Application store display method, device, electronic device and storage medium

Abstract

This application provides an application store display method, apparatus, electronic device, and computer-readable storage medium. The method involves artificial intelligence technology and includes: obtaining user attributes of an account logged into the application store; and, in response to a detail viewing operation for an application in the application store, presenting an application details page, and presenting relevant information about the application on the application details page, as well as an image matching the user attributes. This application enables accurate personalized recommendations in the application store, thereby improving application recommendation efficiency.

Description

Technical Field

[0001] The present application relates to artificial intelligence technology and Internet technology, and in particular to a display method, device, electronic device and computer-readable storage medium for an application store. Background Art

[0002] Artificial intelligence is a comprehensive field of computer science that seeks to understand the essence of intelligence and develop new intelligent machines that can respond in a manner similar to human intelligence. It studies the design principles and implementation methods of various intelligent machines, enabling them to perceive, reason, and make decisions.

[0003] A typical application of artificial intelligence in app stores is intelligent recommendation. Users can browse and install various applications (APP, Application) (hereinafter referred to as Application) through the app store client (hereinafter referred to as App Store).

[0004] App stores can recommend potentially interesting apps to users through app details pages. However, related art app stores often display apps in a single, unrelated way, failing to attract sufficient user attention for effective recommendations. This forces users to spend more time searching for suitable apps, leading to unnecessary consumption of app store backend and communication resources. There is currently no effective solution to this problem. Summary of the Invention

[0005] The embodiments of the present application provide an application store display method, device, electronic device, and computer-readable storage medium, which can perform accurate personalized recommendations in the application store, thereby improving the efficiency of application recommendation.

[0006] The technical solution of the embodiment of the present application is implemented as follows:

[0007] This embodiment of the present application provides a method for displaying an application store, including:

[0008] Get the user attributes of the account logged into the App Store;

[0009] In response to a detail viewing operation on an application in the application store, presenting an application detail page;

[0010] The application details page presents relevant information of the application and an image matching the user attributes.

[0011] An embodiment of the present application provides a display device for an application store, including:

[0012] The acquisition module is used to obtain the user attributes of the account logged in to the app store;

[0013] A display module, configured to present an application details page in response to a detail viewing operation on an application in the application store;

[0014] The display module is further configured to present relevant information of the application on the application details page, and present an image matching the user attributes.

[0015] In the above scheme, the display module is also used to present an image matching the user attributes according to a first visual state; in response to a movement operation of a terminal device presenting the image, the first visual state is synchronously transformed into a second visual state to present the image according to the second visual state; wherein the difference between the first visual state and the second visual state is related to the parameters of the movement operation.

[0016] In the above scheme, the display module is also used to, when the parameters of the moving operation include a rotation direction and a rotation angle, transform the first position of the image included in the first visual state into a second position according to the rotation direction and the rotation angle; when the parameters of the moving operation include a displacement direction and a displacement distance, transform the first size of the image included in the first visual state into a second size according to the displacement direction and the displacement distance.

[0017] In the above scheme, the display module is also used to map the horizontal rotation angle of the moving operation into the horizontal movement distance of the image, and map the vertical rotation angle of the moving operation into the vertical movement distance of the image; use the horizontal movement distance in the opposite direction of the horizontal rotation as the horizontal displacement component, and use the vertical movement distance in the opposite direction of the vertical rotation as the vertical displacement component; and determine the second position relative to the first position based on the horizontal displacement component and the vertical displacement component.

[0018] In the above scheme, the display module is also used to map the displacement distance to a magnification ratio of the image when the displacement direction is a direction for increasing the observation distance, and to enlarge the first size to the second size according to the magnification ratio; when the displacement direction is a direction for reducing the observation distance, map the displacement distance to a reduction ratio of the image, and to reduce the first size to the second size according to the reduction ratio.

[0019] In the above scheme, the display module is also used to switch the presented image when the movement operation meets the switching condition; wherein the switching condition includes at least one of the following: the rotation angle included in the parameters of the movement operation exceeds the angle threshold; the displacement distance included in the parameters of the movement operation exceeds the distance threshold.

[0020] In the above solution, the display module is further used to determine the theme color of the image and apply a background color matching the theme color in the application details page.

[0021] In the above scheme, the display module is also used to determine the hue of each pixel in the image, and determine the hue with the highest frequency of occurrence as the hue of the theme color; use the hue of the theme color as the hue of the background color, and adjust the brightness and saturation of the background color to gradually transition from the brightness and saturation of the background color to the brightness and saturation of the theme color.

[0022] In the above scheme, the acquisition module is also used to present multiple candidate tags; wherein the types of the candidate tags include at least one of the following: portrait attributes of the account, attributes of applications that the account is interested in; in response to the selection operation of the multiple candidate tags, the selected candidate tag is determined as the user attribute of the account.

[0023] In the above scheme, the acquisition module is also used to obtain the operation data of the account in the application store; wherein, the operation data includes at least one of the following: installed applications, favorite applications, browsed applications, and evaluations of applications in the application store; and extract attributes representing the applications that the account is interested in from the operation data as user attributes of the account.

[0024] In the above solution, the display module is further configured to determine an application attribute corresponding to the user attribute; and query an image library for a candidate image matching the application attribute to serve as an image matching the user attribute.

[0025] In the above scheme, the display module is also used to call the first neural network model to perform the following processing: extract the feature vector of the user attribute, map the feature vector into probabilities corresponding to multiple candidate application attributes respectively; determine the candidate application attribute corresponding to the maximum probability as the application attribute corresponding to the user attribute; wherein, the first neural network model is trained based on the user attributes of the sample account and the labeled data for the user attributes of the sample account, and the labeled data includes the application attributes of the sample account.

[0026] In the above scheme, the display module is also used to obtain a first mapping table matching the application when there is operation data corresponding to the application in the application store; wherein the first mapping table includes multiple user attributes and multiple application attributes corresponding one-to-one to the multiple user attributes; the first mapping table is queried according to the user attributes to obtain the application attributes corresponding to the user attributes.

[0027] In the above scheme, the display module is also used to obtain a second mapping table that matches a target application that has an associated relationship with the application when there is no operation data corresponding to the application in the application store; wherein the associated relationship includes at least one of the following: the target application and the application belong to the same developer, the target application and the application have the same application type, and the target application is an application installed by the account; and query the second mapping table according to the user attributes to obtain application attributes corresponding to the user attributes.

[0028] In the above scheme, the display module is also used to obtain a third mapping table matching the application; wherein the third mapping table includes multiple application attributes and multiple candidate images corresponding one-to-one to the multiple application attributes; the third mapping table is queried according to the application attributes, and the candidate image corresponding to the application attribute in the third mapping table is determined as the candidate image matching the application attribute.

[0029] In the above scheme, the display module is also used to obtain multiple candidate images; call the second neural network model to perform the following processing for each of the candidate images: extract the feature vector of the candidate image, and map the feature vector into probabilities corresponding to multiple candidate application attributes respectively; determine the candidate application attribute corresponding to the maximum probability as the application attribute matching the candidate image; wherein, the second neural network model is trained based on the sample image and the annotation data for the sample image, and the annotation data includes the application attribute corresponding to the sample image; construct the third mapping table according to the multiple candidate images and the application attribute matching each of the candidate images.

[0030] In the above solution, the acquisition module is further used to obtain the social user attributes of an account that has a social relationship with the account when the operation data of the account does not exist in the application store; the display module is also used to present an image matching the social user attributes.

[0031] In the above scheme, the display module is also used to obtain a fourth mapping table matching the application; wherein the fourth mapping table includes multiple user attributes and multiple images corresponding one-to-one to the multiple user attributes; the fourth mapping table is queried according to the user attributes, and the image corresponding to the user attribute in the fourth mapping table is determined as the image matching the user attribute.

[0032] In the above scheme, the display module is also used to obtain multiple images; call the third neural network model to perform the following processing for each of the images: extract the feature vector of the image, and map the feature vector into probabilities corresponding to multiple candidate user attributes respectively; determine the candidate user attribute corresponding to the maximum probability as the user attribute matching the image; wherein, the third neural network model is trained based on sample images and annotation data for the sample images, and the annotation data includes user attributes of accounts of interest for the sample images; construct the fourth mapping table based on the multiple images and the user attributes matching each of the images.

[0033] An embodiment of the present application provides an electronic device, including:

[0034] a memory for storing computer-executable instructions;

[0035] The processor is used to implement the application store display method provided in the embodiment of the present application when executing the computer-executable instructions stored in the memory.

[0036] An embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions for implementing the application store display method provided in the embodiment of the present application when executed by a processor.

[0037] An embodiment of the present application provides a computer program product, which includes computer-executable instructions for implementing the application store display method provided in the embodiment of the present application when executed by a processor.

[0038] The embodiments of the present application have the following beneficial effects:

[0039] Presenting images that match user attributes on the app details page enables accurate personalized recommendations in the app store, compared to the single display method of the app store in related technologies, improving the efficiency of app recommendations and thus saving the app store's background resources and communication resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 1 is a schematic diagram of the architecture of the application store display system 100 provided in an embodiment of the present application;

[0041] Figure 2 4 is a schematic diagram of the structure of the terminal 400 provided in an embodiment of the present application;

[0042] Figure 3 This is a flowchart of the application store display method provided in an embodiment of the present application;

[0043] Figure 4 This is a flowchart of the application store display method provided in an embodiment of the present application;

[0044] Figure 5 This is a flowchart of the application store display method provided in an embodiment of the present application;

[0045] Figure 6A 、 Figure 6B 、 Figure 6C and Figure 6D This is a schematic diagram of an application scenario of the application store display method provided in an embodiment of the present application;

[0046] Figure 7A and Figure 7B This is a schematic diagram of an application scenario of the application store display method provided in an embodiment of the present application;

[0047] Figure 8 This is a flowchart of the application store display method provided in an embodiment of the present application;

[0048] Figure 9 This is a schematic diagram of an application scenario of the application store display method provided in an embodiment of the present application;

[0049] Figure 10A and Figure 10B It is a schematic diagram of the principle of the display method of the application store provided in the embodiment of the present application. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0051] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0052] In the following description, the terms "first\second" are only used to distinguish similar objects and do not represent a specific order for the objects. It can be understood that "first\second" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0053] It should be pointed out that the collection and processing of relevant data in this application should be strictly in accordance with the requirements of relevant national laws and regulations when applied in practice, and the informed consent or separate consent of the personal information subject should be obtained. Subsequent data use and processing should be carried out within the scope of authorization of laws and regulations and the personal information subject.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0055] Before further describing the embodiments of the present application in detail, the nouns and terms involved in the embodiments of the present application are explained. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations.

[0056] 1) In response, it is used to indicate the conditions or states on which the executed operations depend. When the dependent conditions or states are met, one or more operations executed can be real-time or have a set delay. Unless otherwise specified, there is no restriction on the order in which the multiple operations executed are executed.

[0057] 2) Header image, which generally refers to the top and center image of the homepage (such as the app details page) on a web page.

[0058] 3) Parallax: This refers to the difference in direction when viewing the same object from two different viewpoints. Parallax animation (or parallax special effects) changes the way an image is presented based on the direction or distance from which the user is viewing it.

[0059] In the related art, the image of the application details page of the app store and the background color of the page are fixed templates manually configured by the operator on the operation platform. The template contains a fixed image and a background color that matches the image. In this way, the user can obtain the image and background color configured by the operator when entering the application details page. The template configured by the operation platform is designed in advance. When configuring the template, the operator can preview the configuration effect and manually select the appropriate image based on the display effect. And the image is usually formed by sliding up and down through the interaction of the system native user interface (UI, User Interface) components (such as Coordinator Layout, App Bar Layout, Collapsing Toolbar Layout) to create a parallax effect.

[0060] During the implementation process, the applicant discovered the following technical problems with the relevant technology:

[0061] (1) The image and background colors are manually configured in advance, so when the operator selects the configuration, there may be a problem that the visual quality of the application details page is reduced due to the deviation in the matching degree between the image and background colors and the application.

[0062] (2) The configuration of the operating platform will occupy human resources and increase operating costs.

[0063] (3) The parallax effect of the image can only be seen when the user slides up and down, which increases the interaction cost.

[0064] In response to the above technical problems, the embodiments of the present application provide an application store display method that can make accurate personalized recommendations in the application store, thereby improving the efficiency of application recommendation. The following describes an exemplary application of the application store display method provided by the embodiments of the present application. The application store display method provided by the embodiments of the present application can be implemented by various electronic devices. For example, it can be applied to various types of user terminals (hereinafter referred to as terminals), such as smartphones, tablet computers, car terminals, and smart wearable devices.

[0065] Next, taking an electronic device as a terminal as an example, an exemplary application system architecture of the terminal implementing the application store display method provided in the embodiment of the present application is described. Figure 1 , Figure 1 FIG. 1 is a schematic diagram of the architecture of an application store display system 100 provided in an embodiment of the present application. The application store display system 100 includes: a server 200, a network 300, and a terminal 400, which will be described separately.

[0066] Server 200 is the background server of application store 410, and is used to receive the user attributes of the logged-in account sent by application store 410; it is also used to respond to the application viewing request of application store 410, obtain relevant information of the application, and images matching the user attributes, and send the relevant information of the application and images matching the user attributes to application store 410.

[0067] The network 300 is used as a medium for communication between the server 200 and the terminal 400, and can be a wide area network or a local area network, or a combination of the two.

[0068] Terminal 400 is configured to run application store 410. Application store 410 is configured to, in response to an account login request, obtain user attributes of the logged-in account; further configured to, in response to a detail viewing operation for an application in the application store, present an application details page in a human-computer interaction interface; further configured to receive application-related information and an image matching the user attributes from server 200, and present the application-related information and an image matching the user attributes on the application details page.

[0069] The embodiments of the present application can be implemented with the help of cloud technology. Cloud technology refers to a hosting technology that unifies a series of resources such as hardware, software, and network within a wide area network or a local area network to realize data calculation, storage, processing, and sharing.

[0070] Cloud technology is a general term for network, information, integration, management platform, and application technologies used in the cloud computing business model. It can form a resource pool that can be used flexibly and conveniently on demand. Cloud computing technology will become a key support. The backend services of technical network systems require a large amount of computing and storage resources.

[0071] As an example, the server 200 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal 400 and the server 200 can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiments of the present application.

[0072] Next, let’s explain Figure 1 The structure of the terminal 400 in FIG. Figure 2 , Figure 2 is a schematic diagram of the structure of the terminal 400 provided in an embodiment of the present application, Figure 2 The terminal 400 shown includes: at least one processor 410, a memory 450, at least one network interface 420, and a user interface 430. The various components in the terminal 400 are coupled together via a bus system 440. It is understood that the bus system 440 is used to achieve connection and communication between these components. In addition to including a data bus, the bus system 440 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, the bus system 440 is not shown in FIG. Figure 2 Various buses are labeled as bus system 440 .

[0073] The processor 410 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., where the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0074] The user interface 430 includes one or more output devices 431 that enable presentation of media content, including one or more speakers and / or one or more visual display screens. The user interface 430 also includes one or more input devices 432, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.

[0075] The memory 450 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state memory, hard drives, optical drives, etc. The memory 450 may optionally include one or more storage devices that are physically remote from the processor 410.

[0076] The memory 450 includes volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory may be a read-only memory (ROM), and the volatile memory may be a random access memory (RAM). The memory 450 described in the embodiments of the present application is intended to include any suitable type of memory.

[0077] In some embodiments, the memory 450 can store data to support various operations, examples of which include programs, modules, and data structures, or a subset or superset thereof, as exemplified below.

[0078] The operating system 451 includes system programs for processing various basic system services and performing hardware-related tasks, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic businesses and process hardware-based tasks.

[0079] The network communication module 452 is used to reach other computing devices via one or more (wired or wireless) network interfaces 420. Exemplary network interfaces 420 include Bluetooth, Wireless LAN (WiFi), and Universal Serial Bus (USB).

[0080] The presentation module 453 is configured to enable presentation of information (eg, a user interface for operating peripheral devices and displaying content and information) via one or more output devices 431 (eg, a display screen, a speaker, etc.) associated with the user interface 430 .

[0081] The input processing module 454 is configured to detect one or more user inputs or interactions from one of the one or more input devices 432 and to translate the detected inputs or interactions.

[0082] In some embodiments, the display device of the application store provided in the embodiments of the present application can be implemented in a software manner. Figure 2 The display device 455 of the application store stored in the memory 450 is shown. This device can be software in the form of a program or plug-in, and includes the following software modules: an acquisition module 4551 and a display module 4552. These modules are logical and can be arbitrarily combined or further separated according to the functions they implement. The functions of each module will be described below.

[0083] Below, by Figure 1 The terminal 400 in the embodiment of the present application independently executes the display method of the application store provided by the embodiment of the present application as an example. Figure 3 , Figure 3 This is a flow chart of the display method of the application store provided by the embodiment of the present application, which will be combined with Figure 3 Steps S103 and S104 can be executed in parallel or in no particular order. Figure 3 The sequential execution of step S103 and step S104 is taken as an example.

[0084] It should be noted that Figure 3 The method shown can be executed by various forms of computer programs running on the terminal 400, and is not limited to the above-mentioned application store 410, such as the above-mentioned operating system 451, software modules and scripts. Therefore, the client example below should not be regarded as a limitation on the embodiments of the present application.

[0085] In step S101, the user attributes of the account used to log in to the application store are obtained.

[0086] In some embodiments, multiple candidate tags are presented; wherein the types of candidate tags include at least one of the following: portrait attributes of the account (such as age, gender, personality, etc.), attributes of applications of interest to the account (such as types of applications of interest, virtual characters in applications of interest, etc.); in response to a selection operation for multiple candidate tags, the selected candidate tag is determined as a user attribute of the account.

[0087] As an example, candidate tags may be automatically presented to the user for selection when the account logs into the app store (for example, the first time logging into the app); candidate tags may be presented to the user for selection when a detail viewing operation is obtained for an app in the app store; or candidate tags may be presented to the user for selection in response to a tag setting operation received in the account settings page.

[0088] For example, Figure 9 In the example, multiple different types of candidate tags 901 may be presented for the user to choose from. The types of candidate tags 901 include but are not limited to age, gender, personality, and virtual characters of interest. After the user selects a candidate tag 901, the "Done" button may be triggered to determine the selected candidate tag 901 as the user attribute of the account.

[0089] In other embodiments, operational data of an account in an app store is obtained; wherein the operational data includes at least one of the following: installed applications, favorite applications, browsed applications, and evaluations of applications in the app store (e.g., ratings, comment information); attributes representing applications of interest to the account are extracted from the operational data as user attributes of the account.

[0090] As an example, the operation data obtained can be the operation data of the account in the application store within a time range of a preset time interval (such as one week or one month) from the current time point; it can also be the data of the operation performed by the account during one or more logins to the application store most recently with respect to the current time point; it can also be sorting all the operation data of the account in the application store in chronological order, and selecting part of the operation data in sequence from the back to the front according to the sorting, until the amount of the selected part of the operation data exceeds the data amount threshold (which can be the default value or the value set by the user, client or server), and stopping the selection, and determining the user attributes based on the selected part of the operation data.

[0091] As an example, query whether there is a candidate tag selected by the user in the app store; when the candidate tag selected by the user does not exist in the app store or the candidate tag selected by the user exceeds the validity period (which can be a default value or a value set by the user, client or server), obtain the account's operation data in the app store, and extract attributes representing the applications that the account is interested in from the operation data as user attributes of the account.

[0092] Determining the user attributes of an account based on the account's operation data in the app store consumes more time and computing resources than directly using the candidate tags selected by the user as the user attributes of the account. Therefore, the embodiment of the present application can determine the user attributes of an account based on the account's operation data in the app store only when there is no candidate tag selected by the user or the candidate tag selected by the user has expired. This can increase the speed of obtaining user attributes while saving resources.

[0093] In step S102 , in response to a detail viewing operation on an application in the application store, an application detail page is presented.

[0094] In some embodiments, when presenting the application details page, the process may further include: determining a theme color of an image presented in the application details page, and applying a background color matching the theme color in the application details page.

[0095] For example, color consists of three parts: hue, lightness, and saturation (or purity and chroma). Hue refers to a name that can more accurately represent the color of a certain color, such as rose red, orange, etc. Hue is determined by the spectral composition of the light entering the human eye. Lightness refers to the brightness of the color. Various colored objects produce different shades of color due to the difference in the amount of light they reflect. Saturation refers to the purity of the color, which indicates the proportion of colored components contained in the color. The greater the proportion of colored components, the higher the saturation of the color, and the smaller the proportion of colored components, the lower the saturation of the color.

[0096] As an example, the hue of each pixel in the image is determined, and the hue with the highest frequency of occurrence is determined as the hue of the theme color; the hue of the theme color is used as the hue of the background color, and the brightness and saturation of the background color are adjusted to gradually transition from the brightness and saturation of the background color to the brightness and saturation of the theme color.

[0097] For example, when determining the background color, the hue is kept unchanged, because the hue is the color tone of the background color. Only by keeping the hue unchanged can the tone of the theme color of the image and the background color be consistent, so that the image and background in the application details page can be integrated. When adjusting the brightness of the background color, the brightness of the background color can be adjusted to the same as the brightness of the theme color, or adjusted to a preset ratio of the brightness of the theme color (for example, 90%); when adjusting the saturation of the background color, the saturation of the background color can be adjusted to the same as the saturation of the theme color, or adjusted to a preset ratio of the saturation of the theme color (for example, 90%), so that the background and image in the application details page are connected and transitioned naturally and integrated, thereby solving the technical problem in the related art that when selecting pre-configured images and background colors, the visual quality of the application details page is reduced due to the deviation in the matching degree between the image and background color and the application, thereby improving user favorability and achieving effective recommendation of the application.

[0098] Take the application details page as an example, Figure 7B In the example, the game details page 703 automatically absorbs the theme color 705 of the image as the background color 704 of the game details page.

[0099] In step S103, relevant information of the application is presented on the application details page.

[0100] In some embodiments, the relevant information of the application includes at least one of the following: the rating of the application, the type of application, the popularity of the application (such as the number of downloads, ranking, etc.), the relevant controls of the application (such as the download button, forward button, etc.), the introduction information of the application (such as the name, developer, size of the installation package, copyright, age rating, compatibility information, etc.), and the virtual characters contained in the application.

[0101] Take the application details page as an example, Figure 6A In the game details page 601, information such as the name of the game, the download button of the game, the score of the game, the download volume of the game, the ranking of the game, and the type of the game are presented.

[0102] In step S104 , an image matching the user attributes is presented on the application details page.

[0103] In some embodiments, the image that matches the user attributes may be a picture that matches the user attributes, or may be a video frame in a video that matches the user attributes.

[0104] In some embodiments, when there is no operating data of the account in the application store, social user attributes of an account that has a social relationship with the account are obtained; and an image matching the social user attributes is presented in the application details page.

[0105] As an example, an account that has a social relationship with the account (hereinafter referred to as a social account) can be a friend account, a followed account, or an interactive account (such as an account that has commented, liked, forwarded, recommended, etc.) of the account that logged into the app store.

[0106] The operation data of the account that does not exist in the app store indicates that the account logged in to the app store may be a newly registered account. In other words, the user attributes of the account logged in to the app store cannot be obtained. Considering the high similarity in preferences between the social account and the account logged in to the app store, an image matching the user attributes of the social account can be presented to fit the logged-in user, thereby increasing the attractiveness of the app to users and further improving the recommendation efficiency of the app.

[0107] In some embodiments, see Figure 4 , Figure 4 This is a flow chart of the display method of the application store provided by the embodiment of the present application, based on Figure 3 , step S104 may include step S1041 and step S1042.

[0108] In step S1041 , an image matching the user attributes is presented according to the first visual state.

[0109] As an example, Figure 7A , before the device is rotated to the left, an image 701 corresponding to the first visual state is presented in the application details page.

[0110] In step S1042, in response to a movement operation on a terminal device (hereinafter referred to as device or terminal) presenting an image, the first visual state is synchronously transformed into a second visual state to present an image according to the second visual state.

[0111] As an example, Figure 7A In the example, after the device is rotated to the left, an image 702 corresponding to the second visual state is presented in the application details page, wherein the image 702 corresponding to the second visual state is offset to the right relative to the image 701 corresponding to the first visual state. That is, when the device is rotated to the left, the image moves to the right. Similarly, when the device is rotated to the right, the image moves to the left; when the device is rotated upward, the image moves downward; when the device is rotated downward, the image moves upward; and when the device is rotated to the upper right, the image moves to the lower left. Examples will not be given here one by one.

[0112] In some embodiments, the difference between the first visual state and the second visual state is related to parameters of the movement operation. The first visual state and the second visual state are not two specific states, but are relative. That is, the second visual state appears after the first visual state. After the first visual state changes to the second visual state, the second visual state is equivalent to the new first visual state, and can continue to change according to the movement operation.

[0113] In some embodiments, synchronously transforming the first visual state to the second visual state may include: when the parameters of the movement operation include a rotation direction and a rotation angle, transforming a first position of an image included in the first visual state to a second position according to the rotation direction and the rotation angle.

[0114] As an example, the data collected from the gyroscope sensor is detected through the sensor management interface to obtain the horizontal rotation direction, horizontal rotation angle, vertical rotation direction, and vertical rotation angle of the moving operation; the horizontal rotation angle of the moving operation is mapped to the horizontal movement distance of the image, and the vertical rotation angle of the moving operation is mapped to the vertical movement distance of the image; the horizontal movement distance in the opposite direction of the horizontal rotation is used as the horizontal displacement component, and the vertical movement distance in the opposite direction of the vertical rotation is used as the vertical displacement component; and the second position relative to the first position is determined based on the horizontal displacement component and the vertical displacement component.

[0115] For example, the mapping relationship between the horizontal rotation angle of the moving operation and the horizontal movement distance of the image can be a positive correlation relationship, that is, the larger the horizontal rotation angle of the moving operation, the larger the horizontal movement distance of the image; the mapping relationship between the vertical rotation angle of the moving operation and the vertical movement distance of the image can be a positive correlation relationship, that is, the larger the vertical rotation angle of the moving operation, the larger the vertical movement distance of the image.

[0116] For example, if the moving operation is to rotate 30 degrees to the left horizontally and 30 degrees upward vertically, Figure 10AIn the move operation, the horizontal rotation direction is the negative x-axis direction, the horizontal rotation angle is 30 degrees, and the vertical rotation direction is the positive y-axis direction, the vertical rotation angle is 30 degrees. The 30-degree horizontal rotation angle is mapped to the horizontal image movement distance b, and the 30-degree vertical rotation angle is mapped to the vertical image movement distance a. The first position is moved by a distance b in the positive x-axis direction and a distance a in the negative y-axis direction. The resulting position becomes the second position, and the image is then displayed at the second position.

[0117] For example, by obtaining a system service method and calling the sensor manager (the sensor manager interface mentioned above), the gyroscope sensor is detected through the Sensor Manager. When the device deviates from the x-axis or y-axis, the Sensor Manager sends the gyroscope sensor data through a sensor event. The data sent includes the device's offset angle relative to the x-axis and y-axis (or rotation angle, where the offset angle relative to the x-axis is the horizontal rotation angle mentioned above, and the offset angle relative to the y-axis is the vertical rotation angle mentioned above). The offset angle is mapped to the displacement on the x-axis and y-axis (where the displacement on the x-axis is the horizontal displacement component mentioned above, and the displacement on the y-axis is the vertical displacement component mentioned above). Finally, the image is moved according to the displacement on the x-axis and y-axis to form a parallax animation effect of the image. This can solve the technical problem in the related art that the parallax animation of the image can only be seen when the user slides up and down, resulting in a waste of operating resources, thereby reducing the consumption of display resources of the terminal device.

[0118] In other embodiments, synchronously transforming the first visual state to the second visual state may include: when the parameters of the movement operation include a displacement direction and a displacement distance, transforming a first size of an image included in the first visual state to a second size according to the displacement direction and the displacement distance.

[0119] As an example, the displacement distance and displacement direction of the moving operation are obtained through the camera data acquisition interface, wherein the displacement direction includes: a direction for increasing the observation distance and a direction for reducing the observation distance; when the displacement direction is a direction for increasing the observation distance, the displacement distance is mapped to the magnification ratio of the image, and the first size is enlarged to the second size according to the magnification ratio; when the displacement direction is a direction for reducing the observation distance, the displacement distance is mapped to the reduction ratio of the image, and the first size is reduced to the second size according to the reduction ratio.

[0120] For example, the mapping relationship between the displacement distance and the image magnification / reduction ratio can be a positive correlation, that is, the greater the displacement distance, the greater the image magnification / reduction ratio; the smaller the displacement distance, the smaller the image magnification / reduction ratio.

[0121] Take the mobile phone as an example, Figure 10B In this example, when the user moves the phone away from the eye, the image is magnified, and the greater the distance moved, the greater the magnification ratio. When the user moves the phone closer to the eye, the image is zoomed out, and the greater the distance moved, the greater the zoom ratio. This method of updating the image displayed on the app details page based on the observation distance can enhance interactivity in the app store, encourage users to pay attention to app-related information, improve app recommendation efficiency, and thus save the app store's backend and communication resources.

[0122] In some embodiments, when the movement operation satisfies a switching condition, the presented image may be switched; wherein the switching condition includes at least one of the following: the rotation angle included in the parameters of the movement operation exceeds an angle threshold; the displacement distance included in the parameters of the movement operation exceeds a distance threshold.

[0123] For example, when the rotation angle of a movement operation exceeds an angle threshold, or the displacement distance exceeds a distance threshold, the presented image is switched to a different image of the same application, where the similarity between the image before and after the switch exceeds an image similarity threshold, e.g., the image before and after the switch belong to different image styles. This ensures that when the presented image fails to attract the user's attention, a different image can be switched, thereby increasing the probability of attracting the user's attention and achieving effective application recommendation.

[0124] For example, when the rotation angle of a movement operation exceeds an angle threshold, or the displacement distance exceeds a distance threshold, the presented image is switched to an image of a different application, and the relevant information of the application presented on the application details page is updated. The similarity between the application before and after the switch exceeds an application similarity threshold, for example, the application before and after the switch belong to different application types. This ensures that when the presented application fails to attract the user's attention, the image of a different application can be switched, thereby increasing the probability of attracting the user's attention and achieving effective application recommendation.

[0125] As an example, the angle threshold and the distance threshold can be default values ​​or values ​​set by the user, client, or server. The switched image can be a personalized image that matches the user's attributes or an image uniformly set by the operator.

[0126] In the process of changing the visual state according to the mobile operation, the embodiment of the present application can switch the image when the visual state reaches a certain level, thereby eliminating the need for the user to switch the image by manually sliding the screen. This can save user operating resources while enhancing the interactivity in the application store, thereby prompting users to pay attention to relevant information of the application, improving the recommendation efficiency of the application, and thus saving the background resources and communication resources of the application store.

[0127] In some embodiments, the presented image may be switched in response to a switching operation, wherein the image switching operation includes a triggering operation on a switching button, a sliding operation, and the like.

[0128] For example, in response to an image switching operation, the presented image is switched to a different image of the same application, where the similarity between the image before and after the switching exceeds an image similarity threshold, e.g., the image before and after the switching belong to different image styles. This ensures that when the presented image fails to attract the user's attention, a different image can be switched through the image switching operation, thereby increasing the probability of attracting the user's attention and achieving effective application recommendation.

[0129] For example, in response to an app switching operation, the displayed image is switched to an image of a different app, and the relevant information of the app presented on the app details page is updated, wherein the similarity between the apps before and after the switching exceeds an app similarity threshold, for example, the apps before and after the switching belong to different application types. This ensures that when the displayed app fails to attract the user's attention, the app switching operation can be used to switch to an image of a different app, thereby increasing the probability of attracting the user's attention and achieving effective app recommendation.

[0130] In some embodiments, see Figure 5 , Figure 5 This is a flow chart of the display method of the application store provided by the embodiment of the present application, based on Figure 3 , step S105 and step S106 may be included before step S104.

[0131] In step S105, the application attribute corresponding to the user attribute is determined.

[0132] In some embodiments, the application attributes include at least one of the following: the type of application (e.g., shooting, multiplayer tower defense, construction, etc.), the virtual character in the application, the virtual skills used by the virtual character in the application, the virtual props in the application, and the style of the virtual character in the application (e.g., ancient style, fantasy, cute, modern, dark, etc.).

[0133] In some embodiments, the first neural network model is called to perform the following processing: extracting the feature vector of the user attribute, mapping the feature vector into probabilities corresponding to multiple candidate application attributes respectively; and determining the candidate application attribute corresponding to the maximum probability as the application attribute corresponding to the user attribute.

[0134] As an example, a first neural network model is trained based on user attributes of sample accounts and labeled data for the sample accounts' user attributes, including the sample accounts' application attributes. This enables the first neural network model to identify corresponding application attributes from user attributes, thereby improving the fit between the determined application attributes and user attributes.

[0135] As an example, the first neural network model may include various types, such as a convolutional neural network (CNN) model, a recurrent neural network (RNN) model, and a multi-layer feedforward neural network model. The above neural network model may be trained in a supervised manner, wherein the loss function used to train the first neural network model is used to represent the difference between the predicted value and the actual labeled data, and the loss function may be a 0-1 loss function, a perceptual loss function, or a cross-entropy loss function.

[0136] In other embodiments, when operation data corresponding to an application exists in an application store, a first mapping table matching the application is obtained; and the first mapping table is queried according to user attributes to obtain application attributes corresponding to the user attributes.

[0137] As an example, the operation data of the corresponding application includes at least one of the following: browsing data of the application, download data of the application, and favorite data of the application. The first mapping table includes multiple user attributes and multiple application attributes corresponding to the multiple user attributes. The first mapping table can be a mapping table set uniformly for all applications; it can also be different mapping tables set for different types of applications, that is, the same mapping table corresponds to the same application; or it can be different mapping tables set for different applications, that is, each application corresponds to a corresponding mapping table.

[0138] The embodiment of the present application determines the corresponding application attributes based on the first mapping table. Compared with the solution of determining application attributes through artificial intelligence, it consumes less time and computing resources and improves the speed of obtaining images that match user attributes.

[0139] In some further embodiments, when there is no operation data of the corresponding application in the application store, a second mapping table matching the target application associated with the application is obtained; and the second mapping table is queried according to the user attributes to obtain the application attributes corresponding to the user attributes.

[0140] As an example, the association relationship includes at least one of the following: the target application and the application belong to the same developer, the target application and the application are of the same application type (for example, both belong to the shooting category), and the target application is an application installed by the account.

[0141] When there is no operation data of the corresponding application in the app store, it indicates that the application may be newly listed in the app store. At this time, there may not be a first mapping table matching it, that is, the corresponding application attributes cannot be obtained. Considering that the target application associated with the application and the application have a high similarity, a second mapping table matching the target application can be obtained, thereby ensuring that regardless of whether there is operation data of the corresponding application in the app store, the application can be effectively recommended.

[0142] In step S106 , the image material library is searched for candidate images that match the application attributes, to be used as images that match the user attributes.

[0143] In some embodiments, a third mapping table matching the application is obtained; the third mapping table is queried according to the application attributes, and the candidate images corresponding to the application attributes in the third mapping table are determined as candidate images matching the application attributes.

[0144] As an example, the third mapping table includes multiple application attributes and multiple candidate images corresponding to the multiple application attributes. The third mapping table can be a mapping table set uniformly by the operator for all applications; it can also be different mapping tables set for different types of applications, that is, the same mapping table corresponds to the same application of the same type; or it can be different mapping tables set for different applications, that is, each application corresponds to a corresponding mapping table.

[0145] The embodiment of the present application determines an image that matches the user attributes based on the third mapping table, which consumes less time and computing resources and improves the image acquisition speed.

[0146] As an example, multiple candidate images are obtained by crawling from the network through crawler technology or by manual configuration; the second neural network model is called to perform the following processing on each candidate image: extract the feature vector of the candidate image, and map the feature vector into probabilities corresponding to multiple candidate application attributes respectively; determine the candidate application attribute corresponding to the maximum probability as the application attribute matching the candidate image; and construct a third mapping table based on the multiple candidate images and the application attributes matching each candidate image.

[0147] For example, the second neural network model is trained based on sample images and labeled data for the sample images, where the labeled data includes application attributes corresponding to the sample images. This enables the second neural network model to identify the corresponding application attributes from the images, thereby improving the fit between the candidate images in the third mapping table and the corresponding application attributes.

[0148] For example, the second neural network model may include various types, such as a convolutional neural network model, a recurrent neural network model, and a multi-layer feedforward neural network model. The above neural network models may be trained in a supervised manner, wherein a loss function used to train the second neural network model is used to represent the difference between the predicted value and the actual labeled data. The loss function may be a 0-1 loss function, a perceptual loss function, or a cross-entropy loss function.

[0149] In some embodiments, as an alternative to step S105 and step S106, before step S104, a fourth mapping table matching the application can also be obtained; the fourth mapping table is queried based on the user attributes, and the image corresponding to the user attributes in the fourth mapping table is determined as the image matching the user attributes; wherein the fourth mapping table includes multiple user attributes and multiple images corresponding one-to-one to the multiple user attributes.

[0150] As an example, multiple images are obtained by crawling from the Internet through crawler technology or by manual configuration; the third neural network model is called to perform the following processing on each image: extract the feature vector of the image, and map the feature vector into probabilities corresponding to multiple candidate user attributes; determine the candidate user attribute corresponding to the maximum probability as the user attribute matching the image; and construct a fourth mapping table based on the multiple images and the user attribute matching each image.

[0151] For example, the third neural network model is trained based on sample images and labeled data for the sample images, where the labeled data includes user attributes of accounts of interest in the sample images. This enables the third neural network model to identify corresponding user attributes from images, thereby improving the fit between images and corresponding user attributes in the fourth mapping table.

[0152] For example, the third neural network model may include various types, such as a convolutional neural network model, a recurrent neural network model, and a multi-layer feedforward neural network model. The above neural network models may be trained in a supervised manner, wherein a loss function used to train the third neural network model is used to represent the difference between the predicted value and the actual labeled data. The loss function may be a 0-1 loss function, a perceptual loss function, or a cross-entropy loss function.

[0153] The embodiment of the present application directly determines the corresponding image based on the user attributes. Compared with the solutions of step S105 and step S106, the step of determining the application attributes corresponding to the user attributes is omitted, thereby reducing the time and computing resources consumed and improving the image acquisition speed.

[0154] Below, the display method of the application store provided in the embodiment of the present application is explained using a game application (hereinafter referred to as a game) as an example.

[0155] Users can view game-related information, obtain game benefits, and download and install games through the app store. The game details page (i.e., the above-mentioned application details page) is a page that includes game information, information, benefits and other related content as well as a download button. This page helps users understand the game and encourages users to download and install the game. The embodiment of the present application recommends a header image (i.e., the above-mentioned image) on the game details page based on user attributes. The header image can form a parallax effect, and the background color of the game details page can change according to the header image. This can solve the problem of the lack of immersion in the default operator-recommended header image and display format in the related art, allowing users to have a stronger sense of game involvement when reading the game details page and experience more fun, thereby improving the efficiency of game recommendations.

[0156] See also Figure 6A 、 Figure 6B 、 Figure 6C 、 Figure 6D 、 Figure 7A and Figure 7B , Figure 6A 、 Figure 6B 、 Figure 6C 、 Figure 6D 、 Figure 7A and Figure 7B This is a schematic diagram of an application scenario of the display method of the application store provided in the embodiment of the present application. Figure 6A 、 Figure 6B 、 Figure 6C 、 Figure 6D 、 Figure 7A and Figure 7B The specific implementation of the application store display method provided in the embodiment of the present application is described.

[0157] (1) Automatically identify user attributes and match corresponding images.

[0158] In some embodiments, when a user accesses the game details page, the system automatically matches images based on the user's attributes. For example, in-game character positioning includes tanks, warriors, assassins, mages, shooters, and supports; character categories include male, female, and other; and image styles can be categorized as classical, fantasy, cute, modern, and dark.

[0159] As an example, Figure 6AAs shown, when the user attributes are female, mage, assassin, and ancient style, the virtual character 602 can be matched with the image of Shangguan XX in the game details page 601.

[0160] As an example 2, Figure 6B As shown, when the user attributes are male, warrior, and dark, the virtual character 602 can be matched with the image of Cao X in the game details page 601.

[0161] As example three, Figure 6C As shown, when the user attributes are male and tank, the virtual character 602 can be matched with the image of Zhuang X in the game details page 601.

[0162] As example 4, Figure 6D As shown, when the user attributes are male, assassin, and ancient style, the virtual character 602 can be matched with the image of Li X in the game details page 601.

[0163] (2) Parallax effects appear based on the rotation of the terminal device displaying the game details page.

[0164] In some embodiments, when the device is not rotated, the game details page presents an image that matches the user's attributes, such as Figure 7A As shown in the left picture of ; when the device is rotated to the left, the image displayed on the game details page shifts to the right as it rotates, as shown in Figure 7A As shown in the right picture, this creates a three-dimensional space effect.

[0165] (3) The game details page automatically matches the background color based on the image.

[0166] In some embodiments, as Figure 7B As shown, the game details page 703 automatically absorbs the theme color 705 of the image as the background color 704 of the game details page.

[0167] The embodiment of the present application automatically determines the appropriate image and background color through precise matching of user attributes and game attributes, and sends the image and background color to the application store for display, without the need for manual operation, which can save operating costs.

[0168] See also Figure 8 , Figure 8 This is a flow chart of the display method of the application store provided by the embodiment of the present application. Figure 8 This section describes how to automatically identify user attributes, match corresponding images, and automatically match background colors based on images.

[0169] In step S801, when the user triggers the game details page, the client requests background data with user information.

[0170] In some embodiments, the background data requested by the client includes images and background colors displayed on the game details page.

[0171] In step S802, a user tag (ie, the aforementioned user attribute) is obtained through user information, and a corresponding game tag (ie, the aforementioned game attribute) is matched according to the user tag.

[0172] In some embodiments, the backend server includes a user tag system and a game tag system. During the user account registration and login phase, users are required to actively select their own tags, such as "post-90s," "post-00s," and "anime." The backend server will store the user-selected tags as user tags. Game tags can be tags configured by operators at the time of game release to suit the game's characteristics, such as "shooting," "tower pusher," and "multiplayer online."

[0173] In step S803, the corresponding images are matched through the game tags.

[0174] In some embodiments, the game tag is mapped to a corresponding image library to obtain a matching image, wherein the image library corresponding to the game tag includes images designed in advance by the operator for the game tag.

[0175] In step S804, the background color is automatically matched according to the image.

[0176] In some embodiments, the theme color of an image is automatically used as the background color of the game details page. After obtaining a matching image, the backend server extracts the theme color of the image using a color extraction tool (Haishoku in the Python library) or a median cut algorithm. The theme color and image are then returned to the client as data for the game details page. This allows the image and background color displayed on the game details page to blend seamlessly, improving the user experience.

[0177] In step S805 , the backend server returns the image and the extracted background color to the client for display.

[0178] Next, we will explain how to use the gyroscope sensor to create a parallax effect.

[0179] In some embodiments, using an Android device as an example, the Sensor Manager is called on the game details page through a method that obtains system services. The Sensor Manager then detects the Gyroscope Sensor. When the device deviates horizontally from the x-axis or y-axis, the Sensor Manager sends gyroscope sensor data to the client (App Store app) via a sensor event. The data sent includes the device's offset angle (or rotation angle) relative to the x-axis and y-axis. An algorithm maps the offset angle to displacement on the x-axis and y-axis, which may have a maximum limit. Finally, the image's x-axis and y-axis displacements are controlled to perform movement operations, thereby creating a parallax effect.

[0180] In the embodiment of the present application, the device's built-in gyroscope sensor is used to calculate the device's rotation angle on the x-axis and y-axis relative to the horizontal plane when the device is in different postures. The rotation angle is then mapped to the displacement of the x-axis and y-axis on the device screen. The image is moved using the obtained displacement to form a parallax animation effect of the image, which can save user interaction costs and enable users to see the parallax animation effect as soon as they enter the game details page, thereby improving the user experience.

[0181] In the embodiment of the present application, the header image is the user's first perception of the game. Targeted recommendations based on user attributes enhance the game's appeal to players and improve user retention. The parallax effect of the header image causes the header image to shift as the device rotates, increasing the fun of the experience and giving users a more immersive feeling. The automatic color absorption system pulls the color of the largest area of ​​the header image, keeps the hue unchanged, and adjusts the brightness and saturation. Applying it to the game details page can make the transition between the game details page and the header image harmonious, thereby improving the visual comfort of the page.

[0182] The following combination Figure 2 The following describes an exemplary structure of a software module in which the display device of the application store provided in the embodiment of the present application is implemented.

[0183] In some embodiments, as Figure 2 As shown, the software modules stored in the display device 455 of the application store of the memory 450 may include:

[0184] The acquisition module 4551 is used to obtain the user attributes of the account used to log in to the application store;

[0185] Display module 4552, for presenting an application details page in response to a detail viewing operation on an application in the application store;

[0186] The display module 4552 is further configured to present application-related information on the application details page, and to present an image that matches the user's attributes.

[0187] In the above scheme, the display module 4552 is also used to present an image matching the user attributes according to the first visual state; in response to a movement operation of the terminal device for presenting the image, the first visual state is synchronously transformed into the second visual state to present the image according to the second visual state; wherein the difference between the first visual state and the second visual state is related to the parameters of the movement operation.

[0188] In the above scheme, the display module 4552 is also used to transform the first position of the image included in the first visual state into the second position according to the rotation direction and the rotation angle when the parameters of the moving operation include the rotation direction and the rotation angle; and when the parameters of the moving operation include the displacement direction and the displacement distance, transform the first size of the image included in the first visual state into the second size according to the displacement direction and the displacement distance.

[0189] In the above scheme, the display module 4552 is also used to map the horizontal rotation angle of the moving operation to the horizontal movement distance of the image, and map the vertical rotation angle of the moving operation to the vertical movement distance of the image; use the horizontal movement distance in the opposite direction of the horizontal rotation as the horizontal displacement component, and use the vertical movement distance in the opposite direction of the vertical rotation as the vertical displacement component; determine the second position relative to the first position based on the horizontal displacement component and the vertical displacement component.

[0190] In the above scheme, the display module 4552 is also used to map the displacement distance to the magnification ratio of the image when the displacement direction is a direction for increasing the observation distance, and to enlarge the first size to the second size according to the magnification ratio; when the displacement direction is a direction for reducing the observation distance, the displacement distance is mapped to the reduction ratio of the image, and to reduce the first size to the second size according to the reduction ratio.

[0191] In the above scheme, the display module 4552 is also used to switch the presented image when the moving operation meets the switching condition; wherein the switching condition includes at least one of the following: the rotation angle included in the parameters of the moving operation exceeds the angle threshold; the displacement distance included in the parameters of the moving operation exceeds the distance threshold.

[0192] In the above solution, the display module 4552 is further used to determine the theme color of the image and apply a background color matching the theme color in the application details page.

[0193] In the above scheme, the display module 4552 is also used to determine the hue of each pixel in the image, and determine the hue with the highest frequency of occurrence as the hue of the theme color; use the hue of the theme color as the hue of the background color, and adjust the brightness and saturation of the background color to gradually transition from the brightness and saturation of the background color to the brightness and saturation of the theme color.

[0194] In the above scheme, the acquisition module 4551 is also used to present multiple candidate tags; wherein the types of candidate tags include at least one of the following: portrait attributes of the account, attributes of applications that the account is interested in; in response to the selection operation for multiple candidate tags, the selected candidate tags are determined as user attributes of the account.

[0195] In the above scheme, the acquisition module 4551 is also used to obtain the operation data of the account in the application store; wherein the operation data includes at least one of the following: installed applications, favorite applications, browsed applications, and evaluations of applications in the application store; and extract attributes representing the applications that the account is interested in from the operation data as user attributes of the account.

[0196] In the above solution, the display module 4552 is further configured to determine the application attributes corresponding to the user attributes; and query the image library for candidate images matching the application attributes to serve as images matching the user attributes.

[0197] In the above scheme, the display module 4552 is also used to call the first neural network model to perform the following processing: extract the feature vector of the user attribute, map the feature vector into probabilities corresponding to multiple candidate application attributes respectively; determine the candidate application attribute corresponding to the maximum probability as the application attribute corresponding to the user attribute; wherein, the first neural network model is trained based on the user attributes of the sample account and the labeled data for the user attributes of the sample account, and the labeled data includes the application attributes of the sample account.

[0198] In the above scheme, the display module 4552 is also used to obtain a first mapping table matching the application when there is operation data of the corresponding application in the application store; wherein the first mapping table includes multiple user attributes and multiple application attributes corresponding one-to-one to the multiple user attributes; the first mapping table is queried according to the user attributes to obtain the application attributes corresponding to the user attributes.

[0199] In the above scheme, the display module 4552 is also used to obtain a second mapping table that matches the target application that has an associated relationship with the application when there is no operation data of the corresponding application in the application store; wherein the associated relationship includes at least one of the following: the target application and the application belong to the same developer, the target application and the application have the same application type, and the target application is an application installed by the account; and query the second mapping table according to the user attributes to obtain the application attributes corresponding to the user attributes.

[0200] In the above scheme, the display module 4552 is also used to obtain a third mapping table that matches the application; wherein the third mapping table includes multiple application attributes and multiple candidate images that correspond one-to-one to the multiple application attributes; the third mapping table is queried according to the application attributes, and the candidate image corresponding to the application attribute in the third mapping table is determined as the candidate image that matches the application attribute.

[0201] In the above scheme, the display module 4552 is also used to obtain multiple candidate images; call the second neural network model to perform the following processing for each candidate image: extract the feature vector of the candidate image, and map the feature vector into probabilities corresponding to multiple candidate application attributes respectively; determine the candidate application attribute corresponding to the maximum probability as the application attribute matching the candidate image; wherein the second neural network model is trained based on the sample image and the annotation data for the sample image, and the annotation data includes the application attributes corresponding to the sample image; construct a third mapping table based on the multiple candidate images and the application attributes matching each candidate image.

[0202] In the above solution, the acquisition module 4551 is also used to obtain the social user attributes of an account that has a social relationship with the account when the operation data of the account does not exist in the application store; the display module 4552 is also used to present an image that matches the social user attributes.

[0203] In the above scheme, the display module 4552 is also used to obtain a fourth mapping table that matches the application; wherein the fourth mapping table includes multiple user attributes and multiple images that correspond one-to-one to the multiple user attributes; the fourth mapping table is queried according to the user attributes, and the image corresponding to the user attribute in the fourth mapping table is determined as the image that matches the user attribute.

[0204] In the above scheme, the display module 4552 is also used to obtain multiple images; call the third neural network model to perform the following processing for each image: extract the feature vector of the image, and map the feature vector into probabilities corresponding to multiple candidate user attributes respectively; determine the candidate user attribute corresponding to the maximum probability as the user attribute matching the image; wherein, the third neural network model is trained based on the sample image and the annotation data for the sample image, and the annotation data includes the user attributes of the account of interest for the sample image; construct a fourth mapping table based on the multiple images and the user attributes matching each image.

[0205] The present invention provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the application store display method described in the present invention.

[0206] The embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions. The computer-executable instructions are stored in the storage medium. When the computer-executable instructions are executed by a processor, the processor will execute the application store display method provided by the embodiment of the present application. For example, Figure 3 、 Figure 4 、 Figure 5 and Figure 8 The application store display method shown is a computer including various computing devices including smart terminals and servers.

[0207] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or various devices including one or any combination of the above memories.

[0208] In some embodiments, computer-executable instructions may be in the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0209] As an example, computer-executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, such as in one or more scripts in a hypertext markup language document, in a single file dedicated to the program in question, or in multiple coordinating files (e.g., files storing one or more modules, subroutines, or code portions).

[0210] By way of example, computer-executable instructions may be deployed to be executed on one computing device or on multiple computing devices at one site or on multiple computing devices distributed across multiple sites and interconnected by a communication network.

[0211] In summary, presenting images that match user attributes on the app details page, compared to the single display method of app stores in related technologies, can make accurate personalized recommendations in app stores, improve the efficiency of app recommendations, and thus save the background resources and communication resources of the app store.

[0212] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. Any modifications, equivalent replacements, and improvements made within the spirit and scope of the present application are included in the scope of protection of the present application.

Claims

1. A display method for an application store, characterized in that: The method comprises: Get the user attributes of the account logged into the App Store; In response to a detail viewing operation for an application in the application store, an application detail page is presented, and the hue of each pixel in the image matching the user attribute is determined, and the hue with the highest frequency of occurrence is determined as the hue of the theme color; the hue of the theme color is used as the hue of the background color of the application in the application detail page, and the lightness and saturation of the background color are adjusted to gradually transition from the lightness and saturation of the background color to the lightness and saturation of the theme color, or the lightness of the background color is adjusted to a preset ratio of the lightness of the theme color, and the saturation of the background color is adjusted to a preset ratio of the saturation of the theme color; Presenting relevant information of the application on the application details page, and presenting the image as the header image according to the first visual state; In response to a movement operation on a terminal device presenting the image, synchronously transforming the first visual state into a second visual state to present the image according to the second visual state, wherein a difference between the first visual state and the second visual state is related to a parameter of the movement operation; When the parameters of the movement operation include a displacement direction and a displacement distance, when the displacement direction is a direction for increasing the observation distance, the displacement distance is mapped to a magnification ratio of the image, and the first size is magnified to a second size according to the magnification ratio; when the displacement direction is a direction for decreasing the observation distance, the displacement distance is mapped to a reduction ratio of the image, and the first size is reduced to the second size according to the reduction ratio; When the movement operation satisfies a switching condition, switching the presented image, wherein the switching condition includes at least one of the following: a rotation angle included in the parameters of the movement operation exceeds an angle threshold, a displacement distance included in the parameters of the movement operation exceeds a distance threshold, and a similarity between the image before switching and the image after switching exceeds an image similarity threshold; The synchronously transforming the first visual state into the second visual state includes: When the parameters of the movement operation include a rotation direction and the rotation angle, mapping the horizontal rotation angle of the movement operation to a horizontal movement distance of the image, and mapping the vertical rotation angle of the movement operation to a vertical movement distance of the image; taking the horizontal movement distance in the opposite direction of the horizontal rotation as the horizontal displacement component, and taking the vertical movement distance in the opposite direction of the vertical rotation as the vertical displacement component; A second position relative to the first position is determined based on the horizontal displacement component and the vertical displacement component.

2. The method according to claim 1, characterized in that The method of obtaining user attributes of the account used to log in to the app store includes: Present multiple candidate labels; The type of the candidate tag includes at least one of the following: a portrait attribute of the account, an attribute of an application that the account is interested in; In response to a selection operation on the plurality of candidate tags, the selected candidate tags are determined as user attributes of the account.

3. The method according to claim 1, characterized in that The method of obtaining user attributes of the account used to log in to the app store includes: Obtaining operation data of the account in the application store; The operation data includes at least one of the following: installed applications, favorite applications, browsed applications, and evaluations of applications in the application store; the operation data is the operation data of the account in the application store within a time range of a preset length of time from the current time point, or the operation data is the operation data of the account during one or more logins to the application store most recently relative to the current time point, or the operation data is all operation data of the account in the application store sorted in chronological order and partial operation data selected in order from the latest to the earliest according to the sorting; Attributes representing applications that the account is interested in are extracted from the operation data as user attributes of the account.

4. The method according to claim 1, wherein Before presenting the image matching the user attributes, the method further includes: Determining application attributes corresponding to the user attributes; An image material library is queried for candidate images that match the application attributes, to be used as images that match the user attributes.

5. The method according to claim 4, characterized in that The determining of the application attribute corresponding to the user attribute includes: Call the first neural network model to perform the following processing: Extracting a feature vector of the user attribute, and mapping the feature vector into probabilities corresponding to a plurality of candidate application attributes; Determine the candidate application attribute corresponding to the maximum probability as the application attribute corresponding to the user attribute; The first neural network model is trained based on user attributes of the sample account and labeled data for the user attributes of the sample account, and the labeled data includes application attributes of the sample account.

6. The method according to claim 4, characterized in that The determining of the application attribute corresponding to the user attribute includes: When operation data corresponding to the application exists in the application store, obtaining a first mapping table matching the application; The first mapping table includes a plurality of user attributes and a plurality of application attributes corresponding one-to-one to the plurality of user attributes; The first mapping table is queried according to the user attribute to obtain an application attribute corresponding to the user attribute.

7. The method according to claim 6, characterized in that The method further comprises: When the operation data corresponding to the application does not exist in the application store, obtaining a second mapping table matching a target application associated with the application; The association relationship includes at least one of the following: the target application and the application belong to the same developer, the target application and the application are of the same application type, and the target application is an application installed by the account; The second mapping table is queried according to the user attribute to obtain an application attribute corresponding to the user attribute.

8. The method according to claim 4, characterized in that The candidate images in the query image library that match the application attributes include: Obtaining a third mapping table matching the application; The third mapping table includes a plurality of application attributes and a plurality of candidate images corresponding one-to-one to the plurality of application attributes; The third mapping table is searched according to the application attribute, and the candidate image corresponding to the application attribute in the third mapping table is determined as the candidate image matching the application attribute.

9. The method according to claim 8, characterized in that The method further comprises: Acquire multiple candidate images; Call the second neural network model to perform the following processing on each candidate image: Extracting a feature vector of the candidate image, and mapping the feature vector into probabilities corresponding to a plurality of candidate application attributes; Determining the candidate application attribute corresponding to the maximum probability as the application attribute matching the candidate image; The second neural network model is trained based on a sample image and labeled data for the sample image, wherein the labeled data includes application attributes corresponding to the sample image; The third mapping table is constructed according to the multiple candidate images and the application attribute matching each candidate image.

10. The method according to claim 1, characterized in that The method further comprises: When the operation data of the account does not exist in the application store, obtaining the social user attributes of an account that has a social relationship with the account; The presenting of an image matching the user attributes includes: Images matching the social user attributes are presented.

11. A display device for an application store, characterized in that: include: The acquisition module is used to obtain the user attributes of the account logged in to the app store; a display module configured to, in response to a detail viewing operation for an application in the application store, present an application detail page, determine the hue of each pixel in the image matching the user attribute, and determine the hue with the highest frequency of occurrence as the hue of the theme color; use the hue of the theme color as the hue of the background color of the application in the application detail page, and adjust the lightness and saturation of the background color to gradually transition from the lightness and saturation of the background color to the lightness and saturation of the theme color, or adjust the lightness of the background color to a preset ratio of the lightness of the theme color, and adjust the saturation of the background color to a preset ratio of the saturation of the theme color; The display module is further configured to present relevant information of the application on the application details page, and to present the image as the header image according to the first visual state; The display module is further configured to, in response to a movement operation on a terminal device presenting the image, synchronously transform the first visual state into a second visual state, so as to present the image according to the second visual state, wherein a difference between the first visual state and the second visual state is related to a parameter of the movement operation; The display module is further configured to, when the parameters of the movement operation include a displacement direction and a displacement distance, map the displacement distance to a magnification ratio of the image and enlarge the first size to a second size according to the magnification ratio when the displacement direction is a direction for increasing the observation distance; and map the displacement distance to a reduction ratio of the image and reduce the first size to the second size according to the reduction ratio when the displacement direction is a direction for reducing the observation distance; The display module is further configured to switch the presented image when the movement operation satisfies a switching condition, wherein the switching condition includes at least one of the following: a rotation angle included in the parameters of the movement operation exceeds an angle threshold, a displacement distance included in the parameters of the movement operation exceeds a distance threshold, and a similarity between the image before switching and the image after switching exceeds an image similarity threshold; The display module is also used to, when the parameters of the moving operation include the rotation direction and the rotation angle, map the horizontal rotation angle of the moving operation to the horizontal movement distance of the image, and map the vertical rotation angle of the moving operation to the vertical movement distance of the image; use the horizontal movement distance in the opposite direction of the horizontal rotation as the horizontal displacement component, and use the vertical movement distance in the opposite direction of the vertical rotation as the vertical displacement component; and determine the second position relative to the first position based on the horizontal displacement component and the vertical displacement component.

12. An electronic device, characterized in that: include: a memory for storing computer-executable instructions; A processor, configured to implement the application store display method according to any one of claims 1 to 10 when executing the computer-executable instructions stored in the memory.

13. A computer-readable storage medium, characterized in that Computer-executable instructions are stored, and when the computer-executable instructions are executed, they are used to implement the application store display method according to any one of claims 1 to 10.

14. A computer program product comprising computer-executable instructions, characterized in that When the computer-executable instructions are executed by a processor, the application store display method according to any one of claims 1 to 10 is implemented.

Images