Method and device for displaying theme style of user graphical interface of streaming media application program

Abstract

The invention relates to a theme style display method and device for a user graphical interface of a streaming media application program, and the method comprises the steps: constructing a user portrait and a content portrait of a target user for any target user, the user portrait being feature information used for describing the attribute of the target user, and the content portrait being feature information used for describing the attribute of the target user; the content portrait is feature information used for describing the attribute of the interested content of the target user; determining target composition elements of the theme style according to the user portrait, the content portrait and a preset theme style recommendation model; in a user graphical interface of the streaming media application program, the target theme style is displayed in real time based on the target composition element, and the target theme style is matched with the user portrait and the content portrait. According to the method, the change of the user can be responded in real time, the preference of the user can be adapted, the user interface elements are dynamically adjusted, the theme style of the user is seamlessly adapted, in addition, the new theme style is introduced, the interest of the user can be stimulated, the interaction and access frequency is improved, and the user experience is enhanced.

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 theme style in a user graphical interface of a streaming media application. Background Art

[0002] At present, with the development of science and technology, mainstream media apps (Applications) have brought new changes to the content production and dissemination of video websites, helping mainstream video websites to further expand their market influence, and thus are favored by mainstream media App users. Improving the user experience of mainstream media apps has also become an important area of ​​competition among major suppliers. In the process of implementing this solution, the technical personnel of this application found that the current major mainstream media apps only implement customized display of the theme style of the user graphical interface of the application, and cannot achieve dynamic expansion, and cannot generate theme style displays that meet user preferences based on user interests and hobbies, affecting the user experience of mainstream media apps. Summary of the invention

[0003] The present application provides a method and device for displaying a theme style in a user graphical interface of a streaming media application program, so as to solve the problem that the related technology cannot generate a theme style display that conforms to the user's preferences based on the user's interests and hobbies, thus affecting the user experience of mainstream media apps.

[0004] In a first aspect, the present application provides a method for displaying a theme style in a user graphical interface of a streaming media application, the method comprising:

[0005] For any target user, construct a user portrait and a content portrait of the target user, wherein the user portrait is feature information used to describe the attributes of the target user, and the content portrait is feature information used to describe the attributes of the content of interest to the target user;

[0006] Determine the target component elements of the theme style according to the user portrait, the content portrait and a preset theme style recommendation model;

[0007] In the streaming media application user graphical interface, a target theme style is displayed in real time based on the target component elements, and the target theme style matches the user portrait and the content portrait.

[0008] As an optional embodiment, for any target user, constructing a user profile and a content profile of the target user includes:

[0009] Obtaining user attribute information of all users and content attribute information of all contents in the streaming media application;

[0010] Performing clustering processing on the user attribute information of all users and the content attribute information of all contents respectively to obtain user attribute labels and content attribute labels respectively;

[0011] For any target user, obtaining user attribute information of the target user and content attribute information of the target user's historical browsing content;

[0012] Based on the user attribute information of the target user, the content attribute information of the target user's historical browsing content, the user attribute label and the content attribute label, the target user and the target user's historical browsing content are classified and processed respectively through a preset classification algorithm to obtain a user portrait and a content portrait of the target user.

[0013] As an optional embodiment, clustering the user attribute information of all users and the content attribute information of all contents to obtain user attribute labels and content attribute labels respectively includes:

[0014] Clustering the user attribute information of all users by using a first preset clustering algorithm to obtain a plurality of user attribute labels corresponding to the user attribute information of all users;

[0015] The content attribute information of all the contents is clustered by using a second preset clustering algorithm to obtain a plurality of content attribute labels corresponding to the content attribute information of all the contents.

[0016] As an optional embodiment, based on the user attribute information of the target user, the content attribute information of the historical browsing content of the target user, the user attribute label and the content attribute label, the target user and the historical browsing content of the target user are classified by a preset classification algorithm to obtain a user profile and a content profile of the target user, including:

[0017] Determine, by a first preset classification algorithm, a first similarity value between the user attribute information of the target user and each of the user attribute labels;

[0018] Determine a target user attribute label for classifying the user attribute information according to the first similarity value, and obtain a user portrait of the target user;

[0019] and, determining, by a second preset classification algorithm, a second similarity value between the content attribute information of the target user's historical browsing content and each of the content attribute tags;

[0020] A target content attribute label for classifying the content attribute information is determined according to the second similarity value, so as to obtain a content portrait of the target user.

[0021] As an optional embodiment, the user attribute information is divided into static user information and dynamic user information, wherein the static user information includes the user's geographic location, age, gender and device information; the dynamic user information includes the user's browsing history, favorite content, click pattern and search history for content in the streaming media application; the content attribute information includes the classification type, tag, popularity and release time of the content.

[0022] As an optional embodiment, determining the target component elements of the theme style according to the user portrait, the content portrait and a preset theme style recommendation model includes:

[0023] The user portrait and the content portrait are input into the preset theme style recommendation model to obtain the target component elements of the theme style.

[0024] As an optional embodiment, the method includes:

[0025] The preset training data set is input into the preset neural network algorithm to train and obtain the preset theme style recommendation model, wherein the preset training data set is the association relationship between several user portraits and content portraits and the constituent elements of the theme style.

[0026] As an optional embodiment, in the streaming media application user graphical interface, real-time display of the target theme style based on the target component elements includes:

[0027] Acquire a target element material from a preset element material model library based on the target component element, the target element material corresponding to the target component element;

[0028] Generate at least one theme style according to the target element material;

[0029] Determining the target theme from the at least one theme;

[0030] The target theme style is displayed in real time in the streaming media application user graphical interface.

[0031] As an optional embodiment, determining the target theme style from the at least one theme style includes:

[0032] Sending the at least one theme style to the streaming media application user graphical interface for the target user to click and select;

[0033] Determine the target theme style in response to a click selection by the target user;

[0034] and / or,

[0035] The at least one theme style is sorted according to a third similarity value, and a theme style with the highest third similarity value is determined as the target theme style, wherein the third similarity value is a similarity value between any one of the at least one theme style and the user portrait and the content portrait.

[0036] In a second aspect, the present application provides a theme style display device for a user graphical interface of a streaming media application program, the device comprising:

[0037] A portrait construction module, used to construct a user portrait and a content portrait of any target user, wherein the user portrait is feature information used to describe the attributes of the target user, and the content portrait is feature information used to describe the attributes of the content of interest to the target user;

[0038] An element determination module, used to determine the target component elements of the theme style according to the user portrait, the content portrait and a preset theme style recommendation model;

[0039] A display module is used to display a target theme style in real time in the user graphical interface of the streaming media application based on the target component elements, and the target theme style matches the user portrait and the content portrait.

[0040] 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:

[0041] For any target user, construct a user portrait and a content portrait of the target user, wherein the user portrait is feature information used to describe the attributes of the target user, and the content portrait is feature information used to describe the attributes of the content of interest to the target user;

[0042] Determine the target component elements of the theme style according to the user portrait, the content portrait and a preset theme style recommendation model;

[0043] In the streaming media application user graphical interface, a target theme style is displayed in real time based on the target component elements, and the target theme style matches the user portrait and the content portrait.

[0044] 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 theme style of a user graphical interface of a streaming media application as described in any one of the above items of the present application.

[0045] 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, by constructing a user portrait and a content portrait, and using a deep learning model (preset theme style recommendation model) to determine the constituent elements of the theme style, finally generates and displays the target theme style, and uses a machine learning model to analyze the user's behavior data in real time and dynamically adjust the user portrait. That is, the embodiment of the present application can respond to user changes in real time and adapt to user preferences, realize dynamic adjustment of user interface elements (such as color, font, layout), and seamlessly adapt to the user's theme style. In addition, the introduction of a new theme style can stimulate user interest, increase interaction and access frequency, and enhance user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] 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.

[0047] 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.

[0048] 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.

[0049] Figure 1 One of the flowcharts of a method for displaying a theme style in a user graphical interface of a streaming media application provided in an embodiment of the present application;

[0050] Figure 2 A second flowchart of a method for displaying a theme style in a user graphical interface of a streaming media application provided in an embodiment of the present application;

[0051] Figure 3 A third flowchart of a method for displaying a theme style in a user graphical interface of a streaming media application provided in an embodiment of the present application;

[0052] Figure 4 A structural block diagram of a theme style display device for a streaming media application user graphical interface provided by an embodiment of the present application;

[0053] Figure 5 A structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0054] 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.

[0055] 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.

[0056] In order to solve the technical problem that the prior art cannot generate a theme style display that meets the user's preferences based on the user's interests and hobbies, which affects the user experience of mainstream media apps, the present application provides a theme style display method and device for a streaming media application user graphical interface, which can respond to user changes and adapt to user preferences in real time, realize dynamic adjustment of user interface elements (such as color, font, layout), and seamlessly adapt to the user's theme style. In addition, the introduction of new theme styles can stimulate user interest, increase interaction and access frequency, and enhance user experience.

[0057] 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.

[0058] Figure 1 This is a flow chart of a method for displaying a theme style in a user graphical interface of a streaming media application provided in an embodiment of the present application. Figure 1 As shown, a method for displaying a theme style in a user graphical interface of a streaming media application program according to an embodiment of the present application may include the following steps:

[0059] Step 101: for any target user, construct a user profile and content profile of the target user.

[0060] The user portrait is feature information used to describe the attributes of the target user, and the content portrait is feature information used to describe the attributes of the content that the target user is interested in. The target user is the user whose streaming media graphical user interface in the device is displayed in a theme style through the embodiment of the present application.

[0061] Step 102, determining target component elements of the theme style according to the user portrait, content portrait and a preset theme style recommendation model.

[0062] In an embodiment of the present application, a neural network algorithm can be used to input the user portrait and content portrait in the form of feature vectors into the neural network algorithm for training to obtain a preset theme style recommendation model. Then, for the user portrait of each target user, the preset theme style recommendation model can obtain the similarity score between the user portrait and the corresponding content portrait and the constituent elements of all theme styles, and recommend the constituent elements with the highest scores to the target user, thereby generating the corresponding theme style. Specifically, a preset training data set can be input into a preset neural network algorithm to train a preset theme style recommendation model, wherein the preset training data set is the association relationship between several user portraits and content portraits and the constituent elements of the theme style. Then, the user portrait and content portrait are input into the preset theme style recommendation model to obtain the target constituent elements of the theme style. A machine learning model (neural network algorithm) is used to analyze user and content data in real time, and dynamically adjust user portraits and content portraits, so as to achieve real-time response to user changes and adapt to their long-term and short-term preferences.

[0063] The components of a theme style can be a set of pre-designed theme style templates, including but not limited to the color scheme, layout, icons and other visual elements of the theme style. A set of labels is formulated for each theme template to describe which user profile or content profile it is suitable for, and then used as a training data set to train the neural network algorithm. In addition, the materials of the components of a series of designed theme styles such as color schemes, layouts, icons and other visual elements can be stored to form an element material model library.

[0064] Step 103: In the user graphical interface of the streaming media application, a target theme style is displayed in real time based on the target component elements, wherein the target theme style matches the user portrait and the content portrait.

[0065] The target component elements are determined based on the user portrait and the content portrait. Therefore, the target theme style determined based on the target component elements can better adapt to the user portrait and the content portrait, can better adapt to the user preferences, and can enhance the user experience of the streaming media application.

[0066] Figure 2 The second flow chart of a method for displaying a theme style of a user graphical interface of a streaming media application provided in an embodiment of the present application. Figure 2 As shown, a method for displaying a theme style in a user graphical interface of a streaming media application program according to an embodiment of the present application may include the following steps:

[0067] Step 1011: Obtain user attribute information of all users and content attribute information of all contents in the streaming media application.

[0068] Assuming that there are, for example, 10,000 users in the streaming media application, user attribute information of the 10,000 users can be obtained. Assuming that the streaming media application is a video playback software including 1,000 video contents, content attribute information of the 1,000 video contents can be obtained.

[0069] Among them, user attribute information may include, for example, static user information and dynamic user information. The static user information includes but is not limited to the user's geographic location, age, gender and device information, while the dynamic user information includes but is not limited to the user's browsing history, favorite content, click pattern and search history for content in the streaming application. The content attribute information includes but is not limited to the classification type, tag, popularity and release time of the content.

[0070] Step 1012: cluster the user attribute information of all users and the content attribute information of all contents to obtain user attribute labels and content attribute labels respectively.

[0071] Specifically, the user attribute information of all users can be clustered by a first preset clustering algorithm to obtain multiple user attribute labels corresponding to the user attribute information of all users; the content attribute information of all contents can be clustered by a second preset clustering algorithm to obtain multiple content attribute labels corresponding to the content attribute information of all contents. The first preset clustering algorithm includes but is not limited to the K-Means clustering algorithm, the clustering method based on the probability model, and the density-based clustering algorithm (such as DBSCAN), and the second preset clustering algorithm includes but is not limited to text analysis, image processing and other technologies.

[0072] Step 1013: For any target user, obtain the user attribute information of the target user and the content attribute information of the target user's historical browsing content.

[0073] In this step, user attribute information and content attribute information of the target user are obtained in the same manner as in the aforementioned step 1011, except that this step is only for obtaining the user attribute information and content attribute information of a specific user.

[0074] Step 1014, based on the user attribute information of the target user, the content attribute information of the target user's historical browsing content, the user attribute label and the content attribute label, the target user and the target user's historical browsing content are classified and processed respectively through a preset classification algorithm to obtain a user portrait and a content portrait of the target user.

[0075] With the aforementioned data as the data foundation, data analysis can be performed to obtain user portraits and content portraits (for example, creating user portraits based on user historical behaviors and preferences (specifically, browsing history, interactive content such as favorites and clicks, search history), personal information (specifically, age, gender, geographic location), etc.), and performing the same analysis on the content to establish a content portrait, including the type, style, tone, etc. of the content).

[0076] Specifically, in the application embodiment, a first preset classification algorithm can be used to determine a first similarity value between the user attribute information of the target user and each user attribute label, and a target user attribute label for classifying the user attribute information can be determined based on the first similarity value to obtain a user portrait of the target user; and a second preset classification algorithm can be used to determine a second similarity value between the content attribute information of the target user's historical browsing content and each content attribute label, and a target content attribute label for classifying the content attribute information can be determined based on the second similarity value to obtain a content portrait of the target user. The first preset classification algorithm and the second preset classification algorithm can be, for example, logistic regression, decision tree, support vector machine (SVM), naive Bayes, K-nearest neighbor algorithm (KNN), etc., and the first similarity value and the second similarity value can be, for example, cosine similarity value, Euclidean distance, etc., which are not limited in the present application embodiment.

[0077] In an embodiment of the present application, the second preset classification algorithm may be to directly use text analysis, image processing and other technologies to determine the content label of the historical browsing content corresponding to the target user, and then calculate the similarity value between the content label and the aforementioned content attribute label to finally obtain a content portrait.

[0078] Step 102, determining target component elements of the theme style according to the user portrait, content portrait and a preset theme style recommendation model.

[0079] For details, please refer to Figure 1 For the sake of brevity, the relevant contents of step 102 are not repeated here.

[0080] Step 103: In the user graphical interface of the streaming media application, a target theme style is displayed in real time based on the target component elements, wherein the target theme style matches the user portrait and the content portrait.

[0081] For details, please refer to Figure 1 For the sake of brevity, the relevant contents of step 103 are not repeated here.

[0082] Figure 3 The third flow chart of a method for displaying a theme style of a user graphical interface of a streaming media application provided in an embodiment of the present application. Figure 3As shown, a method for displaying a theme style in a user graphical interface of a streaming media application program according to an embodiment of the present application may include the following steps:

[0083] Step 1011: Obtain user attribute information of all users and content attribute information of all contents in the streaming media application.

[0084] Step 1012: cluster the user attribute information of all users and the content attribute information of all contents to obtain user attribute labels and content attribute labels respectively.

[0085] Step 1013: for any target user, obtain the user attribute information of the target user and the content attribute information of the target user's historical browsing content.

[0086] Step 1014, based on the user attribute information of the target user, the content attribute information of the target user's historical browsing content, the user attribute label and the content attribute label, the target user and the target user's historical browsing content are classified and processed respectively through a preset classification algorithm to obtain a user portrait and a content portrait of the target user.

[0087] Step 102, determining target component elements of the theme style according to the user portrait, content portrait and a preset theme style recommendation model.

[0088] For details, please refer to Figure 1 For the sake of brevity, the relevant contents of step 102 are not repeated here.

[0089] Step 1031: acquiring target element material from a preset element material model library based on the target component element.

[0090] Theme style element materials can be pre-designed, including but not limited to color schemes, typography, icons and other visual elements. A set of labels is formulated for each theme style element material to describe which user profile or content profile each theme style element material is suitable for, so as to label the theme style element materials. All the labeled theme style element materials are then stored in a specific location to form a preset element material model library.

[0091] The target component element is, for example, a label or description content of a theme style element material. After the target component element is determined, the corresponding material, namely, the target element material, can be obtained from a preset element material model library based on the label or description content of the theme style element material.

[0092] Step 1032: Generate at least one theme style according to the target element material.

[0093] After obtaining the target element materials, such as color schemes, typography, and icons, there may be only one type of these materials, or there may be several types. For example, if there are two types of materials that meet the color scheme of the target component elements, then at least two themes can be generated. Similarly, if there are multiple types of layouts and icons that meet the target elements, more themes can be generated.

[0094] Step 1033: determine a target theme style from at least one theme style.

[0095] In one embodiment of the present application, a target theme style is determined from at least one theme style, and at least one theme style can be sent to the user graphical interface of the streaming media application for the target user to click and select, and the target theme style is determined in response to the target user's click and selection, that is, a user interface can be used to display the theme styles for selection in the user interface, allowing the user to browse and select the theme style that matches the user style, and then the theme style selected by the user is sent after the front-end processing and then processed by the back-end and sent to the front-end for display. Dynamic adjustment of user interface elements (such as color, font, layout) is achieved, and the theme style selected by the user or recommended by the system is seamlessly adapted. It is achieved that users can provide feedback through simple interactions (such as sliding, dragging and dropping, etc.), and real-time style adaptation is performed according to these operations. In addition, user feedback can be further analyzed, and conversational communication can be conducted with users to deeply understand their intentions and preferences, so that users can further analyze user and content data and recommend theme styles that are more suitable for users.

[0096] For example, assuming that three theme styles A, B, and C are generated based on the target element material, the three themes will be displayed through the user graphical interface of the application, and selection buttons will be provided to receive the user's selection of the selection button. Assuming that the user selects theme style A, theme style A will be determined as the target theme style.

[0097] In another embodiment of the present application, at least one theme style can be sorted according to the third similarity value, and the theme style with the highest third similarity value can be determined as the target theme style, where the third similarity value is the similarity value between any one of the at least one theme style and the user portrait and the content portrait.

[0098] For another example, assuming that three theme styles A, B, and C are generated based on the target element material, and the third similarity values ​​of the three theme styles are ranked from high to low as B, C, and A, then theme style B can be determined as the target theme style.

[0099] As another embodiment of the present application, a cron job can be deployed to regularly check whether the theme style needs to be switched. For example, it is determined whether the theme style needs to be switched according to preset rules (such as rules set by the user, such as switching once an hour) or user portraits (such as changes in user interaction information). If necessary, a new theme style is determined as the target theme style according to the preset rules. The embodiment of the present application can automatically apply the theme style to the user interface or content display according to the real-time input of the user or the preset rules.

[0100] For example, assuming that three theme styles A, B, and C are generated based on the target element material, and the user sets the theme style to be switched every hour, then the three theme styles A, B, and C can be determined as target theme styles in order of each hour.

[0101] Step 1034: Display the target theme style in real time in the streaming media application user graphical interface.

[0102] After the target theme style is determined, the target theme style is displayed in real time on the user graphical interface of the user's streaming media application.

[0103] To summarize, the method provided in the embodiment of the present application constructs a user portrait and a content portrait, and uses a deep learning model (a preset theme style recommendation model) to determine the constituent elements of the theme style, and finally generates and displays the target theme style, and uses a machine learning model to analyze the user's behavior data in real time and dynamically adjust the user portrait. That is, the embodiment of the present application can respond to user changes in real time and adapt to user preferences, realize dynamic adjustment of user interface elements (such as color, font, layout), and seamlessly adapt to the user's theme style. In addition, the introduction of new theme styles can stimulate user interest, increase interaction and access frequency, and enhance user experience.

[0104] Correspondingly, an embodiment of the present application also provides a theme style display device for a user graphical interface of a streaming media application. Figure 4 A structural block diagram of a theme display device for a streaming media application user graphical interface provided by an embodiment of the present application, such as Figure 4 As shown, the theme style display device of the streaming media application user graphical interface may include:

[0105] A portrait construction module 201 is used to construct a user portrait and a content portrait of any target user, wherein the user portrait is feature information used to describe the attributes of the target user, and the content portrait is feature information used to describe the attributes of the content of interest to the target user;

[0106] An element determination module 202 is used to determine the target component elements of the theme style according to the user portrait, the content portrait and a preset theme style recommendation model;

[0107] The display module 203 is used to display a target theme style in real time in the streaming media application user graphical interface based on the target component elements, and the target theme style matches the user portrait and the content portrait.

[0108] Correspondingly, the device provided in the embodiment of the present application constructs a user portrait and a content portrait, and uses a deep learning model (a preset theme style recommendation model) to determine the components of the theme style, and finally generates and displays the target theme style. It uses a machine learning model to analyze the user's behavior data in real time and dynamically adjust the user portrait. That is, the embodiment of the present application can respond to user changes in real time and adapt to user preferences, realize dynamic adjustment of user interface elements (such as color, font, layout), and seamlessly adapt to the user's theme style. In addition, the introduction of new theme styles can stimulate user interest, increase interaction and access frequency, and enhance user experience.

[0109] 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.

[0110] Memory 303, used for storing computer programs;

[0111] In one embodiment of the present application, the processor 301 is used to implement the theme style display method of the user graphical interface of the streaming media application provided by any of the above method embodiments when executing the program stored in the memory 303. The processor 301 is configured to:

[0112] For any target user, construct a user portrait and a content portrait of the target user, wherein the user portrait is feature information used to describe the attributes of the target user, and the content portrait is feature information used to describe the attributes of the content of interest to the target user;

[0113] Determine the target component elements of the theme style according to the user portrait, the content portrait and a preset theme style recommendation model;

[0114] In the streaming media application user graphical interface, a target theme style is displayed in real time based on the target component elements, and the target theme style matches the user portrait and the content portrait.

[0115] The embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of displaying a theme style of a user graphical interface of a streaming media application program as provided in any of the aforementioned method embodiments are implemented.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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 theme style in a user graphical interface of a streaming media application, characterized in that: The method comprises: For any target user, construct a user portrait and a content portrait of the target user, wherein the user portrait is feature information used to describe the attributes of the target user, and the content portrait is feature information used to describe the attributes of the content of interest to the target user; Determine the target component elements of the theme style according to the user portrait, the content portrait and a preset theme style recommendation model; In the streaming media application user graphical interface, a target theme style is displayed in real time based on the target component elements, and the target theme style matches the user portrait and the content portrait.

2. The method according to claim 1, characterized in that: The step of constructing a user profile and a content profile of any target user includes: Obtaining user attribute information of all users and content attribute information of all contents in the streaming media application; Performing clustering processing on the user attribute information of all users and the content attribute information of all contents respectively to obtain user attribute labels and content attribute labels respectively; For any target user, obtaining user attribute information of the target user and content attribute information of the target user's historical browsing content; Based on the user attribute information of the target user, the content attribute information of the target user's historical browsing content, the user attribute label and the content attribute label, the target user and the target user's historical browsing content are classified and processed respectively through a preset classification algorithm to obtain a user portrait and a content portrait of the target user.

3. The method according to claim 2, characterized in that The clustering process is performed on the user attribute information of all users and the content attribute information of all contents to obtain user attribute labels and content attribute labels respectively, including: Clustering the user attribute information of all users using a first preset clustering algorithm to obtain a plurality of user attribute labels corresponding to the user attribute information of all users; The content attribute information of all the contents is clustered by using a second preset clustering algorithm to obtain a plurality of content attribute labels corresponding to the content attribute information of all the contents.

4. The method according to claim 2 or 3, characterized in that: The method of classifying the target user and the target user's historical browsing content respectively based on the user attribute information of the target user, the content attribute information of the target user's historical browsing content, the user attribute tag, and the content attribute tag by using a preset classification algorithm to obtain a user profile and a content profile of the target user includes: Determine, by a first preset classification algorithm, a first similarity value between the user attribute information of the target user and each of the user attribute labels; Determine a target user attribute label for classifying the user attribute information according to the first similarity value, and obtain a user portrait of the target user; and, determining, by a second preset classification algorithm, a second similarity value between the content attribute information of the target user's historical browsing content and each of the content attribute tags; A target content attribute label for classifying the content attribute information is determined according to the second similarity value, so as to obtain a content portrait of the target user.

5. The method according to claim 2, characterized in that: The user attribute information is divided into static user information and dynamic user information, wherein the static user information includes the user's geographic location, age, gender and device information, and the dynamic user information includes the user's browsing history, favorite content, click pattern and search history for content in the streaming media application; the content attribute information includes the classification type, tag, popularity and release time of the content.

6. The method according to claim 1, characterized in that The determining the target component elements of the theme style according to the user portrait, the content portrait and a preset theme style recommendation model includes: The user portrait and the content portrait are input into the preset theme style recommendation model to obtain the target component elements of the theme style.

7. The method according to claim 1, characterized in that The method comprises: The preset training data set is input into the preset neural network algorithm to train and obtain the preset theme style recommendation model, wherein the preset training data set is the association relationship between several user portraits and content portraits and the constituent elements of the theme style.

8. The method according to claim 1, characterized in that The step of displaying the target theme style in real time based on the target component elements in the streaming media application user graphical interface includes: Acquire a target element material from a preset element material model library based on the target component element, the target element material corresponding to the target component element; Generate at least one theme style according to the target element material; Determining the target theme from the at least one theme; The target theme style is displayed in real time in the streaming media application user graphical interface.

9. The method according to claim 1 or 8, characterized in that: The step of determining the target theme style from the at least one theme style includes: Sending the at least one theme style to the streaming media application user graphical interface for the target user to click and select; Determine the target theme style in response to a click selection by the target user; and / or, The at least one theme style is sorted according to a third similarity value, and a theme style with the highest third similarity value is determined as the target theme style, wherein the third similarity value is a similarity value between any one of the at least one theme style and the user portrait and the content portrait.

10. A theme display device for a user graphical interface of a streaming media application, characterized in that: The device comprises: A portrait construction module, used to construct a user portrait and a content portrait of any target user, wherein the user portrait is feature information used to describe the attributes of the target user, and the content portrait is feature information used to describe the attributes of the content of interest to the target user; An element determination module, used to determine the target component elements of the theme style according to the user portrait, the content portrait and a preset theme style recommendation model; A display module is used to display a target theme style in real time in the user graphical interface of the streaming media application based on the target component elements, and the target theme style matches the user portrait and the content portrait.

Images