Method and device for displaying time machine in streaming media application program
By training machine learning algorithms in streaming media applications, building a time machine content recommendation model and personalized content recommendations for target users, it solves the problem that time machine does not have dynamic theme display in the existing technology, and improves user experience and content Consumption satisfaction.
Patent Information
- Application Number
- CN202411334751.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-24
- Publication Date
- 2025-01-10
AI Technical Summary
In the prior art, the time machine of the video and audio app does not have dynamic theme displays for user portraits and content portraits, resulting in poor user experience.
By obtaining user data and content data in streaming media applications, training preset machine learning algorithms, building a time machine content recommendation model, personalized content recommendations for target users, and dynamically generate time machine content.
It realizes accurate matching of time machine content, improves user experience, and enhances the relevance and satisfaction of content consumption.
Smart Images
Figure CN119299787A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a method and device for displaying a time machine in a streaming media application. Background Art
[0002] With the development of technology, users of major Apps (Applications) are very fond of their annual summaries of a certain App, and by the end of the year, users have "shown off" their "transcripts". At present, all video and audio App software have implemented annual summaries based on App data such as user viewing and listening. The annual summary is called a "time machine" in the field. The time machine can display the user's summary data for the year or a period of time, including but not limited to the data of the episodes watched, the number of songs listened to, the longest-watched episode information and other customized information. However, in the current technology, the implementation of the time machine of each video and audio App uses a fixed template, and then the user's summary data for a certain period of time is customized and filled into the fixed template to form a time machine. Therefore, the current technology for the implementation of the time machine does not have a dynamic time machine theme display for user portraits and content portraits, and the user experience is poor. Summary of the invention
[0003] The present application provides a method and device for displaying a time machine in a streaming media application to solve the problem that the current technology for implementing a time machine does not have a dynamic time machine theme display for user portraits and content portraits, resulting in a poor user experience.
[0004] In a first aspect, the present application provides a method for displaying a time machine in a streaming media application, the method comprising:
[0005] Obtain user data of all users and content data of all contents in the streaming application;
[0006] Training a preset machine learning algorithm based on the user data of all users and the content data of all content to obtain a time machine content recommendation model;
[0007] For any target user, user data, content data and the time machine content recommendation model of the target user are used to obtain the display content of the time machine of the target user in the streaming media application;
[0008] The time machine is recommended and displayed to the target user according to the displayed content of the time machine.
[0009] As an optional embodiment, the training of a preset machine learning algorithm according to the user data of all users and the content data of all contents to obtain a time machine content recommendation model includes:
[0010] Performing denoising processing on the user data and the content data;
[0011] Performing feature extraction on the user data and the content data after the denoising process respectively to obtain a user feature vector and a content feature vector;
[0012] The user feature vector and the content feature vector are used to train a preset machine learning algorithm to obtain a time machine content recommendation model.
[0013] As an optional embodiment, for any target user, obtaining the display content of the time machine of the target user in the streaming media application by combining the user data, content data and the time machine content recommendation model of the target user includes:
[0014] For any target user, feature extraction is performed on the user data of the target user and the content data of the target user respectively, so as to construct a user profile of the target user and a content profile of the target user;
[0015] The user portrait of the target user and the content portrait of the target user are input into the time machine content recommendation model to obtain the display content of the time machine of the target user in the streaming media application.
[0016] As an optional embodiment, for any target user, extracting features from the user data of the target user and the content data of the target user respectively to construct a user profile of the target user and a content profile of the target user includes:
[0017] extracting data features of the user data of the target user and the content data of the target user respectively;
[0018] Calculating a first similarity between a data feature of the user data of the target user and each of the user feature vectors, and calculating a second similarity between a data feature of the content data of the target user and each of the content feature vectors;
[0019] Determine the user feature vector corresponding to the data feature of the user data of the target user based on the first similarity to obtain a user portrait of the target user, and determine the content feature vector corresponding to the data feature of the content data of the target user based on the second similarity to obtain a content portrait of the target user.
[0020] As an optional embodiment, determining the user feature vector corresponding to the data feature of the user data of the target user according to the first similarity to obtain the user portrait of the target user, and determining the content feature vector corresponding to the data feature of the content data of the target user according to the second similarity to obtain the content portrait of the target user, includes:
[0021] Sort the first similarities from high to low, and determine the user feature vector with the highest first similarity ranking as the user profile of the target user;
[0022] And sorting the second similarities from high to low, and determining the content feature vector with the highest second similarity as the content portrait of the target user.
[0023] As an optional embodiment, the method further includes:
[0024] After the preset machine learning algorithm is trained according to the user data of all users and the content data of all contents to obtain the time machine content recommendation model, the model parameters of the time machine content recommendation model are tuned by a cross-validation algorithm and an A / B random testing algorithm.
[0025] As an optional embodiment, the recommending and displaying the time machine to the target user according to the displayed content of the time machine includes:
[0026] Obtaining a first time machine for the target user according to the time value in the displayed content of the time machine and the historical viewing content of the target user in any time range;
[0027] The first time machine of the target user is recommended and displayed to the target user.
[0028] As an optional embodiment, the method further includes:
[0029] For any target user, determine the target user's preferred content in the current time period according to the target user's content data;
[0030] The recommending and displaying the time machine to the target user according to the displayed content of the time machine further includes:
[0031] Obtaining a second time machine for the target user according to the time value in the displayed content of the time machine and the historical viewing content of the target user in any time range;
[0032] According to the target user's preference content of the current time period, the display sorting content of the first time machine of the target user is adjusted to obtain the third time machine of the target user;
[0033] The third time machine of the target user is recommended and displayed to the target user.
[0034] As an optional embodiment, the method further includes:
[0035] A user graphical interface is displayed to the target user, so that the target user can adjust the display content and / or the sorting method of the display content of the first time machine or the third time machine.
[0036] In a second aspect, the present application provides a display device for a time machine in a streaming media application, the device comprising:
[0037] A data acquisition module, used to acquire user data of all users and content data of all contents in the streaming media application;
[0038] A model training module, used to train a preset machine learning algorithm based on the user data of all users and the content data of all contents to obtain a time machine content recommendation model;
[0039] A content recommendation module, for obtaining, for any target user, the display content of the time machine of the target user in the streaming media application by combining the user data, content data and the time machine content recommendation model of the target user;
[0040] The time machine display module is used to recommend and display the time machine to the target user according to the display content of the time machine.
[0041] In a third aspect, the present application provides an electronic device, comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; at least one memory connected to the at least one bus, wherein the processor is configured to:
[0042] Obtain user data of all users and content data of all contents in the streaming application;
[0043] Training a preset machine learning algorithm based on the user data of all users and the content data of all content to obtain a time machine content recommendation model;
[0044] For any target user, user data, content data and the time machine content recommendation model of the target user are used to obtain the display content of the time machine of the target user in the streaming media application;
[0045] The time machine is recommended and displayed to the target user according to the displayed content of the time machine.
[0046] In a fourth aspect, the present application further provides a computer storage medium storing computer executable instructions, wherein the computer executable instructions are used to execute the method for displaying a time machine in a streaming media application as described in any one of the above items of the present application.
[0047] The above-mentioned technical scheme provided by the embodiment of the present application has the following advantages over the prior art: the method provided by the embodiment of the present application, through a large amount of user data and content data in the streaming media application, trains a time machine content recommendation model, thereby using a machine learning algorithm to implement the recommendation of time machine content, and realizes more refined analysis of user data, which helps to accurately locate user preferences, and then inputs the user data and content data of the target user into the time machine content recommendation model to obtain the display content of the time machine corresponding to the target user, thereby realizing the time machine of the target user, so that the time machine of the target user can more accurately match the preferences of the target user, instead of displaying in a fixed template, thereby enhancing the user experience, and further improving the relevance and satisfaction of content consumption in the streaming media application. BRIEF DESCRIPTION OF THE DRAWINGS
[0048] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0049] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0050] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.
[0051] Figure 1 One of the flowcharts of a method for displaying a time machine in a streaming media application provided in an embodiment of the present application;
[0052] Figure 2 A second flow chart of a method for displaying a time machine in a streaming media application provided in an embodiment of the present application;
[0053] Figure 3 A third flowchart of a method for displaying a time machine in a streaming media application provided in an embodiment of the present application;
[0054] Figure 4A structural block diagram of a display device of a time machine in a streaming media application provided in an embodiment of the present application;
[0055] Figure 5 A structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0056] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0057] The disclosure below provides many different embodiments or examples to realize the different structures of the present application. In order to simplify the disclosure of the present application, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present application. In addition, the present application can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.
[0058] In order to solve the technical problem that the implementation of time machine in the prior art lacks dynamic time machine theme display for user portraits and content portraits, resulting in poor user experience, the present application provides a method and device for displaying a time machine in a streaming media application, which can enable the time machine of the target user to more accurately match the preferences of the target user, rather than displaying it in a fixed template.
[0059] In order to enable those skilled in the art to clearly and accurately understand the technical solutions of the embodiments of the present application, the technical solutions of the embodiments of the present application are described in detail below in conjunction with the accompanying drawings.
[0060] Figure 1 The following is a flow chart of a method for displaying a time machine in a streaming media application provided by an embodiment of the present application. Figure 1 As shown, the method for displaying a time machine in a streaming media application in an embodiment of the present application may include the following steps:
[0061] Step 101: Obtain user data of all users and content data of all content in a streaming media application.
[0062] In the embodiment of the present application, the user's viewing history, preferences, ratings, and search and other interactive data can be recorded through a log system or tracking technology to obtain user data; and the metadata of movies, TV series, and other content in the streaming media application can be extracted and recorded, including type (such as comedy, action, etc.), release date, actors, directors, duration, etc., to obtain content data. The content data can also include user feedback (ratings, comments) on the content.
[0063] Step 102 , training a preset machine learning algorithm based on the user data of all users and the content data of all content to obtain a time machine content recommendation model.
[0064] In some embodiments of the present application, the user data and content data can be denoised, and the denoised user data and content data can be feature extracted to obtain user feature vectors and content feature vectors, and the user feature vectors and content feature vectors are used to train the preset machine learning algorithm to obtain the time machine content recommendation model. The user data and content data are cleaned to remove outliers and noise, and the data is normalized to make it more suitable for machine learning algorithms. Exemplarily, key features can be extracted from user data by machine learning algorithms or statistical methods to obtain user feature vectors. The user feature vectors may include user preference categories, active time, feedback patterns, etc. On the other hand, the description and comment text in the content data can be processed by a natural language processing (NLP) algorithm, and image processing technology can be used to analyze content posters and trailers to obtain visual features, thereby obtaining content feature vectors. Through this embodiment, valuable features can be extracted from the data for training models.
[0065] Among them, the preset machine learning algorithm can be, for example, a collaborative filtering model, a deep learning recommendation model or a hybrid model. In an embodiment of the present application, a suitable machine learning model can be selected from the collaborative filtering model, the deep learning recommendation model or the hybrid model according to the data characteristics.
[0066] In other embodiments of the present application, after a preset machine learning algorithm is trained based on the user data of all users and the content data of all content to obtain the time machine content recommendation model, the model parameters of the time machine content recommendation model can be tuned through a cross-validation algorithm and an A / B random testing algorithm to obtain the optimal model parameter settings to maximize the recommendation quality of the time machine's displayed content.
[0067] Step 103 , for any target user, the user data, content data and the time machine content recommendation model of the target user are combined to obtain the display content of the time machine of the target user in the streaming media application.
[0068] In some embodiments, the user data and content data of the target user may be subjected to feature extraction processing to obtain key features of the user data and content data of the target user, and input into the time machine content recommendation model, and then the key features may be used to infer the display content of the time machine of the target user in the streaming media application, so as to better locate the target user's content genre, style and user interaction data preferences.
[0069] Step 104 , recommending and displaying the time machine to the target user based on the displayed content of the time machine.
[0070] The display content of the time machine may include, for example, a time range and a specific time value, and also include the historical viewing content of the target user within the time range, and the historical viewing content may be displayed in the order of the time values. In other embodiments, the latest viewing content may be combined with the target user's latest and preferred viewing content within the time range, and the latest viewing content may be highlighted. For example, if the target user frequently watches documentaries recently, the documentary display may be highlighted in the time machine or arranged in the position before the time machine.
[0071] Figure 2 The second flowchart of a method for displaying a time machine in a streaming media application provided in an embodiment of the present application.
[0072] Step 101: Obtain user data of all users and content data of all content in a streaming media application.
[0073] For details, please refer to Figure 1 The detailed description of step 101 is omitted here for the sake of brevity.
[0074] Step 102 , training a preset machine learning algorithm based on the user data of all users and the content data of all content to obtain a time machine content recommendation model.
[0075] For details, please refer to Figure 1 The detailed description of step 102 is omitted here for the sake of brevity.
[0076] Step 1031 , for any target user, feature extraction is performed on the user data of the target user and the content data of the target user respectively, so as to construct a user portrait of the target user and a content portrait of the target user.
[0077] As an embodiment of the present application, data features of the target user's user data and the target user's content data can be extracted respectively, and a first similarity between the data features of the target user's user data and each user feature vector can be calculated, as well as a second similarity between the data features of the target user's content data and each content feature vector can be calculated. A user feature vector corresponding to the data features of the target user's user data can be determined based on the first similarity to obtain a user portrait of the target user, and a content feature vector corresponding to the data features of the target user's content data can be determined based on the second similarity to obtain a content portrait of the target user.
[0078] As an optional embodiment, the user feature vector with the highest first similarity ranking is sorted from high to low according to the first similarity, and is determined as the user portrait of the target user; and the content feature vector with the highest second similarity ranking is sorted from high to low according to the second similarity, and is determined as the content portrait of the target user.
[0079] The user portrait obtained through step 1031 of this embodiment can better locate the user's preferences and behavioral characteristics, and the content portrait obtained can better locate the content's genre, style and user interaction data.
[0080] Step 1032: Input the user portrait of the target user and the content portrait of the target user into the time machine content recommendation model to obtain the display content of the time machine of the target user in the streaming media application.
[0081] The user portrait of the target user and the content portrait of the target user can both be represented in the form of feature vectors, so that by inputting the feature vectors of both into the time machine content recommendation model, the display content of the time machine of the target user in the streaming media application can be obtained.
[0082] Step 104 , recommending and displaying the time machine to the target user based on the displayed content of the time machine.
[0083] For details, please refer to Figure 1 The detailed description of step 104 is omitted here for the sake of brevity.
[0084] Figure 3 The third flowchart of a method for displaying a time machine in a streaming media application provided in an embodiment of the present application.
[0085] Step 101: Obtain user data of all users and content data of all content in a streaming media application.
[0086] For details, please refer to Figure 1 The detailed description of step 101 is omitted here for the sake of brevity.
[0087] Step 102 , training a preset machine learning algorithm based on the user data of all users and the content data of all content to obtain a time machine content recommendation model.
[0088] For details, please refer to Figure 1 The detailed description of step 102 is omitted here for the sake of brevity.
[0089] Step 1031 , for any target user, feature extraction is performed on the user data of the target user and the content data of the target user respectively, so as to construct a user portrait of the target user and a content portrait of the target user.
[0090] For details, please refer to Figure 2 The detailed description of step 1031 is omitted here for the sake of brevity.
[0091] Step 1032: Input the user portrait of the target user and the content portrait of the target user into the time machine content recommendation model to obtain the display content of the time machine of the target user in the streaming media application.
[0092] For details, please refer to Figure 2 The detailed description of step 1032 is omitted here for the sake of brevity.
[0093] Step 1041 , obtaining a first time machine for the target user according to the time value in the display content of the time machine and the historical viewing content of the target user in any time range.
[0094] The display content of the time machine may include time values and the target user's historical viewing content within a certain time range. The target user's historical viewing content within the time range may be displayed and arranged in the order of time values, thereby forming a first time machine, that is, the target user's time machine.
[0095] Step 1042 , recommending and displaying the first time machine of the target user to the target user.
[0096] After the first time machine is determined, the first time machine may be displayed in a graphical user interface of a streaming media application used by the target user.
[0097] As another optional embodiment of the embodiment of the present application, the method described in the embodiment of the present application may also include step 105, for any target user, determining the target user's preferred content in the current time period based on the target user's content data.
[0098] On the basis of step 105, step 104 may specifically include the following steps:
[0099] Step 1043, obtaining a second time machine for the target user according to the time value in the display content of the time machine and the historical viewing content of the target user in any time range.
[0100] Step 1044, according to the target user's preference content of the current time period, adjust the display sorting content of the target user's first time machine to obtain the target user's third time machine.
[0101] Step 1045 , recommending and displaying the third time machine of the target user to the target user.
[0102] For example, when user A logs in to a streaming media application, such as a video app, a time machine recommendation list of mainly comedy and action content can be dynamically generated based on user A's viewing history using the aforementioned method embodiment. The content based on user A's preferences will be arranged at the front of the time machine display page, thereby improving user satisfaction and platform usage time. Other content types that do not meet user A's core preferences, such as documentaries or science fiction, may also appear in the recommendation list, but will usually be placed at the back. In this way, user A can be the first to access the content he is most interested in when visiting the time machine.
[0103] exist Figure 3 On the basis of the illustrated method embodiment, the embodiment of the present application can further display a user graphical interface to the target user, so that the target user can adjust the display content and / or the sorting method of the display content of the first time machine or the third time machine.
[0104] Through this embodiment, the arrangement order of the time machine content on the user interface can be adjusted in real time based on the user's instant feedback or the latest interactive behavior, and the length of each content module in the time machine can be adjusted based on user feedback and preferences. Through the embodiment of the present application, methods such as sliding ignore and instant scoring can be used to more quickly respond to changes in user preferences, thereby generating a time machine that is more suitable for user preferences.
[0105] To summarize, the method provided in the embodiment of the present application uses a large amount of user data and content data in the streaming media application to train a time machine content recommendation model, thereby using a machine learning algorithm to implement the recommendation of time machine content and achieve more refined analysis of user data, which helps to accurately locate user preferences. The user data and content data of the target user are then input into the time machine content recommendation model to obtain the display content of the time machine corresponding to the target user, thereby realizing the target user's time machine, so that the target user's time machine can more accurately match the target user's preferences, rather than using a fixed template for display, thereby enhancing the user experience and thereby improving the relevance and satisfaction of content consumption in streaming media applications.
[0106] Correspondingly, an embodiment of the present application also provides a display device for a time machine in a streaming media application. Figure 4 This is a structural block diagram of a display device of a time machine in a streaming media application provided in an embodiment of the present application. Figure 4 As shown, the display device of the time machine in the streaming media application in the embodiment of the present application may include:
[0107] A data acquisition module 201 is used to acquire user data of all users and content data of all contents in the streaming media application;
[0108] A model training module 202, configured to train a preset machine learning algorithm based on the user data of all users and the content data of all contents to obtain a time machine content recommendation model;
[0109] The content recommendation module 203 is used to obtain the display content of the time machine of the target user in the streaming media application by combining the user data, content data and the time machine content recommendation model of the target user with respect to any target user;
[0110] The time machine display module 204 is used to recommend and display the time machine to the target user according to the display content of the time machine.
[0111] like Figure 5 As shown, an embodiment of the present application provides an electronic device, including a processor 301, a communication interface 302, a memory 303 and a communication bus 304, wherein the processor 301, the communication interface 302, and the memory 303 communicate with each other through the communication bus 304.
[0112] Memory 303, used for storing computer programs;
[0113] In one embodiment of the present application, the processor 301 is used to execute the program stored in the memory 303 to implement any of the above-mentioned method embodiments to provide a method for displaying a time machine in a streaming media application. The processor 301 is configured to:
[0114] Obtain user data of all users and content data of all contents in the streaming application;
[0115] Training a preset machine learning algorithm based on the user data of all users and the content data of all content to obtain a time machine content recommendation model;
[0116] For any target user, user data, content data and the time machine content recommendation model of the target user are used to obtain the display content of the time machine of the target user in the streaming media application;
[0117] The time machine is recommended and displayed to the target user according to the displayed content of the time machine.
[0118] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of providing a method for displaying a time machine in a streaming media application as described in any of the aforementioned method embodiments are implemented.
[0119] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0120] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0121] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.
[0122] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.
Claims
1. A method for displaying a time machine in a streaming media application, characterized in that: The method comprises: Obtain user data of all users and content data of all contents in the streaming application; Training a preset machine learning algorithm based on the user data of all users and the content data of all content to obtain a time machine content recommendation model; For any target user, user data, content data and the time machine content recommendation model of the target user are used to obtain the display content of the time machine of the target user in the streaming media application; The time machine is recommended and displayed to the target user according to the displayed content of the time machine.
2. The method according to claim 1, characterized in that The method of training a preset machine learning algorithm based on the user data of all users and the content data of all contents to obtain a time machine content recommendation model includes: Performing denoising processing on the user data and the content data; Performing feature extraction on the user data and the content data after the denoising process respectively to obtain a user feature vector and a content feature vector; The user feature vector and the content feature vector are used to train a preset machine learning algorithm to obtain a time machine content recommendation model.
3. The method according to claim 2, characterized in that For any target user, the user data, content data and the time machine content recommendation model of the target user are used to obtain the display content of the time machine of the target user in the streaming media application, including: For any target user, feature extraction is performed on the user data of the target user and the content data of the target user respectively, so as to construct a user profile of the target user and a content profile of the target user; The user portrait of the target user and the content portrait of the target user are input into the time machine content recommendation model to obtain the display content of the time machine of the target user in the streaming media application.
4. The method according to claim 3, characterized in that For any target user, feature extraction is performed on the user data of the target user and the content data of the target user respectively to construct a user portrait of the target user and a content portrait of the target user, including: extracting data features of the user data of the target user and the content data of the target user respectively; Calculating a first similarity between a data feature of the user data of the target user and each of the user feature vectors, and calculating a second similarity between a data feature of the content data of the target user and each of the content feature vectors; Determine the user feature vector corresponding to the data feature of the user data of the target user based on the first similarity to obtain a user portrait of the target user, and determine the content feature vector corresponding to the data feature of the content data of the target user based on the second similarity to obtain a content portrait of the target user.
5. The method according to claim 4, characterized in that The step of determining the user feature vector corresponding to the data feature of the user data of the target user according to the first similarity to obtain the user portrait of the target user, and determining the content feature vector corresponding to the data feature of the content data of the target user according to the second similarity to obtain the content portrait of the target user includes: Sort the first similarities from high to low, and determine the user feature vector with the highest first similarity ranking as the user profile of the target user; And sorting the second similarities from high to low, and determining the content feature vector with the highest second similarity as the content portrait of the target user.
6. The method according to claim 1, characterized in that The method further comprises: After the preset machine learning algorithm is trained according to the user data of all users and the content data of all contents to obtain the time machine content recommendation model, the model parameters of the time machine content recommendation model are tuned by a cross-validation algorithm and an A / B random testing algorithm.
7. The method according to claim 1, characterized in that The recommending and displaying the time machine to the target user according to the displayed content of the time machine includes: Obtaining a first time machine for the target user according to the time value in the displayed content of the time machine and the historical viewing content of the target user in any time range; The first time machine of the target user is recommended and displayed to the target user.
8. The method according to claim 1, characterized in that The method further comprises: For any target user, determine the target user's preferred content in the current time period according to the target user's content data; The recommending and displaying the time machine to the target user according to the displayed content of the time machine further includes: Obtaining a second time machine for the target user according to the time value in the displayed content of the time machine and the historical viewing content of the target user in any time range; According to the target user's preference content of the current time period, the display sorting content of the first time machine of the target user is adjusted to obtain the third time machine of the target user; The third time machine of the target user is recommended and displayed to the target user.
9. The method according to claim 7 or 8, characterized in that: The method further comprises: A user graphical interface is displayed to the target user, so that the target user can adjust the display content and / or the sorting method of the display content of the first time machine or the third time machine.
10. A time machine display device in a streaming media application, characterized in that: The device comprises: A data acquisition module, used to acquire user data of all users and content data of all contents in the streaming media application; A model training module, used to train a preset machine learning algorithm based on the user data of all users and the content data of all contents to obtain a time machine content recommendation model; A content recommendation module, for obtaining, for any target user, the display content of the time machine of the target user in the streaming media application by combining the user data, content data and the time machine content recommendation model of the target user; The time machine display module is used to recommend and display the time machine to the target user according to the display content of the time machine.