application.

[0143] In the embodiment of the present application, a content recommendation application runs on the terminal, where the content recommendation application is an application program with content recommendation function. It should be noted that the content recommendation function can be implemented as the main function of the content recommendation application, or can be implemented as the auxiliary function of the content recommendation application, that is, the content recommendation application includes an application program with content recommendation function, for example, a video application program, an e-book application program, a social application program, an e-commerce application program, a game application program, etc. with content recommendation function, which is not limited here.

[0144] Schematically, the content recommendation page provided by the content recommendation application includes a jump link to the live broadcast application, and this jump link is used to reach the application page of the live broadcast application. Optionally, the above-mentioned jump link can be implemented as at least one of DeepLink, App Linking, Universal Links for IOS, and App Links for Android, which is not limited herein.

[0145] In some embodiments, the above-mentioned jump link is set in the recommended content for recommending the live broadcast application on the content recommendation page. Optionally, the above-mentioned jump link can be implemented as a visual link, for example, a hyperlink; optionally, the above-mentioned jump link can also be implemented as a non-visual link, for example, configured in a jump control, which is not limited herein.

[0146] Step 420, in response to a trigger request for the jump link, start the live broadcast application.

[0147] In the embodiments of the present application, a live broadcast application is also installed in the terminal, and this live broadcast application is an application program capable of implementing the live broadcast function. It should be noted that the live broadcast function can be implemented as the main function of the live broadcast application or as an auxiliary function of the live broadcast application, that is, the live broadcast application includes application programs with the live broadcast function, such as video application programs, e-book application programs, social application programs, e-commerce application programs, game application programs, etc. with the live broadcast function, which is not limited herein.

[0148] In some embodiments, when the jump link is implemented as a visual link, in response to a trigger operation received by the jump link, it is determined that a trigger request for the jump link is received.

[0149] In other embodiments, when the jump link is implemented as a non-visual link, in response to a trigger operation received by the trigger medium corresponding to the jump link, it is determined that a trigger request for the jump link is received. In one example, when the above-mentioned trigger medium is implemented as a trigger control, in response to the trigger control receiving a trigger operation, it is determined that a trigger request for the jump link is received. In another example, when the above-mentioned trigger medium is implemented as a gesture operation, in response to the terminal detecting a preset gesture associated with the jump link, it is determined that a trigger request for the jump link is received. For example, when the terminal detects a shaking gesture, the jump link is triggered to jump to the live broadcast application.

[0150] In one example, taking the implementation of a jump link as a deep link as an example, schematically, the manifest configuration file of the live application is configured with a protocol (scheme) and an address (host) that support deep link jumps. When the jump link in the content recommendation application receives a trigger request, the content recommendation application attempts to open the corresponding live application of the jump link. In one example, the content recommendation application calls the application programming interface (Application Programming Interface, API) of the terminal operating system to open the deep link. The operating system checks whether the live application is installed to process the deep link. If it is determined that the live application is installed, the operating system starts the live application and passes the deep link to the live application. When the operating system determines that the live application is not installed, it sends a jump failure message to the content recommendation application. The content recommendation application displays a jump failure according to the jump failure message, or the content recommendation application triggers a jump link to an app store or browser to display the download page of the live application.

[0151] Step 430, obtain the device information of the terminal through the live application, and, when the terminal meets the new user acquisition requirements, obtain the platform identifier of the content recommendation application.

[0152] Schematically, the device information of the terminal refers to the attributes and / or parameters related to the device. Optionally, the device information of the terminal includes at least one of the following: hardware information, such as device model, operating system version, screen resolution, memory capacity, etc.; network information, such as network type, IP address, network signal strength, etc.; software information, such as device language, time zone information, installed application list, etc.; identification information, such as device unique identifier (IMEI, advertising identifier), identification number (mobile phone number), etc.

[0153] In some embodiments, the live application obtains the device information of the terminal through the operating system API. In one example, when the obtained device information includes the device model, the device model can be obtained by calling the corresponding API of the operating system through "String model = android.os.Build.MODEL;". In another example, when the obtained device information includes the device unique identifier, the device unique identifier can be obtained by calling the corresponding API of the operating system through "String androidId = Settings.Secure.getString(getContentResolver(), Settings.Secure.ANDROID_ID);".

[0154] In the embodiments of the present application, the device information of the terminal is reference data used by the server to obtain a matching user profile. Schematically, the server determines a second account logged in to the live application based on the device information and obtains the user profile corresponding to the second account.

[0155] Schematically, there is a mapping relationship between the device information and the second account stored in the server. In response to the server receiving the device information, the corresponding second account is found according to the above mapping relationship, and the user profile corresponding to the second account is obtained.

[0156] In one example, the device information includes the identification number (mobile phone number) of the terminal. The server obtains the user profile corresponding to the second account by querying the second account registered corresponding to the identification number.

[0157] In another example, the device information includes the unique device identifier of the terminal. The server queries at least one second account logged in on the device according to the unique device identifier to obtain the user profile corresponding to the second account. When the server queries multiple second accounts logged in on the device, optionally, select the user profile corresponding to the most recently logged-in second account, or select the user profile of the second account with the longest historical login duration on the device, or randomly select the user profile corresponding to the second account.

[0158] In some other embodiments, in some cases, the server of the live application may not be able to query the corresponding second account through the device information. Therefore, it is necessary to introduce the platform identifier of the content recommendation application to query the corresponding first account in the advertising platform to obtain the user profile. That is, when the terminal meets the new user acquisition requirements, the live application obtains the platform identifier of the content recommendation application, and this platform identifier is used to identify the advertising platform corresponding to the content recommendation application.

[0159] Optionally, the above new user acquisition requirements include at least one of the following:

[0160] · The live application in the terminal is not logged in to an account;

[0161] · There is no matching second account in the live application for the registration information of the first account logged in to the content recommendation application in the terminal. For example, the mobile phone number used to register the first account has not been registered for an account in the live application;

[0162] · There is no matching second account in the live application for the identification number associated with the terminal. For example, the mobile phone number associated with the terminal has not been registered for an account in the live application.

[0163] In some embodiments, the above platform identifier can be sent to the live application along with the trigger of the jump link; in some other embodiments, the live application obtains the platform identifier of the content recommendation application through the operating system API.

[0164] Step 440: Send device information and platform identifier to the server of the live application via the live application.

[0165] Optionally, the data transmission formats adopted by the device information and the platform identifier include at least one of the following: JSON format, XML format, Protocol Buffers format, etc., which are not limited herein.

[0166] Optionally, the data transmission methods adopted by the device information and the platform identifier include at least one of the following:

[0167] · Transmit data via HTTP / HTTPS requests;

[0168] · Transmit data via WebSocket;

[0169] · Transmit data via long polling technology.

[0170] In the embodiments of the present application, the server is used to determine the advertising platform based on the platform identifier and obtain the user profile matching the device information from the advertising platform. Schematically, after receiving the platform identifier, the server determines the advertising platform matching the platform identifier, and sends a user profile acquisition request containing the above-mentioned device information to the server corresponding to the advertising platform. After receiving the user profile acquisition request sent by the server corresponding to the live application, the server corresponding to the advertising platform queries and obtains the matching user profile through the device information.

[0171] Schematically, there is a mapping relationship between the device information and the first account of the advertising platform stored in the server corresponding to the advertising platform. In response to the server corresponding to the advertising platform receiving the device information, the corresponding first account is found according to the above mapping relationship, the user profile corresponding to the first account is obtained, and the user profile is returned to the server of the live application.

[0172] In one example, the device information includes the identification number (mobile phone number) of the terminal. The server corresponding to the advertising platform queries the first account registered corresponding to the identification number to obtain the user profile corresponding to the first account.

[0173] In another example, the device information includes the unique device identifier of the terminal. The server corresponding to the advertising platform queries at least one first account that has logged in to the content recommendation application on the device according to the unique device identifier to obtain the user profile corresponding to the first account. When the server corresponding to the advertising platform queries multiple first accounts that have logged in to the content recommendation application on the device, optionally, select the user profile corresponding to the first account that logged in most recently, or select the user profile of the first account with the longest historical login duration on the device, or randomly select the user profile corresponding to the first account.

[0174] Step 450: Receive the live broadcast recommendation data sent by the server of the live broadcast application.

[0175] In the embodiments of the present application, the live broadcast recommendation data includes the live broadcast room identifier of the first live broadcast room.

[0176] Optionally, the live broadcast recommendation data further includes the buffer data corresponding to the first live broadcast room. The terminal can quickly build and load the live broadcast room page of the first live broadcast room through the buffer data. Optionally, the above buffer data includes the live broadcast room title information, the live broadcast room introduction information, the live broadcast room cover, the live streaming media data corresponding to the current moment, etc.

[0177] Optionally, the data transmission format adopted by the live broadcast recommendation data includes at least one of the following: JSON format, XML format, Protocol Buffer format, etc., which are not limited herein.

[0178] Optionally, the data transmission method adopted by the live broadcast recommendation data includes at least one of the following:

[0179] · Transmit data through an HTTP / HTTPS request;

[0180] · Transmit data through WebSocket;

[0181] · Transmit data through the long polling technique.

[0182] Step 460: Display the live broadcast room page corresponding to the first live broadcast room based on the live broadcast room identifier indicated by the live broadcast recommendation data.

[0183] Schematically, after receiving the live broadcast recommendation data, the terminal parses the live broadcast recommendation data to obtain the live broadcast room identifier of the first live broadcast room.

[0184] When the terminal obtains the live broadcast room identifier of the first live broadcast room, it constructs a live broadcast room page according to the live broadcast room identifier of the first live broadcast room. Schematically, the terminal sends a live broadcast data acquisition request to the server. The live broadcast data acquisition request includes the live broadcast room identifier. The server sends the live streaming media data of the first live broadcast room to the terminal according to the live broadcast data acquisition request. The terminal renders and displays the live broadcast room page through the live streaming media data.

[0185] In some embodiments, the terminal will record and report the touch information generated during the display process of the live broadcast room page of the first live broadcast room. Schematically, in response to receiving an interaction operation within the live broadcast room page of the first live broadcast room, a touch information corresponding to the first live broadcast room is generated based on the interaction operation. The touch information includes the terminal identifier corresponding to the terminal, the live broadcast room identifier corresponding to the first live broadcast room, and the operation information corresponding to the interaction operation; the touch information corresponding to the first live broadcast room is sent to the server, and the server is used to update the user portrait corresponding to the terminal based on the touch information.

[0186] In some embodiments, after the server updates the user profile corresponding to the terminal according to the reach information, when jumping to the live application through the content recommendation application next time, a matching live room is obtained according to the updated user profile.

[0187] In summary, in the process of implementing cross-application jump, when the jump link to the live application is triggered on the content recommendation page provided by the content recommendation application, the terminal sends the device information of the terminal to the server of the live application, so that the live application server can recommend the first live room to the terminal through the user profile matching the device information, and after successfully jumping to the live application, directly enter the live room page corresponding to the first live room, thereby realizing personalized reach in the cross-application jump process, making the cross-application jump result better meet the pull-live / pull-new requirements of the live business scenario, and improving the retention rate and conversion effect of users after cross-application jump.

[0188] In some alternative embodiments, the live recommendation data further includes home page content data matching the user profile, and the home page content data is used to recommend multiple candidate live rooms matching the user profile to the terminal, and the terminal can achieve a secondary jump through the home page content data. Please refer to Figure 5 , which shows a flowchart of a page jump method provided by an exemplary embodiment of the present application. The method includes step 510, where step 510 is executed after step 240 or step 460.

[0189] Step 510, in response to receiving an exit operation for the first live room, display the application home page of the live application based on the home page content data.

[0190] Among them, the application home page includes live room entrances of multiple candidate live rooms.

[0191] In some embodiments, the above-mentioned multiple candidate live rooms are live rooms matched by the server according to the user profile.

[0192] Schematically, in the process of the server generating the live recommendation data, the server determines the first live room and multiple candidate live rooms from the live rooms currently in the live state according to the user profile matching the device information, generates home page content data corresponding to the multiple candidate live rooms, and generates live recommendation data according to the live room identifier of the first live room and the home page content data.

[0193] In some embodiments, a live room pool is maintained in the server. The live room pool stores the live room identifiers of the live rooms that are currently in the live broadcast state. That is, when there is a newly started live room, the live room identifier of the newly started live room is stored in the live room pool. When there is a live room that has ended the broadcast, the live room identifier of the live room that has ended the broadcast is deleted from the live room pool.

[0194] Illustratively, the server queries from the live room pool to obtain at least one first live room that matches the user profile, and multiple candidate live rooms. In some embodiments, in order to improve the screening and matching efficiency of the live rooms, the live broadcast types that the user is interested in are determined according to the user profile, multiple live rooms that match the live broadcast type are obtained from the live room pool, the live room information of the multiple live rooms and the user profile are input into a pre-trained dual tower model, and the matching degrees between the multiple live rooms and the user profile are output through the dual tower model.

[0195] Among them, the above pre-trained dual tower model is a pre-trained machine learning model. The dual tower model includes a live room side feature tower and a user side feature tower. The live room feature representation is obtained through the extraction of live room information, the user feature representation is obtained through the extraction of user information, and the vector similarity between the live room feature representation and the user feature representation is used to obtain the matching degrees between the multiple live rooms and the user profile respectively.

[0196] Optionally, the live room information includes the live room title, the live room bullet screen, the basic information of the anchor, the live room category information, the historical live broadcast information of the anchor, etc.

[0197] Optionally, the above pre-trained dual tower model can be implemented by neural network models such as convolutional neural network, feedforward neural network, residual network, transformer, graph neural network, graph convolutional network, etc., and no specific limitation is made here.

[0198] In some embodiments, the multiple live rooms are sorted according to the matching degrees between the multiple live rooms output by the dual tower model and the user profile, and a live room queue is obtained. Among them, the order of the live rooms in the live room queue is positively correlated with the matching degrees between the live rooms and the user profile.

[0199] In an example, the live room with the highest matching degree with the user profile in the live room queue is used as the first live room, and N live rooms with matching degrees lower than the first live room are determined as multiple candidate live rooms, where N is a positive integer.

[0200] In some embodiments, the multiple candidate live rooms also include the first live room. That is, after the user exits the live room page corresponding to the first live room, the live room entrance of the first live room is still included in the application home page of the live broadcast application displayed, so that after the user accidentally touches and exits the live room, the user can still quickly find the interested first live room.

[0201] In some embodiments, the home page content data corresponding to multiple candidate live rooms includes live room identifiers, live room title information, live room introduction information, host information, live room covers, home page layout positions, etc. respectively corresponding to the multiple candidate live rooms.

[0202] In some embodiments, when the home page content data includes the home page layout positions respectively corresponding to multiple candidate live rooms, the layout display priority of the multiple candidate live rooms on the application home page is positively correlated with the matching degree with the user portrait. Among them, the layout display priority includes at least one of display order, display position size, and display content amount. For example, the live room entrances of multiple candidate live rooms are displayed in sequence according to the matching degree with the user portrait; for another example, the first area of the application home page is used to display the live room entrance of the first size, and the second area of the application home page is used to display the live room entrance of the second size. Among them, the first size is greater than the second size, then the matching degree of the candidate live room displayed in the first area with the user portrait is higher than that of the candidate live room displayed in the second area.

[0203] Schematically, when the terminal receives the live broadcast recommendation data sent by the server, it parses the live broadcast recommendation data to obtain the live room identifier of the first live room and the home page content data. The terminal displays the live room page corresponding to the first live room based on the live room identifier of the first live room, and retains and caches the home page content data.

[0204] In one example, the above home page content data can be stored in the form of DeepLink information, and this DeepLink information is used to implement secondary page jumps. Schematically, in response to receiving an exit operation for the first live room, the terminal displays the application home page of the live broadcast application, and loads the live room entrances of multiple candidate live rooms through the above DeepLink information.

[0205] In some embodiments, the terminal will record and report the touch information generated during the display process of the application home page by the user. Schematically, in response to receiving a selection operation for the second live room among multiple candidate live rooms, it jumps to display the live room page corresponding to the second live room; sends the touch information corresponding to the second live room to the server, where the touch information includes the terminal identifier corresponding to the terminal and the live room identifier corresponding to the second live room, and the server is used to update the user portrait corresponding to the terminal based on the touch information.

[0206] In some embodiments, when the server updates the user portrait corresponding to the terminal according to the touch information, the next time it jumps to the live broadcast application through the content recommendation application, it obtains the matching live room according to the updated user portrait.

[0207] Such as Figure 6As shown, it shows a schematic diagram of the page jump interface provided by an exemplary embodiment of the present application. In the content recommendation page 610 provided by the content recommendation application, a jump control 611 for the live broadcast application is displayed. When the jump control 611 receives a trigger operation, the terminal sends the device information of the terminal to the server of the live broadcast application. The server returns the live broadcast room identifier of the first live broadcast room and the home page content data according to the user portrait matching the device information. The terminal loads the live video stream from the server through the live broadcast room identifier and renders the live broadcast room page 620 corresponding to the first live broadcast room. When the terminal receives an exit operation for the live broadcast room page 620, it calls the home page content data to construct and render the application home page 630.

[0208] In summary, in the process of implementing cross-application jump, when the jump link to the live broadcast application in the content recommendation page provided by the content recommendation application is triggered, the terminal sends the device information of the terminal to the server of the live broadcast application, enabling the live broadcast application server to recommend the first live broadcast room to the terminal through the user portrait matching the device information. After successfully jumping to the live broadcast application, it directly enters the live broadcast room page corresponding to the first live broadcast room, thus realizing personalized reach in the cross-application jump process, making the cross-application jump result better meet the requirements of activating / pulling new users in the live broadcast business scenario, and improving the retention rate and conversion effect of users after cross-application jump.

[0209] In one example, taking the content recommendation application implemented as an advertising application as an example, taking the application side corresponding to the advertising application as the main body, a schematic illustration of the data processing when the application side corresponding to the advertising application realizes page jump is given. As Figure 7 shown, it shows a data processing flow chart of the application side corresponding to the advertising application provided by an exemplary embodiment of the present application. The process includes the following steps: 701, the advertising platform configures the DeepLink advertisement of the live broadcast application, sets information such as the advertisement id and the platform id; 702, the advertising platform delivers the advertisement to the advertising application; 703, the advertising application receives the operation of the user clicking the advertisement; 704, reports the user information to the advertising platform; 705, executes the DeepLink jump carrying the device information of the terminal.

[0210] In another example, taking the application side corresponding to the live broadcast application as the main body, a schematic illustration of the data processing when the application side corresponding to the live broadcast application realizes page jump is given. As Figure 8As shown, it shows the data processing flow chart of the application side corresponding to the live broadcast application provided by an exemplary embodiment of the present application. The process includes the following steps: 801. Configure the scheme and host that support DeepLink in the Mainfest configuration file of the live broadcast application; 802. When the live broadcast application is launched, parse the advertisement information carried by DeepLink and report it to the server; 803. The server processes the DeepLink information; 804. The server finds the portrait information of the user on the corresponding advertisement platform according to the advertisement id and device information; 805. The server finds the portrait information of the user on its own platform according to the device information; 806. The server matches the most interesting anchor according to the user portrait; 807. The live broadcast application receives the live broadcast room information and performs a jump.

[0211] It should be noted that before and during the process of collecting relevant data of users, the present application can display a prompt interface, a pop-up window or output a voice prompt message. The prompt interface, pop-up window or voice prompt message is used to prompt the user that their relevant data is being collected currently, so that the present application only starts to execute the relevant steps of obtaining the relevant data of the user after obtaining the confirmation operation issued by the user for the prompt interface or pop-up window. Otherwise (that is, when the confirmation operation issued by the user for the prompt interface or pop-up window is not obtained), the relevant steps of obtaining the relevant data of the user are ended, that is, the relevant data of the user is not obtained. In other words, all user data collected by the present application is collected under the consent and authorization of the user, and the collection, use and processing of the relevant user data need to comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0212] Please refer to Figure 9 , which shows the structural block diagram of the page jump device provided by an exemplary embodiment of the present application. The device includes the following modules:

[0213] A display module 910, configured to display a content recommendation page provided by a content recommendation application, where the content recommendation page includes a jump link to a live broadcast application;

[0214] A sending module 920, configured to send the device information of the terminal to the server of the live broadcast application in response to a trigger request of the jump link. The server is used to generate live broadcast recommendation data based on a user portrait matching the device information. The live broadcast recommendation data includes a live broadcast room identifier of a first live broadcast room recommended to the terminal;

[0215] A receiving module 930, configured to receive the live broadcast recommendation data sent by the server of the live broadcast application;

[0216] The display module 910 is further configured to display the live room page corresponding to the first live room based on the live room identifier indicated by the live broadcast recommendation data.

[0217] In some alternative embodiments, as Figure 10 shown, the apparatus further includes:

[0218] A start module 940, configured to start the live application in response to a trigger request for the jump link;

[0219] An acquisition module 950, configured to acquire the device information of the terminal through the live application;

[0220] The sending module 920 is further configured to send the device information to the server of the live application through the live application.

[0221] In some alternative embodiments, the acquisition module 950 is further configured to acquire a platform identifier of the content recommendation application when the terminal meets the new user acquisition requirement, where the platform identifier is used to identify the advertising platform corresponding to the content recommendation application;

[0222] The sending module 920 is further configured to send the device information and the platform identifier to the server of the live application through the live application;

[0223] Wherein, the server is configured to determine the advertising platform based on the platform identifier, and acquire a user portrait matching the device information from the advertising platform.

[0224] In some alternative embodiments, the new user acquisition requirement includes at least one of the following:

[0225] The live application in the terminal is not logged in with an account;

[0226] There is no matching second account in the live application for the registration information of the first account logged in to the content recommendation application in the terminal;

[0227] There is no matching second account in the live application for the identification number associated with the terminal.

[0228] In some alternative embodiments, the server is configured to determine a second account logged in to the terminal in the live application based on the device information; and acquire the user portrait corresponding to the second account.

[0229] In some alternative embodiments, the server is configured to input the device information into a pre-trained portrait generation model to obtain the user portrait, where the device information includes at least one of hardware information, network information, software information, and identification information;

[0230] Wherein, the pre-trained portrait generation model is used to generate the user portrait matching the device information from at least one value dimension according to the device information;

[0231] The at least one value dimension includes at least one of: a consumption ability dimension associated with the hardware information, a technical preference dimension associated with the hardware information, a scenario-based content dimension associated with the network information, an interest graph dimension associated with the software information, and a cross-platform portrait dimension associated with the identification information.

[0232] In some optional embodiments, the server is configured to obtain candidate device information corresponding to multiple candidate accounts, where the candidate accounts are user accounts in the live broadcast application that meet preset conditions, and the candidate accounts correspond to candidate user portraits; compare the candidate device information with the device information, and determine the target device information with the highest similarity to the device information from the candidate device information; use the candidate user portrait of the candidate account corresponding to the target device information as the user portrait corresponding to the terminal.

[0233] In some optional embodiments, the live broadcast recommendation data further includes home page content data matching the user portrait, and the home page content data is used to recommend multiple candidate live broadcast rooms matching the user portrait to the terminal;

[0234] The display module 910 is further configured to, in response to receiving an exit operation for the first live broadcast room, display the application home page of the live broadcast application based on the home page content data, and the application home page includes live broadcast room entrances of the multiple candidate live broadcast rooms.

[0235] In some optional embodiments, the display module 910 is further configured to, in response to receiving a selection operation for a second live broadcast room among the multiple candidate live broadcast rooms, jump to and display the live broadcast room page corresponding to the second live broadcast room;

[0236] The sending module 920 is further configured to send reach information corresponding to the second live broadcast room to the server, where the reach information includes the terminal identifier corresponding to the terminal and the live broadcast room identifier corresponding to the second live broadcast room, and the server is configured to update the user portrait corresponding to the terminal based on the reach information.

[0237] In some optional embodiments, the receiving module 930 is further configured to, in response to receiving an interaction operation within the live broadcast room page of the first live broadcast room, generate reach information corresponding to the first live broadcast room based on the interaction operation, where the reach information includes the terminal identifier corresponding to the terminal, the live broadcast room identifier corresponding to the first live broadcast room, and operation information corresponding to the interaction operation;

[0238] The sending module 920 is further configured to send the reach information corresponding to the first live broadcast room to the server, and the server is configured to update the user profile corresponding to the terminal based on the reach information.

[0239] In some alternative embodiments, the jump link is implemented as a deep link, and a protocol and an address for supporting the deep link jump are configured in the configuration file of the live broadcast application.

[0240] In summary, in the process of implementing cross-application jump, when the jump link for jumping to the live broadcast application on the content recommendation page provided by the content recommendation application is triggered, the terminal sends the device information of the terminal to the server of the live broadcast application, so that the live broadcast application server can recommend the first live broadcast room to the terminal through the user profile matching the device information, and directly enter the live broadcast room page corresponding to the first live broadcast room after successfully jumping to the live broadcast application, thereby realizing personalized reach in the cross-application jump process, making the cross-application jump result better meet the requirements of pulling live / new users in the live broadcast service scenario, and being able to improve the retention rate and conversion effect of users after cross-application jump.

[0241] It should be noted that: for the page jump device provided in the above embodiments, only the above-mentioned division of each functional module is used for illustration. In practical applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the page jump device provided in the above embodiments and the page jump method embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0242] Figure 11 FIG. shows a structural block diagram of a terminal 1100 provided by an exemplary embodiment of the present application. The terminal 1100 may be: a smart phone, a tablet computer, a Moving Picture Experts Group Audio Layer III (MP3) player, a Moving Picture Experts Group Audio Layer IV (MP4) player, a notebook computer, or a desktop computer. The terminal 1100 may also be referred to by other names such as user equipment, portable terminal, laptop terminal, desktop terminal, etc.

[0243] Generally, the terminal 1100 includes: a processor 1101 and a memory 1102.

[0244] The processor 1101 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. The processor 1101 may be implemented in at least one of the following hardware forms: Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 1101 may also include a main processor and a co-processor. The main processor is used to process data in the wake state and is also called the Central Processing Unit (CPU); the co-processor is a low-power processor used to process data in the standby state. In some embodiments, the processor 1101 may be integrated with a Graphics Processing Unit (GPU), and the GPU is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 1101 may further include an Artificial Intelligence (AI) processor, which is used to process computational operations related to machine learning.

[0245] The memory 1102 may include one or more computer-readable storage media, and the computer-readable storage media may be non-transitory. The memory 1102 may further include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash storage devices. In some embodiments, the non-transitory computer-readable storage media in the memory 1102 is used to store at least one instruction, and the at least one instruction is used to be executed by the processor 1101 to implement the page jump method provided in the method embodiments of the present application.

[0246] Illustratively, the terminal 1100 further includes other components 1103. Those skilled in the art can understand that Figure 11 the structure shown in does not constitute a limitation on the terminal 1100, and it may include more or fewer components than shown, or combine certain components, or adopt a different component layout.

[0247] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program. The program can be stored in a computer-readable storage medium, which can be the computer-readable storage medium included in the memory in the above embodiments; it can also exist separately and be a computer-readable storage medium not assembled into the terminal. The computer-readable storage medium stores at least one instruction, at least one segment of program, a code set or an instruction set, and the at least one instruction, the at least one segment of program, the code set or the instruction set are loaded and executed by the processor to implement any one of the page jump methods in the above embodiments.

[0248] Optionally, the computer-readable storage medium may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), solid state drives (SSD, Solid State Drives), or optical discs, etc. Among them, the random access memory may include resistive random access memory (ReRAM, Resistance RandomAccess Memory) and dynamic random access memory (DRAM, Dynamic Random Access Memory). The serial numbers of the embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0249] Those of ordinary skill in the art can understand that all or part of the steps to implement the above embodiments can be completed by hardware or by instructing relevant hardware through a program. The program can be stored in a computer-readable storage medium, and the storage medium mentioned above can be read-only memory, magnetic disk or optical disc, etc.

[0250] The above are only optional embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A page jump method, characterized in that: The method is executed by a terminal, and includes: Displaying a content recommendation page provided by the content recommendation application, wherein the content recommendation page includes a jump link to the live broadcast application; In response to the trigger request of the jump link, sending the device information of the terminal to the server of the live broadcast application, the server is used to generate live broadcast recommendation data based on the user portrait matching the device information, the live broadcast recommendation data including the live broadcast room identifier of the first live broadcast room recommended to the terminal; Receiving the live broadcast recommendation data sent by the server of the live broadcast application; Based on the live broadcast room identifier indicated by the live broadcast recommendation data, the live broadcast room page corresponding to the first live broadcast room is displayed.

2. The method according to claim 1, characterized in that The sending the device information of the terminal to the server of the live broadcast application in response to the triggering request of the jump link includes: In response to the triggering request of the jump link, starting the live broadcast application; Acquire the device information of the terminal through the live broadcast application; The device information is sent to a server of the live broadcast application through the live broadcast application.

3. The method according to claim 2, characterized in that The sending the device information to the server of the live broadcast application through the live broadcast application includes: When the terminal meets the new user acquisition requirement, obtaining a platform identifier of the content recommendation application, where the platform identifier is used to identify an advertising platform corresponding to the content recommendation application; Sending the device information and the platform identifier to a server of the live broadcast application through the live broadcast application; The server is used to determine the advertising platform based on the platform identifier, and obtain a user portrait matching the device information from the advertising platform.

4. The method according to claim 3, characterized in that The new customer acquisition requirements include at least one of the following: The live broadcast application in the terminal has no account logged in; The registration information corresponding to the first account in the terminal for logging into the content recommendation application does not have a matching second account in the live broadcast application; The identification number associated with the terminal does not have a matching second account in the live broadcast application.

5. The method according to any one of claims 1 to 4, characterized in that: The server is used to determine the second account logged in by the terminal in the live broadcast application based on the device information; and obtain the user portrait corresponding to the second account.

6. The method according to any one of claims 1 to 4, characterized in that: The server is used to input the device information into a pre-trained portrait generation model to obtain the user portrait, wherein the device information includes at least one of hardware information, network information, software information, and identification information; The pre-trained portrait generation model is used to generate the user portrait matching the device information from at least one value dimension according to the device information; The at least one value dimension includes: a consumption capacity dimension associated with the hardware information, a technology preference dimension associated with the hardware information, a scenario-based content dimension associated with the network information, an interest graph dimension associated with the software information, and at least one of a cross-platform portrait dimension associated with the identification information.

7. The method according to any one of claims 1 to 4, characterized in that: The server is used to obtain candidate device information corresponding to a plurality of candidate accounts, wherein the candidate accounts are user accounts in the live broadcast application that meet preset conditions, and the candidate accounts correspond to candidate user portraits; Comparing the candidate device information with the device information, and determining the target device information having the highest similarity with the device information from the candidate device information; The candidate user portrait of the candidate account corresponding to the target device information is used as the user portrait corresponding to the terminal.

8. The method according to any one of claims 1 to 4, characterized in that: The live broadcast recommendation data also includes home page content data matching the user portrait, and the home page content data is used to recommend multiple candidate live broadcast rooms matching the user portrait to the terminal; After the live broadcast room identifier indicated by the live broadcast recommendation data is displayed and the live broadcast room page corresponding to the first live broadcast room is displayed, the method further includes: In response to receiving an exit operation for the first live broadcast room, an application home page of the live broadcast application is displayed based on the home content data, and the application home page includes live broadcast room entrances of the multiple candidate live broadcast rooms.

9. The method according to claim 8, characterized in that After the step of displaying the application home page of the live broadcast application based on the home page content data in response to receiving the exit operation for the first live broadcast room, the step further includes: In response to receiving a selection operation on a second live broadcast room among the multiple candidate live broadcast rooms, jumping to display a live broadcast room page corresponding to the second live broadcast room; Send the reach information corresponding to the second live broadcast room to the server, the reach information including the terminal identifier corresponding to the terminal and the live broadcast room identifier corresponding to the second live broadcast room, and the server is used to update the user portrait corresponding to the terminal based on the reach information.

10. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: In response to receiving an interactive operation in a live broadcast room page of the first live broadcast room, generating contact information corresponding to the first live broadcast room based on the interactive operation, the contact information including a terminal identifier corresponding to the terminal, a live broadcast room identifier corresponding to the first live broadcast room, and operation information corresponding to the interactive operation; Send the reach information corresponding to the first live broadcast room to the server, and the server is used to update the user portrait corresponding to the terminal based on the reach information.

11. The method according to any one of claims 1 to 4, characterized in that: The jump link is implemented as a deep link, and the configuration file of the live broadcast application is configured with a protocol and address that supports the deep link jump.

12. A page jump device, characterized in that: The device is configured in a terminal, and includes: A display module, used to display a content recommendation page provided by the content recommendation application, wherein the content recommendation page includes a jump link to the live broadcast application; a sending module, configured to send the device information of the terminal to the server of the live broadcast application in response to the triggering request of the jump link, wherein the server is configured to generate live broadcast recommendation data based on a user portrait matching the device information, wherein the live broadcast recommendation data includes a live broadcast room identifier of a first live broadcast room recommended to the terminal; A receiving module, used for receiving the live broadcast recommendation data sent by the server of the live broadcast application; The display module is also used to display the live broadcast room page corresponding to the first live broadcast room based on the live broadcast room identifier indicated by the live broadcast recommendation data.

13. A computer device, characterized in that: The computer device includes a processor and a memory, wherein the memory stores at least one program, and the at least one program is loaded and executed by the processor to implement the page jump method according to any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that: At least one program code is stored in the computer-readable storage medium, and the program code is loaded and executed by the processor to implement the page jump method according to any one of claims 1 to 11.

15. A computer program product, characterized in that It comprises a computer program or an instruction, and when the computer program or the instruction is executed by a processor, it implements the page jump method as claimed in any one of claims 1 to 11.

Images