WO2023056850A1 - 页面显示方法、装置、设备及存储介质 - Google Patents

页面显示方法、装置、设备及存储介质 Download PDF

Info

Publication number
WO2023056850A1
WO2023056850A1 PCT/CN2022/121212 CN2022121212W WO2023056850A1 WO 2023056850 A1 WO2023056850 A1 WO 2023056850A1 CN 2022121212 W CN2022121212 W CN 2022121212W WO 2023056850 A1 WO2023056850 A1 WO 2023056850A1
Authority
WO
WIPO (PCT)
Prior art keywords
preset
page
user
application
data
Prior art date
Application number
PCT/CN2022/121212
Other languages
English (en)
French (fr)
Inventor
李昭莹
Original Assignee
北京字跳网络技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京字跳网络技术有限公司 filed Critical 北京字跳网络技术有限公司
Publication of WO2023056850A1 publication Critical patent/WO2023056850A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/74—Browsing; Visualisation therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/451—Execution arrangements for user interfaces
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Definitions

  • the present disclosure relates to the technical field of computers, for example, to a page display method, device, equipment and storage medium.
  • users may be allowed to publish various forms of media content such as pictures, audio or video, for other users to view. Since the number of users of the application is usually large and the amount of media content on the platform is also huge, different media content display pages are usually designed to display media content from different sources. In addition, there may be other functions application pages, such as the user's personal homepage or message list page, etc. However, when the user opens the application, he usually enters a fixed page for displaying media content by default, resulting in the first application page displayed after the application is started is fixed and single, and has poor flexibility.
  • the disclosure provides a page display method, device, storage medium and equipment, which can optimize the page display solution.
  • the present disclosure provides a page display method, including:
  • the first data generated during the use of the preset application program by the current user within the preset statistical period is acquired, wherein the first data includes the difference between the current user and the first user Association data between, the current user and the first user have a preset association relationship in the preset application program;
  • the target application page is displayed through the preset application program.
  • the present disclosure provides a page display device, including:
  • the first data acquisition module is configured to acquire the first data generated during the use of the preset application program by the current user within the preset statistical period when it detects that the preset application program is started, wherein the first data includes the The association data between the current user and the first user, the current user and the first user have a preset association relationship in the preset application program;
  • the target application page determination module is configured to input the first data into the preset page determination model after obtaining the first data, and determine the target application page according to the output result of the preset page determination model, wherein the The preset page determination model is used to determine the first displayed application page after this startup, the target application page is one of multiple candidate application pages in the preset application program, and at least one candidate application page is used to display all Describe the media content published by the first user;
  • the target application page display module is configured to display the target application page through the preset application program after the target application page is determined.
  • the present disclosure provides an electronic device, including a memory, a processor, and a computer program stored in the memory and operable on the processor.
  • the processor executes the computer program, the page display method provided in the present disclosure is implemented.
  • the present disclosure provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the page display method as provided in the present disclosure is realized.
  • FIG. 1 is a schematic flowchart of a page display method provided by an embodiment of the present disclosure
  • FIG. 2 is a schematic diagram of a training process of a preset page determination model in a page display method provided by an embodiment of the present disclosure
  • FIG. 3 is a schematic flowchart of another page display method provided by an embodiment of the present disclosure.
  • FIG. 4 is a schematic diagram of an interaction process of a page display method provided by an embodiment of the present disclosure
  • FIG. 5 is a structural block diagram of a page display device provided by an embodiment of the present disclosure.
  • Fig. 6 is a structural block diagram of an electronic device provided by an embodiment of the present disclosure.
  • the term “comprise” and its variations are open-ended, ie “including but not limited to”.
  • the term “based on” is “based at least in part on”.
  • the term “one embodiment” means “at least one embodiment”; the term “another embodiment” means “at least one further embodiment”; the term “some embodiments” means “at least some embodiments.” Relevant definitions of other terms will be given in the description below.
  • the user Before using the technical solutions disclosed in the embodiments of the present disclosure, the user should be informed of the type, scope of use, and use scenarios of the personal information involved in the present disclosure in an appropriate manner in accordance with relevant laws and regulations, and the authorization of the user should be obtained.
  • the method of sending the prompt information to the user may be, for example, a pop-up window, and the prompt information may be presented in text in the pop-up window.
  • the pop-up window may also carry a selection control for the user to choose "agree” or "disagree” to provide personal information to the electronic device.
  • FIG. 1 is a schematic flow chart of a page display method provided by an embodiment of the present disclosure.
  • the method can be executed by a page display device, which can be implemented by software and/or hardware, and generally can be integrated into an electronic device. As shown in Figure 1, the method includes:
  • the preset application program When it is detected that the preset application program is started, acquire the first data generated when the current user uses the preset application program within the preset statistical period, wherein the first data includes the association data between the current user and the first user , the current user and the first user have a preset association relationship in the preset application program.
  • the type of the preset application program is not limited, for example, it may be a short video application program or a live broadcast application program, or other types of application programs.
  • the preset statistical period may be a time range, for example, one month.
  • the current user may be a user who is using a preset application.
  • the preset association relationship may be a preset association relationship between two users existing in the preset application program.
  • the preset association relationship may include a two-way association relationship, such as a friend relationship, where the current user and the first user follow each other, or there is information interaction between the current user and the first user, such as chatting, commenting and Reply to comments, etc.; the preset association relationship can also include a one-way association relationship, such as the relationship between the current user and the first user can be the relationship between following and being followed, the relationship between liking and being liked, the relationship between commenting and being commented, Or the current user is a fan relationship of the first user, etc.
  • the first user is a user who has a preset association relationship with the current user in the preset application program, and the number of the first users may be one or more.
  • the association data may include data representing the association relationship between the current user and the first user, such as the number of the first user;
  • the data related to the first user for example, may include data (such as interaction data) generated by the current user based on the associated page of the first user.
  • the associated page may include the personal homepage of the first user, displaying the The page where the content is published, the first user’s chat page or the first user’s live broadcast page, etc.
  • the associated data may include the number or duration of the current user’s browsing of the first user’s associated page, the current user’s praise of the first user’s work The amount of content, the number of comments between the current user and the first user, and related data when the current user inputs interactive operations such as following, liking, or commenting.
  • the first data includes association data between the current user and the first user.
  • the first data may also include other data other than the associated data generated during the current user’s use of the preset application program within the preset statistical period, which can be set according to the characteristics of the preset application program.
  • the content of the data is not limited.
  • the first data is stored on the client side, that is, locally on the electronic device currently used by the user.
  • the candidate application pages may include all or part of the application pages in the preset application program, and the application pages may be content pages after the startup page, where the startup page is, for example, an advertisement page.
  • the startup page is, for example, an advertisement page.
  • at least one candidate application page is used to display media content released by the first user.
  • the at least one candidate application page may also display media content released by other users, which is not limited.
  • the candidate application pages may include a video recommendation page, a live broadcast page, the current user's personal homepage or other user's personal homepages, etc., wherein at least one candidate application page may include a video recommendation page, On the live broadcast page or the personal home page of the first user, the videos released by the first user can be displayed on the video recommendation page, and the live stream of the first user can be played on the live broadcast page.
  • the target application page may be one determined from a plurality of candidate application pages by using a preset page determination model, and is used for priority display after this startup.
  • the preset page determination model can be obtained by using sample data for training, and the sample data can include data generated by multiple users when using the preset application program and corresponding label data suitable for the page displayed for the first time. After the first data is input into the preset page determination model, the output result is obtained, and the target application page is determined from the candidate application pages according to the output result, that is, the application page suitable for priority display in this startup.
  • the short video application program inputs the acquired first data into the preset page determination model, and according to the current user's interaction data in the process of using the short video application program in the last month, after being processed by the preset page determination model, the output As a result, the target application page is further determined.
  • the target application page to be displayed first is determined by using the preset page determination model, related resources of the target application page can be loaded and page drawing and other operations can be performed, and the target application page can be displayed in the preset application program .
  • the page display scheme provided in the embodiments of the present disclosure obtains the first data generated during the use of the preset application program by the current user within the preset statistical period, inputs the first data into the preset page determination model, and according to the preset
  • the output result of the page determination model determines the target application page, and the target application page is displayed through the preset application. Compared with the same page opened by default, it can solve the problem that the first application page displayed after the application starts is solidified, single and poor in flexibility , realize the purpose of personalizing and determining the target application page, and improve the user experience.
  • the determining the target application page according to the output result of the preset page determination model includes: determining the target application page according to the evaluation score output by the preset page determination model, wherein different candidate application pages correspond to different assessment scores.
  • the preset page determination model is obtained by training in the following manner: obtaining training sample data corresponding to sample users, wherein the training sample data includes the process of using the preset application program by the sample user within the preset statistical period The second data generated in and the corresponding evaluation score label, the second data includes the association data between the sample user and the second user, and the sample user and the second user are in the preset application program The preset association relationship exists in; the training sample data is input into the preset neural network model, and the corresponding preset loss function is calculated; the preset neural network model is trained based on the preset loss function, Get the preset page to determine the model.
  • the advantage of this setting is that the neural network model is represented by the network topology node characteristics and learning rules, which can be used to deal with imprecise and fuzzy information processing problems that need to consider many factors and conditions at the same time. Training to obtain an accurate preset page determination model, so as to more reasonably determine the target application page.
  • the short video application has following user pages, live broadcast pages, and friend pages, and the corresponding evaluation score labels are 1, 2, and 3. If, for a sample user, the first user who opens the short video application It is best when the page is a user-followed page, so the second data corresponding to the sample user is labeled as 1, and the training sample data corresponding to the sample user is obtained. After the preset neural network model training, the evaluation score corresponding to the output result of the data similar to the training sample data is closer to 1 after the model is applied. When the model is applied, the current user's data can be input into the model. If the output If the evaluation score of is 1, or the closest to 1, or the confidence of 1 is the highest, etc., it is determined that the first page that opens the short video application is the page of the following user.
  • FIG. 2 is a schematic diagram of a training flow of a preset page determination model in a page display method provided by an embodiment of the present disclosure.
  • the training sample data includes the second data and the corresponding evaluation score labels generated during the use of the preset application program by the sample user within the preset statistical period, the second data includes the correlation data between the sample user and the second user, and the sample There is a preset association relationship between the user and the second user in the preset application program.
  • preset statistical cycle preset association relationship and associated data, please refer to the relevant content above, and will not repeat them here.
  • the sample user can be any user who uses the preset application program, which can be selected according to the actual training requirements.
  • the second data can be the data generated by the sample user during the use of the preset application program, and the contained content can be Similar to the first data above, the difference is that the second data is sample data set in advance.
  • the evaluation score label can be the score label marked by the preset neural network model on the second data before training.
  • the score value corresponding to the evaluation score label may be determined through investigation or simulation experiment. For example, determine which application page the sample user most wants to open for the first time when opening the preset application program again when the second data is generated, and determine the evaluation score corresponding to the application page as the evaluation score label corresponding to the current second data.
  • the evaluation score label is determined based on at least one of the following when the first displayed application page is the corresponding candidate application page after the preset application is started: the sample user views the corresponding candidate application page the first duration of the sample user’s viewing of media content through the corresponding candidate application page; the second duration of the sample user’s current use of the preset application program; and the sample user’s current use of the preset application program to view A second quantity of media content.
  • the first duration may be the total time spent on the first displayed candidate application page by the sample user while using the default application program; the first amount may be the total time spent by the sample user on the first displayed candidate application page The total amount of media content viewed on the page; the second duration may be the total duration experienced by the sample user using the preset application program; the second amount may be the total amount of media content viewed by the sample user using the preset application program this time.
  • a longer duration or a larger number may indicate that the user prefers or is more accustomed to browsing the corresponding page, and tags may be marked according to the evaluation scores of the corresponding candidate application pages.
  • sample user a when the first application pages displayed after the short video application is started are the following user page, live broadcast page and friend page respectively, if sample user a views the following user page, live broadcast page and friend
  • the page durations are 30 minutes, 5 minutes, and 6 minutes respectively, which means that when the first displayed application page is a user-followed page, sample user a can stay on the page for a longer time, and the corresponding page of sample user a can be
  • the evaluation score label of the second data is set to 1.
  • sample user b when the first application page displayed after the short video application is started is the following user page, live broadcast page and friend page, if sample user b uses the short video application three times, The number of watched videos or live streams is 10, 5, and 50 respectively, which means that when the first displayed application page is a friend page, sample user b can watch more video content in the short video application,
  • the evaluation score label of the second data corresponding to the sample user b may be set to 3.
  • model structure and weight parameters in the preset neural network model are not limited, and can be set according to actual needs.
  • the preset loss function can be used to evaluate the performance of the preset page determination model.
  • the second data in the training sample data may be input to the preset neural network model, and the predicted value is calculated according to the output of the model and the evaluation score label of the currently input training sample data.
  • the loss function can be used to evaluate the degree of difference between the predicted value of the model and the real value. In the embodiment of the present disclosure, it can calculate the similarity between the output evaluation score and the evaluation score label. The higher the value of the loss function, the higher the value of the loss function. That is, the higher the similarity between the two, the better the performance of the model.
  • the weight parameters in the preset neural network model can be tuned based on the preset loss function, and after multiple iterative adjustments, when the preset convergence condition is reached, the preset page determination model can be obtained.
  • the preset convergence condition is not limited, and may be that the number of iterations reaches a preset number threshold or the preset loss function value is greater than a preset threshold.
  • the first data further includes historical interaction data of the current user.
  • the advantage of this setting is that the first data can more accurately reflect the user's preference for different application pages, and improve the accuracy of the output result of the preset page determination model.
  • the historical interaction data can be the interaction data generated during the current user's use of the preset application program, which can include the interaction data between the user and the preset application program, such as operation data, and also include the interaction data between the user and other users , such as the number of times the current user has liked other users before using the default application.
  • the historical interaction data of the current user is saved on the client.
  • the historical interaction data includes at least one of the following: the number and/or frequency of entering candidate application pages in response to user operations; The number of times the candidate application page was entered.
  • the advantage of this setting is that it can more comprehensively understand the application pages that the user is interested in, and improve the accuracy of the first data and the accuracy of the output results of the model.
  • the preset duration may be a preset duration, such as 3 minutes.
  • the number and/or frequency data of the user's operation to enter the candidate application page may include 5 times in the past week (preset statistical period) in response to the current user entering the concerned page by clicking a page label or other operations or 1 time per day ;
  • the data of the number of times of entering candidate application pages in response to user operations may include 5 times in response to user clicks to enter attention pages within 3 minutes of starting the preset application.
  • the associated data includes at least one of the following: the number of the first users; the number of first users whose interaction data with the current user meets preset requirements; The third duration and/or the third quantity of the media content released by the first user; the current user enters the preset page through the preset candidate application page and stays on the preset page for the fourth duration, wherein the The preset candidate application page includes a candidate application page currently displaying the media content released by the first user; and the number of unread information about the first user of the current user.
  • the preset requirement may be set according to the interaction data generated by the current user based on the associated page of the first user. If the frequency of interaction between the current user and the first user reaches a preset frequency threshold, it may be considered that the preset requirement is met.
  • the current user follows the first user, watches the content of the first user's work, then likes the first user's work, and comments in the comment area of the first user's work content, the first user Also interact with the current user in the comment area, then as the interaction between the current user and the first user gradually increases, the relationship between the two can gradually change from the ordinary follow-and-follow relationship to the follow-and-be-followed relationship that meets the preset requirements. Focus on relationships.
  • the third duration may be the total duration for the current user to view the media content posted by the first user.
  • the third quantity may be the total quantity of media content posted by the first user viewed by the current user.
  • the preset candidate application page may be a candidate application page that displays media content published by the first user while the current user is using the preset application program, and the fourth duration may be that the current user enters the preset page through the preset candidate application page, And the total time spent on the preset page.
  • the unread information may be messages sent by the first user or works published by the first user that have not been read by the current user in the preset application program.
  • the associated data may include the number of users that the current user follows (such as 100); it may include the number of followed users whose interaction data with the current user meets preset requirements (such as 10); it may include the number of users viewed by the current user. Watching time of the media content released by the following user (such as 1 hour), or the number of media content released by the current user (such as 15); it can also include that the current user enters a personal homepage of the following user through the recommendation page, and in The length of stay on the personal homepage (for example, 15 minutes), wherein the recommended page currently displays the media content published by the followed user.
  • the above data can be used as the first data input into the preset page determination model for determining the target application page.
  • the media content displayed on at least one candidate application page is published by the first user.
  • the at least one candidate application page does not include media content published by users other than the first user.
  • the advantage of such setting is that the page types of the candidate application pages are enriched.
  • at least one candidate application page may be a followed user page, and only the first user followed by the current user is included in the followed user page How many short videos have been posted, excluding short videos posted by other users who are not followed by the current user.
  • the associated data further includes: information about associated events of the current user with respect to the first user and preset event information of the first user.
  • Associated events may include, for example, media content release events, group creation events, preset reminder events, and the like.
  • the preset event information may be the first user's notification information related to the associated event.
  • the media content release event may include the start of the live broadcast, and the preset event information may include the start broadcast notification; the media content release event may include the release of a new work, and the preset event information may include a new notification on the work; the preset reminder event may include fans For the group-initiated urging event to update works, the preset event information may include invitation information to participate in the urging update.
  • Fig. 3 is a schematic flow chart of a page display method provided by an embodiment of the present disclosure.
  • the embodiment of the present disclosure is described based on the solutions in the above embodiments.
  • Multiple candidate application pages are pre-set in the application, namely the recommendation page, attention page and live broadcast page.
  • the first displayed application page can be intelligently determined.
  • the recommendation page is used to play short videos of any user
  • the follow page is used to play short videos posted by users followed by the current user
  • the live page is used to play live streams of any user.
  • the method includes:
  • the first data includes historical interaction data of the current user, and further includes association data between the current user and the first user.
  • the current user follows the first user in the short video application.
  • the historical interaction data includes the number of times the candidate application page is entered in response to the user operation, and also includes the number of times the candidate application page is entered in response to the user operation within a preset time period after the preset application program is started. For example, in the last month, the current user actively enters the recommendation page, follow page and friend page 5 times, 30 times and 10 times by entering the page switching operation; within 1 minute after the short video application is launched , the times of actively entering the recommendation page, follow page and friend page by inputting the page switching operation are 0 times, 20 times and 2 times respectively.
  • the historical interaction data may also include, for example, the total time the current user has watched live broadcasts or short videos in the last month.
  • the associated data includes the number of first users, for example, the total number of users currently followed by the current user; and/or the number of first users whose interaction data with the current user meets preset requirements, for example, among all first users Among them, the number of first users whose interaction frequency with the current user reaches more than n times per week (n>0); the third duration and the third amount of the current user viewing the media content published by the first user, for example, the current user viewing The total duration and total number of short videos released by all first users; the current user enters the preset page through the preset candidate application page and stays on the preset page for the fourth time, for example, the current user passes the attention page Enter the personal homepage of the publisher of the currently playing short video and stay on the personal homepage; and the number of unread information about the first user of the current user, for example, the short video published by the first user that the current user has not watched the number of videos.
  • FIG. 4 is a schematic diagram of an interactive process of a page display method provided by an embodiment of the present disclosure.
  • the short video application startup page 401 (such as an advertisement page) is displayed. If the target application is determined by the preset page determination model If the page is an attention page, the attention page 402 can be displayed after the startup page 401 is displayed, that is, the short video application jumps from the startup page 401 to the attention page 402.
  • the page display method provided by the embodiment of the present disclosure can be applied to a short video application program.
  • the evaluation score of the candidate application page can be obtained through the preset page determination model, and the candidate application page can be selected from multiple candidate application pages.
  • the page with the evaluation score label closest to the evaluation score is recommended to the current user as the target application page.
  • FIG. 5 is a structural block diagram of a page display device provided by an embodiment of the present disclosure.
  • the device can be implemented by software and/or hardware, and generally can be integrated in an electronic device, and can display a page by executing a page display method. As shown in Figure 5, the device includes:
  • the first data acquisition module 501 is configured to acquire the first data generated during the use of the preset application program by the current user within the preset statistical period when it detects that the preset application program is started, wherein the first data includes As for the association data between the current user and the first user, the current user and the first user have a preset association relationship in the preset application;
  • the target application page determination module 502 is configured to obtain the first After receiving the data, input the first data into the preset page determination model, and determine the target application page according to the output result of the preset page determination model, wherein the preset page determination model is used to determine the startup After the first displayed application page, the target application page is one of multiple candidate application pages in the preset application program, at least one candidate application page is used to display the media content released by the first user;
  • the target application The page display module 503 is configured to display the target application page through the preset application program after the target application page is determined.
  • the page display device when the user opens the preset application program, can obtain the evaluation score through the preset page determination model, determine the target application page according to the evaluation score, and solve the problem of displaying the first application page after the application program is started
  • the problem of solidification and singleness and poor flexibility can realize the purpose of personalized determination of the target application page and improve user experience.
  • the first data further includes historical interaction data of the current user.
  • the historical interaction data includes at least one of the following: the number and/or frequency of entering candidate application pages in response to user operations; The number of candidate app pages.
  • the associated data includes at least one of the following: the number of the first users; the number of first users whose interaction data with the current user meets preset requirements; the current user views the The third duration and/or the third quantity of the media content released by the first user; the current user enters the preset page through the preset candidate application page and stays on the preset page for the fourth duration, wherein the The preset candidate application pages include a candidate application page currently displaying media content published by the first user; and the number of unread information about the first user of the current user.
  • the media content displayed on at least one candidate application page is published by the first user.
  • the association data further includes: information about an association event of the current user with respect to the first user and preset event information of the first user.
  • the target application page determination module 502 is set to:
  • the target application page is determined according to the evaluation score output by the preset page determination model, wherein different candidate application pages correspond to different evaluation scores; wherein, the preset page determination model is obtained by training in the following manner: obtain the training corresponding to the sample user Sample data, wherein the training sample data includes second data generated during the use of the preset application program by the sample user within the preset statistical period and a corresponding evaluation score label, the second data includes Association data between the sample user and the second user, the sample user and the second user have the preset association relationship in the preset application program; input the training sample data into the preset A neural network model, and calculate a corresponding preset loss function; train the preset neural network model based on the preset loss function to obtain a preset page determination model.
  • the device further includes: an evaluation score label determination module, configured such that the evaluation score label is based on at least the following when the first displayed application page is the corresponding candidate application page A determination: the first duration of viewing the corresponding candidate application page by the sample user; the first amount of media content viewed by the sample user through the corresponding candidate application page; the second duration of using the preset application by the sample user; and A second amount of media content viewed by the sample user using the preset application program at the current time.
  • an evaluation score label determination module configured such that the evaluation score label is based on at least the following when the first displayed application page is the corresponding candidate application page A determination: the first duration of viewing the corresponding candidate application page by the sample user; the first amount of media content viewed by the sample user through the corresponding candidate application page; the second duration of using the preset application by the sample user; and A second amount of media content viewed by the sample user using the preset application program at the current time.
  • FIG. 6 it shows a schematic structural diagram of an electronic device 600 suitable for implementing an embodiment of the present disclosure.
  • the electronic device 600 in the embodiment of the present disclosure may include but not limited to mobile phones, notebook computers, digital broadcast receivers, personal digital assistants (Personal Digital Assistant, PDA), tablet computers (Portable Android Device, PAD), portable multimedia player Mobile terminals such as Portable Media Player (PMP), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital television (Television, TV), desktop computers, etc.
  • PDA Personal Digital Assistant
  • PAD Portable Multimedia Player
  • vehicle-mounted terminals such as vehicle-mounted navigation terminals
  • fixed terminals such as digital television (Television, TV), desktop computers, etc.
  • the electronic device 600 shown in FIG. 6 is only an example, and should not limit the functions and application scope of the embodiments of the present disclosure.
  • an electronic device 600 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) Various appropriate actions and processes are performed by a program loaded into a random access memory (Random Access Memory, RAM) 603 by 608. In the RAM 603, various programs and data necessary for the operation of the electronic device 600 are also stored.
  • the processing device 601, ROM 602, and RAM 603 are connected to each other through a bus 604.
  • An input/output (Input/Output, I/O) interface 605 is also connected to the bus 604 .
  • an input device 606 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; including, for example, a liquid crystal display (Liquid Crystal Display, LCD) , an output device 607 such as a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609.
  • the communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data.
  • FIG. 6 shows electronic device 600 having various means, it is not a requirement to implement or possess all of the means shown. More or fewer means may alternatively be implemented or provided.
  • embodiments of the present disclosure include a computer program product, which includes a computer program carried on a non-transitory computer readable medium, where the computer program includes program code for executing the method shown in the flowchart.
  • the computer program may be downloaded and installed from a network via communication means 609, or from storage means 608, or from ROM 602.
  • the processing device 601 When the computer program is executed by the processing device 601, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are performed.
  • the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two.
  • a computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof.
  • Examples of computer readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, RAM, ROM, Erasable Programmable Read-Only Memory (EPROM) or flash memory), optical fiber, portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal in baseband or propagated as part of a carrier wave carrying computer-readable program code therein. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, and the computer-readable signal medium may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device .
  • the program code contained on the computer readable medium can be transmitted by any appropriate medium, including but not limited to: electric wire, optical cable, radio frequency (Radio Frequency, RF), etc., or any suitable combination of the above.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device, or may exist independently without being incorporated into the electronic device.
  • the above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device: detects that the preset application program is started, and obtains the current user's data within the preset statistical period.
  • the first data generated during the process of using the preset application program wherein the first data includes the association data between the current user and the first user, and the current user and the first user have a preset association relationship in the preset application program;
  • the first data is input into the preset page determination model, and the target application page is determined according to the output result of the preset page determination model, wherein the preset page determination model is used to determine the first displayed application page after this startup, and the target application page is One of multiple candidate application pages in the preset application program, at least one candidate application page is used to display the media content published by the first user; the target application page is displayed through the preset application program.
  • Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, or combinations thereof, including but not limited to object-oriented programming languages—such as Java, Smalltalk, C++, and Includes conventional procedural programming languages - such as the "C" language or similar programming languages.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer can be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or it can be connected to an external computer ( For example, use an Internet service provider to connect via the Internet).
  • LAN Local Area Network
  • WAN Wide Area Network
  • each block in a flowchart or block diagram may represent a module, program segment, or portion of code that contains one or more logical functions for implementing specified executable instructions.
  • the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented by a dedicated hardware-based system that performs the specified functions or operations , or may be implemented by a combination of dedicated hardware and computer instructions.
  • the modules involved in the embodiments described in the present disclosure may be implemented by software or by hardware.
  • the name of the module does not limit the module itself, for example, the first data acquisition module can also be described as "a module that acquires the first data when a preset application is detected to be started".
  • exemplary types of hardware logic components include: Field Programmable Gate Arrays (Field Programmable Gate Arrays, FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (Application Specific Standard Parts, ASSP), System on Chip (System on Chip, SOC), Complex Programmable Logic Device (Complex Programming Logic Device, CPLD) and so on.
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device.
  • a machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • a machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Examples of machine-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard drives, RAM, ROM, EPROM or flash memory, optical fibers, CD-ROMs, optical storage devices, magnetic storage devices, or Any suitable combination of the above.
  • a page display method including:
  • the first data generated during the use of the preset application program by the current user within the preset statistical period is acquired, wherein the first data includes the difference between the current user and the first user Association data between, the current user and the first user have a preset association relationship in the preset application program;
  • the target application page is displayed through the preset application program.
  • the determining the target application page according to the output result of the preset page determination model includes:
  • the preset page determination model is obtained through training in the following manner:
  • the training sample data includes second data generated during the sample user using the preset application program within the preset statistical period and a corresponding evaluation score label,
  • the second data includes association data between the sample user and a second user, and the sample user and the second user have the preset association relationship in the preset application program;
  • the preset neural network model is trained based on the preset loss function to obtain a preset page determination model.
  • the evaluation score tag is determined based on at least one of the following when the first displayed application page is the corresponding candidate application page after the preset application is started:
  • a second amount of media content viewed by the sample user using the preset application program at the current time is viewed by the sample user using the preset application program at the current time.
  • the first data further includes historical interaction data of the current user.
  • the historical interaction data includes at least one of the following:
  • the associated data includes at least one of the following:
  • the current user enters the preset page through the preset candidate application page and stays on the preset page for a fourth period of time, wherein the preset candidate application page includes information that currently displays the media content published by the first user.
  • the media content displayed on at least one candidate application page is published by the first user.
  • the association data further includes: information about an association event of the current user with respect to the first user and preset event information of the first user.
  • a page display device including:
  • the first data acquisition module is configured to acquire the first data generated during the use of the preset application program by the current user within the preset statistical period when it detects that the preset application program is started, wherein the first data includes the The association data between the current user and the first user, the current user and the first user have a preset association relationship in the preset application program;
  • the target application page determination module is configured to input the first data into the preset page determination model after obtaining the first data, and determine the target application page according to the output result of the preset page determination model, wherein the The preset page determination model is used to determine the first displayed application page after this startup, the target application page is one of multiple candidate application pages in the preset application program, and at least one candidate application page is used to display all Describe the media content published by the first user;
  • the target application page display module is configured to display the target application page through the preset application program after the target application page is determined.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Health & Medical Sciences (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

本文公开了页面显示方法、装置、设备及存储介质。该页面显示方法包括：检测到预设应用程序启动时，获取当前用户预设统计周期内使用预设应用程序产生的第一数据，第一数据包括当前用户与第一用户之间的关联数据；将第一数据输入预设页面确定模型，根据预设页面确定模型输出结果确定目标应用页面，预设页面确定模型确定本次启动后首个显示的应用页面，目标应用页面为预设应用程序多个候选应用页面中的一个；预设应用程序显示目标应用页面。

Description

页面显示方法、装置、设备及存储介质
本申请要求在2021年10月08日提交中国专利局、申请号为202111171765.8的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本公开涉及计算机技术领域，例如涉及页面显示方法、装置、设备及存储介质。
背景技术
随着互联网技术的快速发展，多种应用程序层出不穷，为用户提供了越来越丰富的交互方式和交互体验。
在一些应用平台中，可以允许用户发布图片、音频或视频等多种形式的媒体内容，供其他用户查看。由于应用程序的用户数量通常较多，平台上的媒体内容数量也很庞大，因此，通常会设计不同的媒体内容展示页面来展示不同来源的媒体内容，此外，还可能会存在用于实现其他功能的应用页面，如用户个人主页或消息列表页面等。然而，当用户打开应用程序后，通常默认进入一个固定的用于展示媒体内容的页面，导致应用程序启动后显示的首个应用页面固化且单一，灵活性差。
发明内容
本公开提供了页面显示方法、装置、存储介质及设备，可以优化页面显示方案。
本公开提供了一种页面显示方法，包括：
检测到预设应用程序启动时，获取当前用户在预设统计周期内使用所述预设应用程序过程中产生的第一数据，其中，所述第一数据包括所述当前用户与第一用户之间的关联数据，所述当前用户和所述第一用户在所述预设应用程序中存在预设关联关系；
将所述第一数据输入至预设页面确定模型，并根据所述预设页面确定模型的输出结果确定目标应用页面，其中，所述预设页面确定模型用于确定本次启动后首个显示的应用页面，所述目标应用页面为所述预设应用程序中的多个候选应用页面中的一个，至少一个候选应用页面用于展示所述第一用户发布的媒体内容；
通过所述预设应用程序显示所述目标应用页面。
本公开提供了一种页面显示装置，包括：
第一数据获取模块，设置为检测到预设应用程序启动时，获取当前用户在预设统计周期内使用所述预设应用程序过程中产生的第一数据，其中，所述第一数据包括所述当前用户与第一用户之间的关联数据，所述当前用户和所述第一用户在所述预设应用程序中存在预设关联关系；
目标应用页面确定模块，设置为获取到第一数据后，将所述第一数据输入至预设页面确定模型，并根据所述预设页面确定模型的输出结果确定目标应用页面，其中，所述预设页面确定模型用于确定本次启动后首个显示的应用页面，所述目标应用页面为所述预设应用程序中的多个候选应用页面中的一个，至少一个候选应用页面用于展示所述第一用户发布的媒体内容；
目标应用页面显示模块，设置为确定目标应用页面之后，通过所述预设应用程序显示所述目标应用页面。
本公开提供了一种电子设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现如本公开提供的页面显示方法。
本公开提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现如本公开提供的页面显示方法。
附图说明
图1为本公开实施例提供的一种页面显示方法的流程示意图；
图2为本公开实施例提供的一种页面显示方法中预设页面确定模型的训练流程示意图；
图3为本公开实施例提供的另一种页面显示方法的流程示意图；
图4为本公开实施例提供的一种页面显示方法的交互过程示意图；
图5为本公开实施例提供的一种页面显示装置的结构框图；
图6为本公开实施例提供的一种电子设备的结构框图。
具体实施方式
下面将参照附图描述本公开的实施例。虽然附图中显示了本公开的一些实施例，本公开可以通过多种形式来实现，提供这些实施例是为了理解本公开。本公开的附图及实施例仅用于示例性作用。
本公开的方法实施方式中记载的多个步骤可以按照不同的顺序执行，和/或并行执行。此外，方法实施方式可以包括附加的步骤和/或省略执行示出的步骤。本公开的范围在此方面不受限制。
本文使用的术语“包括”及其变形是开放性包括，即“包括但不限于”。术语“基于”是“至少部分地基于”。术语“一个实施例”表示“至少一个实施例”；术语“另一实施例”表示“至少一个另外的实施例”；术语“一些实施例”表示“至少一些实施例”。其他术语的相关定义将在下文描述中给出。
本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。
本公开中提及的“一个”、“多个”的修饰是示意性的，本领域技术人员应当理解，除非在上下文另有指出，否则应该理解为“一个或多个”。
本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的，而并不是用于对这些消息或信息的范围进行限制。
在使用本公开实施例公开的技术方案之前，均应当依据相关法律法规通过恰当的方式对本公开所涉及个人信息的类型、使用范围、使用场景等告知用户并获得用户的授权。
例如，在响应于接收到用户的主动请求时，向用户发送提示信息，以明确地提示用户，其请求执行的操作将需要获取和使用到用户的个人信息。从而，使得用户可以根据提示信息来自主地选择是否向执行本公开技术方案的操作的电子设备、应用程序、服务器或存储介质等软件或硬件提供个人信息。
作为一种实现方式，响应于接收到用户的主动请求，向用户发送提示信息的方式例如可以是弹窗的方式，弹窗中可以以文字的方式呈现提示信息。此外，弹窗中还可以承载供用户选择“同意”或者“不同意”向电子设备提供个人信息的选择控件。
上述通知和获取用户授权过程仅是示意性的，不对本公开的实现方式构成限定，其它满足相关法律法规的方式也可应用于本公开的实现方式中。
下述实施例中，每个实施例中同时提供了可选特征和示例，实施例中记载的多个特征可进行组合，形成多个可选方案，不应将每个编号的实施例仅视为一个技术方案。
图1为本公开实施例提供的一种页面显示方法的流程示意图，该方法可以由页面显示装置执行，该装置可由软件和/或硬件实现，一般可集成在电子设备中。如图1所示，该方法包括：
101、检测到预设应用程序启动时，获取当前用户在预设统计周期内使用预设应用程序过程中产生的第一数据，其中，第一数据包括当前用户与第一用户之间的关联数据，当前用户和第一用户在预设应用程序中存在预设关联关系。
本公开实施例中，对预设应用程序的类型不做限定，例如可以是短视频应用程序或直播应用程序等，还可以是其他类型的应用程序。预设统计周期可以是一个时间范围，例如，一个月。当前用户可以是正在使用预设应用程序的用户。预设关联关系可为预先设定的在预设应用程序中存在的两个用户之间的一种关联关系。在一些应用场景中，预设关联关系可包括双向关联关系，如好友关系，此时当前用户和第一用户互相关注，又如当前用户和第一用户之间存在信息交互，如聊天、评论和回复评论等；预设关联关系也可包括单向关联关系，如当前用户和第一用户之间可以是关注与被关注的关系、点赞与被点赞的关系、评论与被评论的关系、或者当前用户是第一用户的粉丝关系等。第一用户是在预设应用程序中与当前用户存在预设关联关系的用户，第一用户的数量可以是一个或多个。
本公开实施例中，关联数据可以包括用于表示当前用户与第一用户之间的关联关系的数据，如第一用户的数量；关联数据还可包括当前用户在使用预设应用程序过程中产生的与第一用户相关的数据，示例性的，可以包括当前用户基于第一用户的关联页面产生的数据(如交互数据)，关联页面可包括第一用户的个人主页、展示有第一用户所发布内容的页面、第一用户的聊天页面或第一用户的直播页面等等，例如，关联数据可包括当前用户浏览第一用户的关联页面的次数或时长、当前用户点赞第一用户的作品内容的数量、当前用户与第一用户之间的评论数量，还可以是当前用户输入关注、点赞或者评论等交互操作时的相关数据。第一数据中包括当前用户与第一用户之间的关联数据。
第一数据中还可以包括当前用户在预设统计周期内使用预设应用程序过程中产生的除所述关联数据之外的其他数据，可以根据预设应用程序的自身特点来设定，对其他数据的内容不做限定。第一数据存储于客户端，也即当前用户所使用的电子设备本地。
102、将第一数据输入至预设页面确定模型，并根据预设页面确定模型的输出结果确定目标应用页面，其中，预设页面确定模型用于确定本次启动后首个显示的应用页面，目标应用页面为预设应用程序中的多个候选应用页面中的一 个，至少一个候选应用页面用于展示第一用户发布的媒体内容。
本公开实施例中，候选应用页面可包括预设应用程序中的全部或部分应用页面，应用页面可以是启动页面之后的内容页面，启动页面例如为广告页面。其中，至少一个候选应用页面用于展示第一用户发布的媒体内容，此外，该至少一个候选应用页面中也可展示有其他用户发布的媒体内容，对此不做限定。示例性的，对于视频类应用程序来说，候选应用页面可包括视频推荐页面、直播页面、当前用户的个人主页或其他用户的个人主页等，其中，至少一个候选应用页面可包括视频推荐页面、直播页面或第一用户的个人主页页面，第一用户发布的视频可以展示于视频推荐页面中，第一用户的直播流可以在直播页面中播放。目标应用页面可以是利用预设页面确定模型从多个候选应用页面中确定的一个，用于本次启动后进行优先显示。预设页面确定模型可以通过采用样本数据进行训练得到，样本数据可以包括多个用户在使用预设应用程序过程中产生的数据以及对应的适合首次显示的页面的相关标签数据。将第一数据输入到预设页面确定模型后，得到输出结果，根据输出结果从候选应用页面中确定目标应用页面，也即适合本次启动优先显示的应用页面。
示例性的，短视频应用程序将获取的第一数据输入预设页面确定模型，根据当前用户在最近一个月内使用短视频应用程序过程中的交互数据，经由预设页面确定模型处理后，输出结果，进而确定目标应用页面。
103、通过预设应用程序显示目标应用页面。
示例性的，在利用预设页面确定模型确定即将首个显示的目标应用页面后，可以对目标应用页面的相关资源进行加载以及进行页面绘制等操作，并在预设应用程序中显示目标应用页面。
本公开实施例中提供的页面显示方案，通过获取当前用户在预设统计周期内使用预设应用程序过程中产生的第一数据，将第一数据输入至预设页面确定模型，并根据预设页面确定模型的输出结果确定目标应用页面，通过预设应用程序显示目标应用页面，相比于默认打开都是同一页面，可以解决应用程序启动后显示首个应用页面固化且单一和灵活性差的问题，实现个性化确定目标应用页面的目的，提升用户使用体验。
在一些实施例中，所述根据所述预设页面确定模型的输出结果确定目标应用页面，包括：根据所述预设页面确定模型输出的评估分数确定目标应用页面，其中，不同候选应用页面对应不同的评估分数。这样设置的好处在于，建立不同候选应用页面与评估分数之间的对应关系，可以根据评估分数更加快速准确的确定目标应用页面，提高推荐用户感兴趣的目标应用页面的准确率。其中， 评估分数可以是数值分数。
所述预设页面确定模型通过以下方式训练得到：获取样本用户对应的训练样本数据，其中，所述训练样本数据包括所述样本用户在所述预设统计周期内使用所述预设应用程序过程中产生的第二数据和对应的评估分数标签，所述第二数据包括所述样本用户与第二用户之间的关联数据，所述样本用户和所述第二用户在所述预设应用程序中存在所述预设关联关系；将所述训练样本数据输入至预设神经网络模型，并计算对应的预设损失函数；基于所述预设损失函数对所述预设神经网络模型进行训练，得到预设页面确定模型。这样设置的好处在于，神经网络模型由网络拓扑节点特点和学习规则来表示，可以用于处理需要同时考虑许多因素和条件的、不精确和模糊的信息处理问题，通过对预设神经网络模型的训练，得到准确的预设页面确定模型，从而更加合理地确定目标应用页面。
示例性的，假设短视频应用程序有关注用户页面、直播页面和朋友页面，分别对应的评估分数标签为1、2和3，如果对一个样本用户而言，确定首个打开短视频应用程序的页面为关注用户页面时最佳，就给该样本用户对应的第二数据打标签为1，得到该样本用户对应的训练样本数据。经过预设神经网络模型训练之后，与该训练样本数据类似的数据经过模型处理后输出结果对应的评估分数就更接近1，当模型应用的时候，就可将当前用户的数据输入模型，如果输出的评估分数为1、或最接近于1、或1的置信度最高等，就确定首个打开短视频应用程序的页面为关注用户页面。
图2为本公开实施例提供的一种页面显示方法中预设页面确定模型的训练流程示意图。
201、获取样本用户对应的训练样本数据。
训练样本数据包括样本用户在预设统计周期内使用预设应用程序过程中产生的第二数据和对应的评估分数标签，所述第二数据包括样本用户与第二用户之间的关联数据，样本用户和第二用户在预设应用程序中存在预设关联关系。预设统计周期、预设关联关系以及关联数据的相关解释可参考上文相关内容，此处不再赘述。
示例性的，样本用户可以是使用预设应用程序的任意一个用户，可以根据实际训练需求进行选取，第二数据可以是样本用户在使用预设应用程序过程中产生的数据，所包含的内容可以与上述第一数据类似，区别在于第二数据为提前设置的样本数据。
示例性的，评估分数标签可以为预设神经网络模型在训练之前对第二数据 标注的分数标签。其中，评估分数标签对应的分数值可以通过调研或模拟实验等方式确定。例如，确定样本用户在产生第二数据的情况下，再次打开预设应用程序时最希望首次打开哪个应用页面，将该应用页面对应的评估分数确定为当前第二数据对应的评估分数标签。
在一些实施例中，所述评估分数标签基于在所述预设应用程序启动后首个显示的应用页面为对应的候选应用页面的情况下的以下至少一项确定：样本用户查看对应的候选应用页面的第一时长；样本用户通过对应的候选应用页面查看媒体内容的第一数量；样本用户当次使用所述预设应用程序的第二时长；以及样本用户当次使用所述预设应用程序查看媒体内容的第二数量。这样设置的好处在于，可以增加评估分数标签的准确性。第一时长可以为样本用户使用预设应用程序过程中，在首个显示的候选应用页面的停留总时长；第一数量可以为样本用户使用预设应用程序过程中，通过首个显示的候选应用页面查看的媒体内容的总数量；第二时长可以为样本用户当次使用预设应用程序经历的总时长；第二数量可以为样本用户当次使用预设应用程序查看媒体内容的总数量。其中，时长越长或数量越多可说明用户更喜欢或更习惯于浏览对应的页面，可根据对应的候选应用页面的评估分数来打标签。
示例性的，对于样本用户a来说，短视频应用启动后首个显示的应用页面分别为关注用户页面、直播页面和朋友页面的情况下，如果样本用户a查看的关注用户页面、直播页面和朋友页面时长分别为30分钟、5分钟和6分钟，则说明在首个显示的应用页面为关注用户页面的情况下，样本用户a能够在该页面中停留更长时间，可将样本用户a对应的第二数据的评估分数标签设置为1。
示例性的，对于样本用户b来说，短视频应用启动后首个显示的应用页面分别为关注用户页面、直播页面和朋友页面的情况下，如果样本用户b在三次使用短视频应用的过程中，观看视频或直播流的数量分别为10个、5个和50个，则说明在首个显示的应用页面为朋友页面的情况下，样本用户b能够在短视频应用中观看更多的视频内容，可将样本用户b对应的第二数据的评估分数标签设置为3。
202、将训练样本数据输入至预设神经网络模型，并计算对应的预设损失函数。
示例性的，本公开实施例中对预设神经网络模型中的模型结构和权重参数等不做限定，可根据实际需求进行设置。
示例性的，预设损失函数可以用于评价预设页面确定模型的性能。将训练样本数据输入至预设神经网络模型时，可以是将训练样本数据中的第二数据输 入至预设神经网络模型，根据模型的输出和当前输入的训练样本数据的评估分数标签来计算预设损失函数的取值。其中，损失函数可以用来评价模型的预测值和真实值不一样的程度，在本公开实施例中，可以是计算输出的评估分数与评估分数标签的相似度，损失函数的取值越高，也即两者相似程度越高，通常模型的性能越好。
203、基于预设损失函数对预设神经网络模型进行训练，得到预设页面确定模型。
示例性的，基于预设损失函数可以对预设神经网络模型中的权重参数进行调优，经过多次迭代调整，在达到预设收敛条件时，可以得到预设页面确定模型。其中，对预设收敛条件不做限定，可以是迭代次数达到预设次数阈值或预设损失函数值大于预设阈值等。
在一些实施例中，所述第一数据中还包括所述当前用户的历史交互数据。这样设置的好处在于，可以使得第一数据能够更加准确地反映用户对不同应用页面的偏好，提高预设页面确定模型输出结果的准确性。历史交互数据可以为当前用户使用预设应用程序过程中产生的交互数据，可包括用户与预设应用程序之间的交互数据，如操作数据，还可包括用户与其他用户之间进行交互的数据，例如当前用户当次使用预设应用程序之前为其他用户点赞的次数等。当前用户的历史交互数据保存于客户端。
在一些实施例中，所述历史交互数据包括以下至少一个：响应于用户操作进入候选应用页面的次数和/或频率；以及所述预设应用程序启动后的预设时长内，响应于用户操作进入候选应用页面的次数。这样设置的好处在于，可以更全面地了解用户所感兴趣的应用页面，提升第一数据的准确性以及模型输出结果的准确性。预设时长可以为预先设置的时间长度，如3分钟。
示例性的，用户操作进入候选应用页面的次数和/或频率数据可以包括过去的一周(预设统计周期)之内响应于当前用户通过点击页面标签等操作进入关注页面共5次或者每天1次；所述预设应用程序启动后的预设时长内，响应于用户操作进入候选应用页面的次数数据可以包括预设应用程序启动3分钟之内，响应于用户点击操作进入关注页面共5次。
在一些实施例中，所述关联数据包括以下至少一个：所述第一用户的数量；与所述当前用户之间的交互数据满足预设要求的第一用户的数量；所述当前用户查看所述第一用户发布的媒体内容的第三时长和/或第三数量；所述当前用户通过预设候选应用页面进入预设页面，并在所述预设页面停留的第四时长，其中，所述预设候选应用页面包括当前展示所述第一用户发布的媒体内容的候选 应用页面；以及所述当前用户的关于所述第一用户的未读信息的数量。这样设置的好处在于，可以更合理全面地得到当前用户使用预设应用程序过程中产生的第一数据。
示例性的，预设要求可以根据当前用户基于第一用户的关联页面产生的交互数据来设定。若当前用户与第一用户的交互频次达到预设频次阈值时，可认为满足预设要求。例如，当前用户在使用短视频应用程序过程中，关注第一用户，观看第一用户的作品内容，然后点赞第一用户的作品，并在第一用户的作品内容评论区评论，第一用户也与当前用户在评论区互动，那么由于当前用户与第一用户之间的互动逐渐增多，两者之间的关系逐渐由普通的关注与被关注关系可以变为满足预设要求的关注与被关注关系。第三时长可以为当前用户查看第一用户发布的媒体内容的总时长。第三数量可以为当前用户查看第一用户发布的媒体内容的总数量。预设候选应用页面可以为当前用户使用预设应用程序过程中观看的展示有第一用户发布的媒体内容的候选应用页面，第四时长可以为当前用户通过预设候选应用页面进入预设页面，并在预设页面停留的总时长。未读信息可以为预设应用程序中当前用户未读的第一用户发送的消息或者未读的第一用户发布的作品等。
示例性的，关联数据可以包括当前用户关注的用户数量(如100个)；可以包括与当前用户之间的交互数据满足预设要求的关注用户的数量(如10个)；可以包括当前用户查看关注用户发布的媒体内容的观看时长(如1小时)，或者当前用户查看关注用户发布的媒体内容数量(如15个)；还可以包括当前用户通过推荐页面进入一个关注用户的个人主页，并在该个人主页停留的时长(如15分钟)，其中，推荐页面当前展示该关注用户发布的媒体内容。上述数据可以作为第一数据输入预设页面确定模型用于确定目标应用页面。
在一些实施例中，至少一个候选应用页面中展示的媒体内容由所述第一用户发布。此时，该至少一个候选应用页面中不包含第一用户之外的其他用户发布的媒体内容。这样设置的好处在于，丰富候选应用页面的页面类型。示例性的，对于短视频应用来说，假设预设关联关系为当前用户关注第一用户，则至少一个候选应用页面可以是关注用户页面，在关注用户页面中仅包括当前用户关注的第一用户发布的多短视频，而不包括当前用户未关注的其他用户发布的短视频。
在一些实施例中，所述关联数据还包括：所述当前用户针对所述第一用户的关联事件的信息以及所述第一用户的预设事件信息。这样设置的好处在于，可以更全面地得到当前用户与第一用户之间的关联数据。关联事件例如可以包括媒体内容发布事件、群组创建事件或预设提醒事件等等。预设事件信息可以 为第一用户与关联事件有关的通知信息。示例性的，媒体内容发布事件可以包括直播开播，预设事件信息可以包括开播通知；媒体内容发布事件可以包括发布新作品，预设事件信息可以包括作品上新通知；预设提醒事件可以包括粉丝群发起的催促更新作品事件，预设事件信息可以包括参与催更的邀请信息。
图3为本公开实施例提供的一种页面显示方法的流程示意图，本公开实施例以上述实施例中的方案为基础进行说明，为了便于说明，下面以短视频应用为例，假设在短视频应用中预先设置了多个候选应用页面，分别为推荐页、关注页和直播页，在短视频应用启动时，可以智能地确定首个显示的应用页面。示例性的，推荐页用于播放任意用户的短视频、关注页用于播放当前用户关注的用户发布的短视频，直播页用于播放任意用户的直播流。该方法包括：
301、检测到短视频应用启动。
302、获取当前用户在预设统计周期内使用短视频应用过程中产生的第一数据。
示例性的，第一数据包括当前用户的历史交互数据，还包括当前用户与第一用户之间的关联数据。其中，当前用户在短视频应用中关注第一用户。
历史交互数据包括响应于用户操作进入候选应用页面的次数，还包括预设应用程序启动后的预设时长内，响应于用户操作进入候选应用页面的次数。例如，当前用户在最近一个月内，主动通过输入页面切换操作的方式进入推荐页、关注页和朋友页的次数分别为5次、30次和10次；短视频应用启动后的1分钟之内，主动通过输入页面切换操作的方式进入推荐页、关注页和朋友页的次数分别为0次、20次和2次。此外，历史交互数据还可以包括如当前用户在最近一个月内观看直播的总时长或观看短视频的总时长等等。
关联数据包括第一用户的数量，例如可以是当前用户当前关注的用户的总数量；和/或与当前用户之间的交互数据满足预设要求的第一用户的数量，例如在所有第一用户中，与当前用户的交互频次达到每周n次(n>0)以上的第一用户的数量；当前用户查看第一用户发布的媒体内容的第三时长和第三数量，例如，当前用户查看所有第一用户发布的短视频的总时长和短视频的总个数；当前用户通过预设候选应用页面进入预设页面，并在预设页面停留的第四时长，例如，当前用户通过关注页进入当前播放的短视频的发布者的个人主页，并在个人主页停留的时长；以及当前用户的关于第一用户的未读信息的数量，例如，第一用户发布的当前用户未观看过的短视频的数量。
303、将获取到的第一数据输入预设页面确定模型，并获取预设页面确定模型输出的评估分数。
304、根据预设页面确定模型输出的评估分数确定对应的目标应用页面，其中，不同候选应用页面对应不同的评估分数。
305、通过短视频应用显示目标应用页面。
图4为本公开实施例提供的一种页面显示方法的交互过程示意图，短视频应用程序启动之后，显示短视频应用程序启动页面401(例如广告页)，若通过预设页面确定模型确定目标应用页面为关注页，则可以在启动页面401显示完毕后，显示关注页402，也即短视频应用程序从启动页面401跳转到关注页402。
本公开实施例提供的页面显示方法，可应用于短视频应用程序，在短视频应用程序启动时，可以通过预设页面确定模型得到关于候选应用页面的评估分数，从多个候选应用页面中选择与评估分数最接近的评估分数标签的页面，作为目标应用页面推荐给当前用户。通过采用上述技术方案，解决了应用程序启动后显示首个应用页面固化且单一和灵活性差的问题，实现个性化确定目标应用页面的目的，提升用户使用体验。
图5为本公开实施例提供的一种页面显示装置的结构框图，该装置可由软件和/或硬件实现，一般可集成在电子设备中，可通过执行页面显示方法来进行页面显示。如图5所示，该装置包括：
第一数据获取模块501，设置为检测到预设应用程序启动时，获取当前用户在预设统计周期内使用所述预设应用程序过程中产生的第一数据，其中，所述第一数据包括所述当前用户与第一用户之间的关联数据，所述当前用户和所述第一用户在所述预设应用程序中存在预设关联关系；目标应用页面确定模块502，设置为获取到第一数据后，将所述第一数据输入至预设页面确定模型，并根据所述预设页面确定模型的输出结果确定目标应用页面，其中，所述预设页面确定模型用于确定本次启动后首个显示的应用页面，所述目标应用页面为所述预设应用程序中的多个候选应用页面中的一个，至少一个候选应用页面用于展示所述第一用户发布的媒体内容；目标应用页面显示模块503，设置为确定目标应用页面之后，通过所述预设应用程序显示所述目标应用页面。
本公开实施例中提供的页面显示装置，在用户打开预设应用程序时，可以通过预设页面确定模型得到评估分数，根据评估分数确定目标应用页面，解决了应用程序启动后显示首个应用页面固化且单一和灵活性差的问题，实现个性化确定目标应用页面的目的，提升用户体验。
一实施例中，所述第一数据中还包括所述当前用户的历史交互数据。
一实施例中，所述历史交互数据包括以下至少一个：响应于用户操作进入 候选应用页面的次数和/或频率；以及所述预设应用程序启动后的预设时长内，响应于用户操作进入候选应用页面的次数。
一实施例中，所述关联数据包括以下至少一个：所述第一用户的数量；与所述当前用户之间的交互数据满足预设要求的第一用户的数量；所述当前用户查看所述第一用户发布的媒体内容的第三时长和/或第三数量；所述当前用户通过预设候选应用页面进入预设页面，并在所述预设页面停留的第四时长，其中，所述预设候选应用页面包括当前展示所述第一用户发布的媒体内容的候选应用页面；以及所述当前用户的关于所述第一用户的未读信息的数量。
一实施例中，至少一个候选应用页面中展示的媒体内容由所述第一用户发布。
一实施例中，所述关联数据还包括：所述当前用户针对所述第一用户的关联事件的信息以及所述第一用户的预设事件信息。
一实施例中，目标应用页面确定模块502，设置为：
根据所述预设页面确定模型输出的评估分数确定目标应用页面，其中，不同候选应用页面对应不同的评估分数；其中，所述预设页面确定模型通过以下方式训练得到：获取样本用户对应的训练样本数据，其中，所述训练样本数据包括所述样本用户在所述预设统计周期内使用所述预设应用程序过程中产生的第二数据和对应的评估分数标签，所述第二数据包括所述样本用户与第二用户之间的关联数据，所述样本用户和所述第二用户在所述预设应用程序中存在所述预设关联关系；将所述训练样本数据输入至预设神经网络模型，并计算对应的预设损失函数；基于所述预设损失函数对所述预设神经网络模型进行训练，得到预设页面确定模型。
一实施例中，该装置还包括：评估分数标签确定模块，设置为所述评估分数标签基于在所述预设应用程序启动后首个显示的应用页面为对应的候选应用页面的情况下的以下至少一项确定：样本用户查看对应的候选应用页面的第一时长；样本用户通过对应的候选应用页面查看媒体内容的第一数量；样本用户当次使用所述预设应用程序的第二时长；以及样本用户当次使用所述预设应用程序查看媒体内容的第二数量。
下面参考图6，其示出了适于用来实现本公开实施例的电子设备600的结构示意图。本公开实施例中的电子设备600可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、个人数字助理(Personal Digital Assistant，PDA)、平板电脑(Portable Android Device，PAD)、便携式多媒体播放器(Portable Media Player，PMP)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字 电视(Television，TV)、台式计算机等等的固定终端。图6示出的电子设备600仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
如图6所示，电子设备600可以包括处理装置(例如中央处理器、图形处理器等)601，其可以根据存储在只读存储器(Read-Only Memory，ROM)602中的程序或者从存储装置608加载到随机访问存储器(Random Access Memory，RAM)603中的程序而执行多种适当的动作和处理。在RAM 603中，还存储有电子设备600操作所需的多种程序和数据。处理装置601、ROM 602以及RAM 603通过总线604彼此相连。输入/输出(Input/Output，I/O)接口605也连接至总线604。
通常，以下装置可以连接至I/O接口605：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置606；包括例如液晶显示器(Liquid Crystal Display，LCD)、扬声器、振动器等的输出装置607；包括例如磁带、硬盘等的存储装置608；以及通信装置609。通信装置609可以允许电子设备600与其他设备进行无线或有线通信以交换数据。虽然图6示出了具有多种装置的电子设备600，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。
根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在非暂态计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信装置609从网络上被下载和安装，或者从存储装置608被安装，或者从ROM 602被安装。在该计算机程序被处理装置601执行时，执行本公开实施例的方法中限定的上述功能。
本公开上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、RAM、ROM、可擦式可编程只读存储器(Erasable Programmable Read-Only Memory，EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(Compact Disc Read-Only Memory，CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算 机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、射频(Radio Frequency，RF)等等，或者上述的任意合适的组合。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。
上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：检测到预设应用程序启动时，获取当前用户在预设统计周期内使用预设应用程序过程中产生的第一数据，其中，第一数据包括当前用户与第一用户之间的关联数据，当前用户和第一用户在预设应用程序中存在预设关联关系；将第一数据输入至预设页面确定模型，并根据预设页面确定模型的输出结果确定目标应用页面，其中，预设页面确定模型用于确定本次启动后首个显示的应用页面，目标应用页面为预设应用程序中的多个候选应用页面中的一个，至少一个候选应用页面用于展示第一用户发布的媒体内容；通过预设应用程序显示目标应用页面。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码，上述程序设计语言包括但不限于面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(Local Area Network，LAN)或广域网(Wide Area Network，WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开多种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的 是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施例中所涉及到的模块可以通过软件的方式实现，也可以通过硬件的方式来实现。其中，模块的名称在一种情况下并不构成对该模块本身的限定，例如，第一数据获取模块还可以被描述为“检测到预设应用程序启动时，获取第一数据的模块”。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如，非限制性地，可以使用的示范类型的硬件逻辑部件包括：现场可编程门阵列(Field Programmable Gate Array，FPGA)、专用集成电路(Application Specific Integrated Circuit，ASIC)、专用标准产品(Application Specific Standard Parts，ASSP)、片上系统(System on Chip，SOC)、复杂可编程逻辑设备(Complex Programming Logic Device，CPLD)等等。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、RAM、ROM、EPROM或快闪存储器、光纤、CD-ROM、光学储存设备、磁储存设备、或上述内容的任何合适组合。
根据本公开的一个或多个实施例，提供了一种页面显示方法，包括：
检测到预设应用程序启动时，获取当前用户在预设统计周期内使用所述预设应用程序过程中产生的第一数据，其中，所述第一数据包括所述当前用户与第一用户之间的关联数据，所述当前用户和所述第一用户在所述预设应用程序中存在预设关联关系；
将所述第一数据输入至预设页面确定模型，并根据所述预设页面确定模型的输出结果确定目标应用页面，其中，所述预设页面确定模型用于确定本次启动后首个显示的应用页面，所述目标应用页面为所述预设应用程序中的多个候选应用页面中的一个，至少一个候选应用页面用于展示所述第一用户发布的媒体内容；
通过所述预设应用程序显示所述目标应用页面。
根据本公开的一个或多个实施例，所述根据所述预设页面确定模型的输出结果确定目标应用页面，包括：
根据所述预设页面确定模型输出的评估分数确定目标应用页面，其中，不同候选应用页面对应不同的评估分数；
其中，所述预设页面确定模型通过以下方式训练得到：
获取样本用户对应的训练样本数据，其中，所述训练样本数据包括所述样本用户在所述预设统计周期内使用所述预设应用程序过程中产生的第二数据和对应的评估分数标签，所述第二数据包括所述样本用户与第二用户之间的关联数据，所述样本用户和所述第二用户在所述预设应用程序中存在所述预设关联关系；
将所述训练样本数据输入至预设神经网络模型，并计算对应的预设损失函数；
基于所述预设损失函数对所述预设神经网络模型进行训练，得到预设页面确定模型。
根据本公开的一个或多个实施例，所述评估分数标签基于在所述预设应用程序启动后首个显示的应用页面为对应的候选应用页面的情况下的以下至少一项确定：
样本用户查看对应的候选应用页面的第一时长；
样本用户通过对应的候选应用页面查看媒体内容的第一数量；
样本用户当次使用所述预设应用程序的第二时长；以及
样本用户当次使用所述预设应用程序查看媒体内容的第二数量。
根据本公开的一个或多个实施例，所述第一数据中还包括所述当前用户的历史交互数据。
根据本公开的一个或多个实施例，所述历史交互数据包括以下至少一个：
响应于用户操作进入候选应用页面的次数和/或频率；以及
所述预设应用程序启动后的预设时长内，响应于用户操作进入候选应用页面的次数。
根据本公开的一个或多个实施例，所述关联数据包括以下至少一个：
所述第一用户的数量；
与所述当前用户之间的交互数据满足预设要求的第一用户的数量；
所述当前用户查看所述第一用户发布的媒体内容的第三时长和/或第三数量；
所述当前用户通过预设候选应用页面进入预设页面，并在所述预设页面停留的第四时长，其中，所述预设候选应用页面包括当前展示所述第一用户发布的媒体内容的候选应用页面；以及
所述当前用户的关于所述第一用户的未读信息的数量。
根据本公开的一个或多个实施例，至少一个候选应用页面中展示的媒体内容由所述第一用户发布。
根据本公开的一个或多个实施例，所述关联数据还包括：所述当前用户针对所述第一用户的关联事件的信息以及所述第一用户的预设事件信息。
根据本公开的一个或多个实施例，提供了一种页面显示装置，包括：
第一数据获取模块，设置为检测到预设应用程序启动时，获取当前用户在预设统计周期内使用所述预设应用程序过程中产生的第一数据，其中，所述第一数据包括所述当前用户与第一用户之间的关联数据，所述当前用户和所述第一用户在所述预设应用程序中存在预设关联关系；
目标应用页面确定模块，设置为获取到第一数据后，将所述第一数据输入至预设页面确定模型，并根据所述预设页面确定模型的输出结果确定目标应用页面，其中，所述预设页面确定模型用于确定本次启动后首个显示的应用页面，所述目标应用页面为所述预设应用程序中的多个候选应用页面中的一个，至少一个候选应用页面用于展示所述第一用户发布的媒体内容；
目标应用页面显示模块，设置为确定目标应用页面之后，通过所述预设应用程序显示所述目标应用页面。
此外，虽然采用特定次序描绘了多个操作，但是这不应当理解为要求这些操作以所示出的特定次序或以顺序次序执行来执行。在一定环境下，多任务和并行处理可能是有利的。同样地，虽然在上面论述中包含了多个实现细节，但是这些不应当被解释为对本公开的范围的限制。在单独的实施例的上下文中描述的一些特征还可以组合地实现在单个实施例中。相反地，在单个实施例的上下文中描述的多种特征也可以单独地或以任何合适的子组合的方式实现在多个实施例中。

Claims (12)

  1. 一种页面显示方法，包括：
    检测到预设应用程序启动时，获取当前用户在预设统计周期内使用所述预设应用程序过程中产生的第一数据，其中，所述第一数据包括所述当前用户与第一用户之间的关联数据，所述当前用户和所述第一用户在所述预设应用程序中存在预设关联关系；
    将所述第一数据输入至预设页面确定模型，并根据所述预设页面确定模型的输出结果确定目标应用页面，其中，所述预设页面确定模型用于确定本次启动后首个显示的应用页面，所述目标应用页面为所述预设应用程序中的多个候选应用页面中的一个，至少一个候选应用页面用于展示所述第一用户发布的媒体内容；
    通过所述预设应用程序显示所述目标应用页面。
  2. 根据权利要求1所述的方法，其中，所述根据所述预设页面确定模型的输出结果确定目标应用页面，包括：
    根据所述预设页面确定模型输出的评估分数确定所述目标应用页面，其中，不同候选应用页面对应不同的评估分数；
    其中，所述预设页面确定模型通过以下方式训练得到：
    获取样本用户对应的训练样本数据，其中，所述训练样本数据包括所述样本用户在所述预设统计周期内使用所述预设应用程序过程中产生的第二数据和所述第二数据对应的评估分数标签，所述第二数据包括所述样本用户与第二用户之间的关联数据，所述样本用户和所述第二用户在所述预设应用程序中存在所述预设关联关系；
    将所述训练样本数据输入至预设神经网络模型，并计算所述预设神经网络模型对应的预设损失函数；
    基于所述预设损失函数对所述预设神经网络模型进行训练，得到预设页面确定模型。
  3. 根据权利要求2所述的方法，其中，所述评估分数标签基于在所述预设应用程序启动后首个显示的应用页面为对应的候选应用页面的情况下的以下至少一项确定：
    所述样本用户查看所述对应的候选应用页面的第一时长；
    所述样本用户通过所述对应的候选应用页面查看媒体内容的第一数量；
    所述样本用户当次使用所述预设应用程序的第二时长；以及
    所述样本用户当次使用所述预设应用程序查看媒体内容的第二数量。
  4. 根据权利要求1所述的方法，其中，所述第一数据中还包括所述当前用户的历史交互数据。
  5. 根据权利要求4所述的方法，其中，所述历史交互数据包括以下至少一个：
    响应于用户操作进入候选应用页面的次数和频率中的至少之一；以及
    所述预设应用程序启动后的预设时长内，响应于用户操作进入候选应用页面的次数。
  6. 根据权利要求1所述的方法，其中，所述关联数据包括以下至少一个：
    所述第一用户的数量；
    与所述当前用户之间的交互数据满足预设要求的第一用户的数量；
    所述当前用户查看所述第一用户发布的媒体内容的第三时长和第三数量中的至少之一；
    所述当前用户通过预设候选应用页面进入预设页面，并在所述预设页面停留的第四时长，其中，所述预设候选应用页面包括当前展示所述第一用户发布的媒体内容的候选应用页面；以及
    所述当前用户的关于所述第一用户的未读信息的数量。
  7. 根据权利要求6所述的方法，其中，所述至少一个候选应用页面中展示的媒体内容由所述第一用户发布。
  8. 根据权利要求6所述的方法，其中，所述关联数据还包括：所述当前用户针对所述第一用户的关联事件的信息以及所述第一用户的预设事件信息。
  9. 一种页面显示装置，包括：
    第一数据获取模块，设置为检测到预设应用程序启动时，获取当前用户在预设统计周期内使用所述预设应用程序过程中产生的第一数据，其中，所述第一数据包括所述当前用户与第一用户之间的关联数据，所述当前用户和所述第一用户在所述预设应用程序中存在预设关联关系；
    目标应用页面确定模块，设置为获取到第一数据后，将所述第一数据输入至预设页面确定模型，并根据所述预设页面确定模型的输出结果确定目标应用页面，其中，所述预设页面确定模型用于确定本次启动后首个显示的应用页面，所述目标应用页面为所述预设应用程序中的多个候选应用页面中的一个，至少一个候选应用页面用于展示所述第一用户发布的媒体内容；
    目标应用页面显示模块，设置为确定目标应用页面之后，通过所述预设应用程序显示所述目标应用页面。
  10. 根据权利要求9所述的装置，还包括：用于执行如权利要求2-8中任一项所述的方法的模块。
  11. 一种电子设备，包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，其中，所述处理器执行所述计算机程序时实现如权利要求1-8中任一项所述的页面显示方法。
  12. 一种计算机可读存储介质，存储有计算机程序，所述程序被处理器执行时实现如权利要求1-8中任一项所述的页面显示方法。
PCT/CN2022/121212 2021-10-08 2022-09-26 页面显示方法、装置、设备及存储介质 WO2023056850A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111171765.8A CN115964553A (zh) 2021-10-08 2021-10-08 页面显示方法、装置、设备及存储介质
CN202111171765.8 2021-10-08

Publications (1)

Publication Number Publication Date
WO2023056850A1 true WO2023056850A1 (zh) 2023-04-13

Family

ID=85803894

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/121212 WO2023056850A1 (zh) 2021-10-08 2022-09-26 页面显示方法、装置、设备及存储介质

Country Status (2)

Country Link
CN (1) CN115964553A (zh)
WO (1) WO2023056850A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117251162A (zh) * 2023-10-18 2023-12-19 广东抱谷科技有限公司 基于埋点数据分析技术的排版布局方法、设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170293403A1 (en) * 2016-04-11 2017-10-12 Beijing Xiaomi Mobile Software Co., Ltd. Method and device for displaying pages in application program and computer-readable medium
CN110489654A (zh) * 2019-09-12 2019-11-22 五八有限公司 获取用户兴趣度的方法、装置、电子设备及存储介质
CN112732374A (zh) * 2019-10-28 2021-04-30 北京达佳互联信息技术有限公司 一种页面展示方法、展示装置、电子设备及存储介质
CN112732375A (zh) * 2019-10-28 2021-04-30 北京达佳互联信息技术有限公司 启动页面的确定方法、装置、存储介质及服务器

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170293403A1 (en) * 2016-04-11 2017-10-12 Beijing Xiaomi Mobile Software Co., Ltd. Method and device for displaying pages in application program and computer-readable medium
CN110489654A (zh) * 2019-09-12 2019-11-22 五八有限公司 获取用户兴趣度的方法、装置、电子设备及存储介质
CN112732374A (zh) * 2019-10-28 2021-04-30 北京达佳互联信息技术有限公司 一种页面展示方法、展示装置、电子设备及存储介质
CN112732375A (zh) * 2019-10-28 2021-04-30 北京达佳互联信息技术有限公司 启动页面的确定方法、装置、存储介质及服务器

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117251162A (zh) * 2023-10-18 2023-12-19 广东抱谷科技有限公司 基于埋点数据分析技术的排版布局方法、设备及存储介质

Also Published As

Publication number Publication date
CN115964553A (zh) 2023-04-14

Similar Documents

Publication Publication Date Title
CN111711828B (zh) 一种信息处理方法、装置和电子设备
US10148535B2 (en) Mobile device session analyzer
US20190130185A1 (en) Visualization of Tagging Relevance to Video
US20170085519A1 (en) Interactive Content in a Messaging Platform
CN111580921B (zh) 内容创作方法及设备
US20190324779A1 (en) Using salience rankings of entities and tasks to aid computer interpretation of natural language input
US20120077175A1 (en) Time-indexed discussion enabled video education
EP4213005A1 (en) Method and apparatus for music sharing, electronic device, and storage medium
CN106970949A (zh) 一种信息推荐方法及装置
US20220318306A1 (en) Video-based interaction implementation method and apparatus, device and medium
US20240163517A1 (en) Interaction method and device, storage medium and computer program product
CN110392312B (zh) 群聊构建方法、系统、介质和电子设备
CN114003326A (zh) 消息处理方法、装置、设备及存储介质
CN113849258B (zh) 内容展示方法、装置、设备及存储介质
US11991602B2 (en) System and method for location-based content delivery and visualization
CN115190366B (zh) 一种信息展示方法、装置、电子设备、计算机可读介质
WO2023056850A1 (zh) 页面显示方法、装置、设备及存储介质
US20240079002A1 (en) Minutes of meeting processing method and apparatus, device, and medium
US20150332606A1 (en) Real-time, interactive, remote athletic training
US11095945B2 (en) Information processing device, method, and program
WO2023134558A1 (zh) 交互方法、装置、电子设备、存储介质和程序产品
WO2023005508A1 (zh) 一种问卷投放方法、系统、设备、介质及产品
CN114630136B (zh) 视频界面交互方法、装置、电子设备和计算机可读介质
CN118051157A (zh) 媒体内容处理方法、装置、设备、可读存储介质及产品
CN114780187A (zh) 提示方法及设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22877869

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE