Image display methods, devices, electronic devices, and readable storage media

Abstract

This application discloses an image display method, apparatus, electronic device, and readable storage medium, belonging to the field of artificial intelligence technology. The method includes: receiving a first input to a first control; in response to the first input, acquiring a first background image that matches at least one of the first feature data and the historical behavior data, based on the user's first feature data and the user's historical behavior data; and displaying the first background image when a first page indicated by the first control is displayed.

Description

Technical Field

[0001] This application belongs to the field of artificial intelligence technology, specifically relating to an image display method, apparatus, electronic device, and readable storage medium. Background Technology

[0002] Currently, when users browse reading software such as news and information, most software can only display black text on a white background, resulting in a monotonous display effect.

[0003] In existing technologies, users can manually set background images, so when displaying pages of reading software such as news and information, the background of the page is no longer a single white background, but a variety of colorful patterns, which can achieve a personalized display effect.

[0004] However, existing technologies require users to manually set background images, making the process cumbersome. Summary of the Invention

[0005] The purpose of this application is to provide an image display method that can solve the problem that the process of setting a background image by the user is cumbersome because the user needs to manually set the background image.

[0006] In a first aspect, embodiments of this application provide an image display method, the method comprising: receiving a first input to a first control; in response to the first input, acquiring a first background image that matches at least one of the first feature data and the historical behavior data based on the user's first feature data and the user's historical behavior data; and displaying the first background image when displaying a first page indicated by the first control.

[0007] Secondly, embodiments of this application provide an image display device, the device comprising: a first receiving module for receiving a first input to a first control; a first acquiring module for acquiring, in response to the first input, a first background image matching at least one of the first feature data and the historical behavior data, based on the user's first feature data and the user's historical behavior data; and a first display module for displaying the first background image when displaying a first page indicated by the first control.

[0008] Thirdly, embodiments of this application provide an electronic device including a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions, when executed by the processor, implementing the steps of the method described in the first aspect.

[0009] Fourthly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect.

[0010] Fifthly, embodiments of this application provide a chip, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the method as described in the first aspect.

[0011] In a sixth aspect, embodiments of this application provide a computer program product stored in a storage medium, which is executed by at least one processor to implement the method described in the first aspect.

[0012] In the embodiments of this application, when a user makes a first input to the first control to trigger the display of the first page, first feature data describing user profile characteristics and historical behavior data describing user behavior characteristics are obtained. Based on at least one of the first feature data and historical behavior data, a matching first background image is found in the background image library, and then the first background image is displayed when the first page is displayed. Therefore, in the embodiments of this application, intelligently displaying background images based on user characteristics and usage habits not only enriches the display effect and increases user browsing interest, but also simplifies user operation by eliminating the need for manual settings. Attached Figure Description

[0013] Figure 1 This is a flowchart of an image display method according to an embodiment of this application;

[0014] Figure 2 This is a schematic diagram of the model structure of an embodiment of this application;

[0015] Figure 3 This is a block diagram of an image display device according to an embodiment of this application;

[0016] Figure 4 This is one of the hardware structure diagrams of the electronic device according to an embodiment of this application;

[0017] Figure 5 This is the second schematic diagram of the hardware structure of the electronic device according to an embodiment of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0019] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0020] The image display method provided in this application will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0021] Figure 1 A flowchart of an image display method according to an embodiment of this application is shown, with an example of the method being applied to an electronic device. The method includes:

[0022] Step 110: Receive the first input to the first control.

[0023] The first input includes touch input performed by the user on the screen, not limited to clicking, swiping, or dragging. The first input can also be air input, such as gestures or facial expressions. It also includes input from physical buttons on the device, not limited to pressing. Furthermore, the first input includes one or more inputs, which can be continuous or timed.

[0024] In this step, the first input is used to operate the first control to trigger the display of the first page indicated by the first control.

[0025] For example, the first page might be a push notification page for a reading app. Or, the first page might be the main page for an audio playback app.

[0026] The first input method is implemented as follows: when a user clicks the icon of a reading software, the homepage of the reading software is displayed, and a "Push" option is displayed at the top of the homepage. The "Push" option is the first control, and the user clicks the "Push" option.

[0027] Step 120: In response to the first input, obtain a first background image that matches at least one of the first feature data and the historical behavior data, based on the user's first feature data and the user's historical behavior data.

[0028] The first feature data is used to represent the user's basic profile features, including user gender, user age, user preferences and other feature data. The first feature data can depict the user's overall appearance.

[0029] Historical behavioral data is used to represent the semantic features of information such as news that users have browsed, including the classification of information such as news, keywords in information such as news, and entity features in information such as news. This part of historical behavioral data can characterize the information that users are interested in and the information that users are not interested in.

[0030] In this step, a first background image is matched in the background image library based on at least one of the first feature data and historical behavior data.

[0031] Optionally, the background image library stores a large number of background images, and the semantic features of each background image are obtained as feature data of each background image, which are used to compare with at least one of the first user data and historical behavior data.

[0032] For reference, a background image library can be established based on image collection methods; or a background image library can be established based on image generation technologies such as Artificial Intelligence-Generated Content (AIGC).

[0033] Step 130: If the first page indicated by the first control is displayed, display the first background image.

[0034] In this step, while displaying the first page, a first background image is also displayed to enrich the display effect.

[0035] In the embodiments of this application, when a user makes a first input to the first control to trigger the display of the first page, first feature data describing user profile characteristics and historical behavior data describing user behavior characteristics are obtained. Based on at least one of the first feature data and historical behavior data, a matching first background image is found in the background image library, and then the first background image is displayed when the first page is displayed. Therefore, in the embodiments of this application, intelligently displaying background images based on user characteristics and usage habits not only enriches the display effect and increases user browsing interest, but also simplifies user operation by eliminating the need for manual settings.

[0036] In this application, all types of data can be represented as vectors, and each data vector is mapped to the same vector space. The correlation between these vectors is measured by vector distance, ultimately achieving background image matching. Based on this, another embodiment of this application provides a model training process. The model trained using this process can be used to output vectors corresponding to each data point.

[0037] Optionally, see Figure 2 The algorithm employs a deep sequence dual-tower model structure, comprising a user tower and an item tower. The item tower outputs a semantic vector of the item (e.g., a background image), denoted as itemVec. The user tower has multiple outputs: a vector representing the user's basic profile, denoted as userBasicVec, and a vector representing the user sequence, denoted as userSeqVec. Here, userBasicVec corresponds to the first feature data, and userSeqVec corresponds to user behavior data. userSeqVec demonstrates strong representation ability for active users but weak representation ability for new users. Furthermore, the fusion result of userBasicVec and userSeqVec is denoted as userFinalVec. Figure 2 The models in the text include Multilayer Perceptron (MLP), "concat" represents the connection operation used in the model, and "pooling" represents the pooling operation used in the model.

[0038] Based on the above model structure, samples are collected for training the deep sequence dual-tower model. The structure of a single sample is as follows:<userBasicFeature,userSequenceFeature,newFeature,label> Here, `userBasicFeature` represents the input data corresponding to `userBasicVec`, `userSequenceFeature` represents the input data corresponding to `userSeqVec`, and `newFeature` represents the input data corresponding to `itemVec`. Positive feedback (read, like, favorite, etc.) is represented by "1", and negative feedback (exposure without reading, blocking, etc.) is represented by "0". The prediction score (logits) is obtained by taking the dot product of `userFinalVec` and `itemVec`. The loss is calculated using the cross-entropy of `logits` and `label`.

[0039] Furthermore, after training, the model outputs vectors corresponding to the first feature data, historical behavior data, and background image feature data. Utilizing the linear additivity of semantic vectors, the `userSeqVec` vector corresponding to the historical behavior data can be obtained by linearly adding the vectors of each piece of information in the sequence of information viewed by the user; the `picVec` vector corresponding to the background image feature data can be obtained by inputting the same semantic features as the information into the model. In this way, all data vectors are mapped to the same vector space, enabling a series of related calculations to be performed.

[0040] In another embodiment of the image display method of this application, the first page includes at least one second control, which is used to indicate details.

[0041] For example, the multiple secondary controls displayed on the first page are the titles of several news articles. When a user clicks on the title of a news article, the details of that news article will be displayed.

[0042] For example, the multiple secondary controls displayed on the first page are the names of several songs. When a user clicks on the name of a song, the corresponding song details, such as lyrics, will be displayed.

[0043] Optionally, the first page is a primary page, displaying multiple secondary controls, which are used to trigger the display of secondary pages.

[0044] In the process of this embodiment, step 120 includes:

[0045] Sub-step A1: Based on the user's historical behavior data, determine the second input to the second control in L consecutive instances from the historical behavior, where L is a positive integer.

[0046] The second input includes touch input performed by the user on the screen, not limited to tapping, swiping, or dragging. The second input can also be air input, such as gestures or facial expressions. It also includes input from physical buttons on the device, not limited to pressing. Furthermore, the second input can include one or more inputs, which can be continuous or timed.

[0047] In this step, the second input is used to manipulate the second control on the first page to trigger the display of details indicated by the second control.

[0048] The second input method can be implemented by, for example, a user clicking on the title of a news article.

[0049] It should be noted that in this embodiment, the first background image is matched based on the user's historical behavior data. Therefore, the user sequence retrieved based on user information such as user account is not empty.

[0050] Therefore, based on the user's historical behavior data, L instances of second input to the second control can be obtained. Optionally, the L instances of second input to the second control can be the most recent, consecutive L instances of second input.

[0051] For example, each click by a user serves as a second input, thereby determining the historical behavior of the L most recent clicks on news headlines.

[0052] Sub-step A2: If at least two input time information of at least two adjacent second inputs are within the first time range, divide the input behavior corresponding to at least two adjacent second inputs into the first window; and if the input time information of any second input is not within the first time range of either the input time information of the adjacent second inputs, divide the input behavior corresponding to any second input into the second window, resulting in m windows, where m is a positive integer, and the m windows include at least one of the first window and the second window.

[0053] For reference, the input time information of the second input L times can be arranged in order from farthest to near to obtain a sequence of length L.

[0054] Furthermore, in the obtained sequence, if at least two adjacent input time information are within a first time range (e.g., thirty minutes), then the input behaviors corresponding to these at least two adjacent input time information are divided into one window, namely the first window, which includes at least two input behaviors. Simultaneously, for a certain input time information, if neither it nor its left and right adjacent input time information are within the first time range, then the input behavior corresponding to that input time information is divided into a separate window, namely the second window, which includes only one input behavior. In this way, m windows are obtained in a sequence of length L.

[0055] The input time information of the second input refers to the moment when the second input is made, which is the moment when the details are triggered to be displayed, such as the moment when the user clicks on the title of a news article.

[0056] The segmentation method provided in this step analyzes multiple input behaviors within a window as indicating that the user frequently views the details of multiple news articles within a short period, suggesting that the user is not particularly interested in these news articles. Conversely, analyzing a single input behavior within a window as indicating that the user spends a considerable amount of time browsing the details of that news article suggests that the user is quite interested in that particular news article. Therefore, based on this method, information clustering can be achieved.

[0057] Sub-step A3: For each window, obtain the third feature data of the window based on the second feature data of the details indicated by the second control corresponding to the second input in the window. The user's historical behavior data includes the second feature data.

[0058] In this step, a window (win) i The code includes Q input actions, which yields the details of Q news items. The second feature data of each of the Q news item details is obtained, and the average of these Q second feature data is calculated to obtain the third feature data (wvec) of the window. i ).

[0059] The second feature data is used to represent the semantic features of the details content, including the category of the details content, keywords in the details content, entities in the details content, and other feature data. The second feature data can characterize the main content of the details content.

[0060] Sub-step A4: For each window, determine the weight of the window based on the first input time information and the first time information in the window, where the first input time information is later than the other input time information in the window.

[0061] Among them, the first input time information (t) i The first time (t0) is the input time information closest to the current time within a window; the first time information (t0) is the current time information. Furthermore, win... i Represented as <wvec i , t i >. win i See the formula for calculating the weights:

[0062]

[0063] In formula (1), α is the decay factor. The larger the value, the faster the decay. Formula (1) can ensure that the window closer to the current time has a larger weight, and the window farther away from the current time has a faster weight decrease. The window closer to the current time has a relatively stable weight, which is in line with the change process of user interests.

[0064] Sub-step A5: Obtain the fourth feature data based on the third feature data of each window and the weight of each window.

[0065] In this step, the third feature data of each window is weighted and summed to obtain the fourth feature data, denoted as userVec. The formula for calculating the fourth feature data is as follows:

[0066]

[0067] Sub-step A6: Determine the first background image that matches the fourth feature data.

[0068] In this step, the fourth feature data is compared with the feature data of each background image in the background image library to find the best matching first background image.

[0069] In this embodiment, the user's continuous second input behaviors to multiple second controls in the history are divided into multiple windows. The closer the window is to the current time, the greater its weight. This can enhance the changes in the user's short-term interests and increase the weight of the information the user has recently read in the user's historical behavior data, so as to capture the user's instantaneous interests.

[0070] In another embodiment of the image display method of this application, at least one second control includes a third control.

[0071] In the process of this embodiment, after step 130, the method further includes:

[0072] Step B1: Receive third input to the third control.

[0073] Third input includes touch input performed by the user on the screen, not limited to clicking, swiping, or dragging. Third input can also be air input, such as gestures or facial expressions. It also includes input from physical buttons on the device, not limited to pressing. Furthermore, third input can include one or more inputs, which can be continuous or timed.

[0074] In this step, the third input is used to manipulate one of the second controls (i.e., the third control) while the first page is displayed, to trigger the display of the first details indicated by the third control.

[0075] For example, when the first page is displayed, a user may be interested in the title of a news article and click on it.

[0076] Step B2: In response to the third input, display the first details indicated by the third control.

[0077] In this step, you switch from the first page to the first details page.

[0078] Step B3: When returning to the first page from the first details content, obtain the fifth feature data of the first details content and the first weight corresponding to the first details content.

[0079] When returning to the first page from the first details, the third input can be considered the most recent second input in the history.

[0080] For example, if the user clicks the "back" option after the first details page is displayed, the first page will be displayed.

[0081] In the case of returning to the first page from the first details content, the details content displayed triggered by the most recent second input (i.e., the third input) (i.e., the first details content) usually reflects the user's current high point of interest. Therefore, in this step, the fifth feature data of the first details content, denoted as lastReadNewsVec, and the first weight corresponding to the first details content, denoted as r, are obtained to match a new background image for display when returning to the first page from the first details content.

[0082] Optionally, a primary weight can be pre-set based on the user's browsing habits. The higher the primary weight, the greater the influence of the details content recently viewed by the user on the matching results.

[0083] Step B4: Display the second background image based on the fifth feature data, the first weight, and the fourth feature data.

[0084] In this step, to avoid the first details being content that the user unintentionally browsed, the fourth feature data and the fifth feature data can be merged and then matched with the background image.

[0085] The fourth feature data before fusion is represented as tempUserVec.

[0086] Based on the linear additive nature of semantic data, the fused feature data is represented as userVec. The calculation formula for the fused feature data is as follows:

[0087]

[0088] In this embodiment, an application scenario is as follows: The first page is currently displayed, showing a first background image. After the user clicks to view one of the details, they return to the first page, and a second background image is displayed based on the details the user just viewed. In this way, as the user repeatedly switches between the details and the first page, the background image displayed after each switch is continuously updated and increasingly matches the user's current preferences.

[0089] It should be noted that if at least one second control includes a fourth control, when the user returns to the first page from the first details page, and then clicks to enter the second details indicated by the fourth control and returns again, a new background image can be displayed based on the feature data obtained from the previous L second inputs (excluding the second details content) and the feature data of the second details content, and so on.

[0090] In this embodiment, the background image is re-matched using the details content most recently viewed by the user to obtain a second background image, thereby ensuring that the second background image is closer to the user's current preferences. Simultaneously, the second background image also incorporates the details content previously viewed by the user, thus avoiding the situation where the second background image does not match the user's current preferences due to the most recently viewed details content being uninteresting to the user.

[0091] In the flow of the image display method according to another embodiment of this application, step A6 includes:

[0092] Sub-step C1: Calculate the first score for each background image based on the fourth feature data and the sixth feature data of each background image.

[0093] In this step, the similarity between the fourth feature data (userVec) and the sixth feature data (picVec) of any background image is calculated to obtain the first score, denoted as Rscore. j The formula for calculating the first score is as follows:

[0094] Rscore j =userVec·picVec j (4)

[0095] The higher the score, the more similar the two are.

[0096] Alternatively, the similarity between userVec and picVec can be calculated using common methods such as dot product or cosine similarity.

[0097] Sub-step C2: Based on each first score, determine N1 background images from each background image, where N1 is a positive integer.

[0098] In this step, the N1 background images with the highest scores are selected as candidate images.

[0099] For example, arrange the background images in descending order of their first score, and find the first N1 background images.

[0100] Sub-step C3: Obtain the sixth feature data of each of the S first historical background images. The user's historical behavior data includes the sixth feature data of each of the S first historical background images, where S is a positive integer.

[0101] In this step, the S most recently pushed historical background images to the user are found in the history and used as the S first historical background images.

[0102] Wherein, the sixth feature data of the first historical background image is represented as hPicVec; the set of the sixth feature data of each of the S first historical background images is represented as R. userHistoryPic =(hPicVec1, hPicVec2…hPicVec s ).

[0103] Sub-step C4: For each of the N1 background images, calculate the second score of the background image based on the sixth feature data of each of the S first historical background images.

[0104] In this step, the second score is used to represent the diversity of the candidate images. Based on a bounded greedy strategy, the overall perceived diversity by the user depends on the semantic gap between the candidate images and the S first historical background images.

[0105] Optionally, for any candidate image, first calculate the semantic similarity between the candidate image and a first historical background image, then subtract the semantic similarity from "1" to obtain the semantic difference value between the two images. Further, accumulate S semantic difference values, then calculate the average to obtain the second score, denoted as Dscore. j The formula for calculating the second score is as follows:

[0106]

[0107] Sub-step C5: For each of the N1 background images, obtain the third score of the background image based on the first score and the second score.

[0108] The third score is represented by Fscore. j The formula for calculating the third score is as follows:

[0109] Fscore j =Rscore j *Dscore j (6)

[0110] In this step, for any candidate image, its similarity and diversity are fused to evaluate how well it matches the fourth feature data.

[0111] Sub-step C6: Determine the background image corresponding to the highest third score as the first background image.

[0112] In this step, the candidate image with the highest third score is used as the first background image.

[0113] If the fourth feature data needs to be fused with the fifth feature data of the above embodiment, the fused feature data can be used as the fourth feature data in this embodiment, and can eventually be matched with the second background image.

[0114] In this embodiment, the similarity and diversity of background images are taken into account, and the background image is finally matched so that the display of the background image can not only reflect the user's preferences, but also be rich and colorful, avoiding being too limited, thereby bringing a better experience to the user.

[0115] In another embodiment of the image display method of this application, before step 120, the method further includes:

[0116] Step D1: Obtain the seventh feature data of N2 first users and the historical behavior data of N2 first users. The first feature data matches the seventh feature data of N2 first users.

[0117] In this embodiment, for new users, the userSeqVec corresponding to historical behavior data cannot be obtained by linearly adding the vectors of each piece of information in the information sequence that the user has browsed. Therefore, the idea of ​​user collaboration is adopted to find active users similar to the new user and push the background images that have been pushed to the active users to the new user.

[0118] Therefore, by utilizing the basic profile features of each user, a user base vector is generated. Users who make the most purchases in the context of the background image are selected as seed users, and new users are identified by using the seed user with the closest vector distance as similar users. This requires constructing user base vectors in the model; for example, the vectors corresponding to the first feature data and the seventh feature data are both represented as userBasicVec.

[0119] Optionally, to accelerate the online process from user request to background image rendering, some vector retrieval tools can be used to generate an index of the background image library and seed users offline, and online retrieval of these indexes takes only milliseconds.

[0120] For reference, the semantic features of the background images are obtained and input into the item tower to generate an image vector (picVec) for each background image. The picVecs of all background images are then input into a vector retrieval tool to generate a vector index for the background image library. Top seed users (seedUsers) in the news push scenario are selected, and their basic profiles are input into the user tower to generate basic vectors (userBasicVec) for the seed users. The userBasicVecs of all seed users are then input into a vector retrieval tool to generate a vector index for the top users. The main reason for not using userFinalVec here is that userFinalVec is more influenced by userSeqVec, and the userSeqVec of new users is basically a default value, resulting in a large distance in vector space between the userFinalVecs of new user groups and seed user groups, which is not conducive to cross-group similarity calculation. userBasicVec better reflects the basic profile features of users; users with high userBasicVec similarity are more similar in age and software usage preferences, and these similar users also have similar preferences for background images to some extent.

[0121] In addition, this application uses the two vectors userBasicVec and userSeqVec separately instead of using userFinalVec directly, mainly because the calculation logic of userFinalVec is relatively fixed, and it is not as flexible as using userBasicVec and userSeqVec separately.

[0122] Based on the above, we can obtain N2 first users as similar users of the current user.

[0123] Step D2: Determine the historical behavior data of the N2 first users as the user's historical behavior data.

[0124] In this step, historical behavior data of similar users is used as historical behavior data of the current user, so that background images can be pushed to the current user based on the historical behavior data of similar users.

[0125] Step 120 includes:

[0126] Sub-step D3: Based on the user's historical behavior data, determine N2×k second historical background images, where k is a positive integer.

[0127] Optionally, for any first user, obtain the k most recent historical background images pushed to the first user in the history record, thereby obtaining N2×k historical background images, which are used as N2×k second historical background images.

[0128] Among them, k is obtained by referring to the total number (n) of the required second historical background images and using formula (7). The formula for calculating k is as follows:

[0129] k = n / N², where k is an integer (7)

[0130] Sub-step D4: Calculate the fourth score of N2×k second historical background images based on the matching degree between the seventh feature data and the first feature data.

[0131] In this step, the similarity between the seventh feature data and the first feature data is calculated to obtain the matching score, denoted as seedUserScore. i The calculation method involves taking the dot product of the seventh feature data and the first feature data.

[0132] Furthermore, the fourth score ik For the calculation formula, please refer to:

[0133] score ik =seedUserScore i *(1-1 / k) (8)

[0134] Sub-step D5: Accumulate the fourth score of the same second historical background image.

[0135] In this step, if a duplicate background image appears among N2×k second historical background images, the fourth score of the same background image is accumulated.

[0136] Sub-step D6: Determine the second historical background image corresponding to the highest fourth score as the first background image.

[0137] In this step, the second historical background image with the highest fourth score is used as the first background image.

[0138] In this embodiment, since it is impossible to analyze the user's own operating habits, the system matches user groups with the same characteristics based on the user's own characteristics, and then combines the background images that have been pushed to the user groups to finally determine the matching background image to push to the new user.

[0139] In another embodiment of the image display method of this application, background images in the background image library are adaptively processed to ensure the high quality of the pushed background images. For example, low-quality images are removed; images are appropriately scaled and cropped, black borders are removed, and the subject is highlighted.

[0140] In another embodiment of the image display method of this application, the first background image is adaptively processed before being displayed to ensure the adaptability of the pushed background image. For example, the first background image is appropriately scaled and cropped according to the aspect ratio of the electronic device, the orientation of the electronic device (landscape or portrait), etc.; the first background image is also faded.

[0141] In another embodiment of the image display method of this application, when a second input is detected and a background image is pushed to the user, the background records it in a timely manner to update the user's historical behavior data.

[0142] Optionally, for recording the second input, a judgment method can be set to record only when the second input is deemed a valid view. For example, the judgment conditions include: the duration of displaying the details corresponding to the second input exceeds a certain threshold, or the duration of playing the details corresponding to the second input exceeds half the length of the details themselves.

[0143] In summary, the purpose of this application is to propose a method for generating personalized background images based on users' historical information flow behavior, thereby improving user experience and increasing user stickiness in information flow scenarios. Utilizing browsing data from information flow scenarios, a deep neural network is constructed to generate vector representations of users and background images, mapping them to the same vector space. The relevance can be measured by vector distance. Specifically, user vectors are generated using user sequences; the more recent the browsing data, the greater its influence on the user, better adapting to changes in user interests. For new users whose user sequences are unavailable, a user collaboration approach is adopted to provide them with background images. By comprehensively considering the relevance and diversity of background images, a better user experience is provided. Furthermore, addressing situations where user-background image interaction data is lacking and direct modeling of users and background images is impossible, this application uses a dual-tower model, sampling user browsing data as a bridge, and simultaneously constructs an offline index to accelerate retrieval.

[0144] The image display method provided in this application can be executed by an image display device. This application uses an image display device executing the image display method as an example to illustrate the image display device provided in this application.

[0145] Figure 3 A block diagram of an image display apparatus according to an embodiment of this application is shown. The apparatus includes:

[0146] The first receiving module 10 is used to receive the first input to the first control;

[0147] The first acquisition module 20 is configured to, in response to the first input, acquire a first background image that matches at least one of the first feature data and the historical behavior data, based on the user's first feature data and the user's historical behavior data.

[0148] The first display module 30 is used to display a first background image when displaying a first page indicated by a first control.

[0149] In the embodiments of this application, when a user makes a first input to the first control to trigger the display of the first page, first feature data describing user profile characteristics and historical behavior data describing user behavior characteristics are obtained. Based on at least one of the first feature data and historical behavior data, a matching first background image is found in the background image library, and then the first background image is displayed when the first page is displayed. Therefore, in the embodiments of this application, intelligently displaying background images based on user characteristics and usage habits not only enriches the display effect and increases user browsing interest, but also simplifies user operation by eliminating the need for manual settings.

[0150] Optionally, the first page includes at least one second control for indicating details, and the first acquisition module 20 includes:

[0151] The first determining unit is used to determine, based on the user's historical behavior data, L consecutive second inputs to the second control in the historical behavior, where L is a positive integer;

[0152] The partitioning unit is configured to partition the input behavior corresponding to at least two adjacent second inputs into a first window when at least two input time information of adjacent second inputs are within a first time range; and to partition the input behavior corresponding to any second input into a second window when the input time information of any second input and the input time information of adjacent second inputs are not within the first time range, thereby obtaining m windows, where m is a positive integer, and the m windows include at least one of the first window and the second window;

[0153] The first processing unit is used to obtain the third feature data of each window based on the second feature data of the details indicated by the second control corresponding to the second input in the window, and the user's historical behavior data includes the second feature data.

[0154] The second determining unit is used to determine the weight of each window based on the first input time information and the first time information in the window, wherein the first input time information is later than the other input time information in the window.

[0155] The second processing unit is used to obtain the fourth feature data based on the third feature data of each window and the weight of each window;

[0156] The third determining unit is used to determine the first background image that matches the fourth feature data.

[0157] Optionally, at least one second control includes a third control, and the device further includes:

[0158] The second receiving module is used to receive third input to the third control;

[0159] The second display module is used to display the first details indicated by the third control in response to the third input;

[0160] The second acquisition module is used to acquire the fifth feature data of the first details content and the first weight corresponding to the first details content when returning from the first details content to the first page;

[0161] The third display module is used to display the second background image based on the fifth feature data, the first weight, and the fourth feature data.

[0162] Optionally, the third determining unit includes:

[0163] The first calculation subunit is used to calculate the first score of each background image based on the fourth feature data and the sixth feature data of each background image.

[0164] The first determining subunit is used to determine N1 background images from each background image based on each first score, where N1 is a positive integer;

[0165] The acquisition subunit is used to acquire the sixth feature data of each of the S first historical background images. The user's historical behavior data includes the sixth feature data of each of the S first historical background images, where S is a positive integer.

[0166] The second calculation subunit is used to calculate the second score of the background image for each of the N1 background images based on the sixth feature data of each of the S first historical background images.

[0167] The processing subunit is used to obtain a third score for each of the N1 background images based on the first score and the second score.

[0168] The second determining subunit is used to determine the background image corresponding to the highest third score as the first background image.

[0169] Optionally, the device further includes:

[0170] The third acquisition module is used to acquire the seventh feature data of N2 first users and the historical behavior data of N2 first users, wherein the first feature data matches the seventh feature data of N2 first users;

[0171] The determination module is used to determine the historical behavior data of N2 first users as the user's historical behavior data;

[0172] The first acquisition module 20 includes:

[0173] The fourth determining unit is used to determine N2 second historical background images based on the user's historical behavior data, where k is a positive integer;

[0174] The calculation unit is used to calculate the fourth score of the N2 unit's second historical background images based on the matching degree between the seventh feature data and the first feature data.

[0175] The accumulation unit is used to accumulate the fourth score of the same second historical background image;

[0176] The fifth determining unit is used to determine the second historical background image corresponding to the highest fourth score as the first background image.

[0177] The device in this application embodiment can be an electronic device or a component within an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal or other devices besides a terminal. For example, the electronic device can be a mobile phone, tablet computer, laptop computer, PDA, in-vehicle electronic device, mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc. It can also be a server, network attached storage (NAS), personal computer (PC), television set (TV), ATM, or self-service machine, etc. This application embodiment does not specifically limit the device.

[0178] The apparatus in this application embodiment can be an apparatus with an action system. The action system can be an Android action system, an iOS action system, or other possible action systems, and this application embodiment does not specifically limit it.

[0179] The apparatus provided in this application embodiment can implement the various processes implemented in the above method embodiments and achieve the same technical effects. To avoid repetition, it will not be described again here.

[0180] Optionally, such as Figure 4 As shown, this application embodiment also provides an electronic device 100, including a processor 101, a memory 102, and a program or instructions stored in the memory 102 and executable on the processor 101. When the program or instructions are executed by the processor 101, they implement the various steps of any of the above-described image display method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0181] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0182] Figure 5 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of this application.

[0183] The electronic device 1000 includes, but is not limited to, the following components: radio frequency unit 1001, network module 1002, audio output unit 1003, input unit 1004, sensor 1005, display unit 1006, user input unit 1007, interface unit 1008, memory 1009, processor 1010, camera 1011, etc.

[0184] Those skilled in the art will understand that the electronic device 1000 may also include a power supply (such as a battery) for supplying power to various components. The power supply may be logically connected to the processor 1010 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 5 The electronic device structure shown does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0185] The user input unit 1007 is used to receive a first input to the first control; the processor 1010 is used to, in response to the first input, obtain a first background image that matches at least one of the first feature data and the historical behavior data based on the user's first feature data and the user's historical behavior data; and the display unit 1006 is used to display the first background image when displaying a first page indicated by the first control.

[0186] In the embodiments of this application, when a user makes a first input to the first control to trigger the display of the first page, first feature data describing user profile characteristics and historical behavior data describing user behavior characteristics are obtained. Based on at least one of the first feature data and historical behavior data, a matching first background image is found in the background image library, and then the first background image is displayed when the first page is displayed. Therefore, in the embodiments of this application, intelligently displaying background images based on user characteristics and usage habits not only enriches the display effect and increases user browsing interest, but also simplifies user operation by eliminating the need for manual settings.

[0187] Optionally, the first page includes at least one second control, the second control being used to indicate details. The processor 1010 is further configured to, based on the user's historical behavior data, determine L consecutive second inputs to the second control in the historical behavior, where L is a positive integer; if at least two input time information of at least two adjacent second inputs are within a first time range, classify the input behavior corresponding to the at least two adjacent second inputs into a first window; and if the input time information of any second input and the input time information of any adjacent second input are not within the first time range, classify the input behavior corresponding to any second input into a second window. The system generates m windows, where m is a positive integer, and the m windows include at least one of the first window and the second window. For each window, a third feature data is obtained based on the second feature data of the details indicated by the second control corresponding to the second input in the window, wherein the user's historical behavior data includes the second feature data. For each window, a weight is determined based on the first input time information and the first time information in the window, wherein the first input time information is later than the other input time information in the window. A fourth feature data is obtained based on the third feature data of each window and the weight of each window. A first background image matching the fourth feature data is determined.

[0188] Optionally, the at least one second control includes a third control; the user input unit 1007 is further configured to receive a third input to the third control; the display unit 1006 is further configured to display first details indicated by the third control in response to the third input; the processor 1010 is further configured to obtain a fifth feature data of the first details content and a first weight corresponding to the first details content when returning from the first details content to the first page; and the display unit 1006 is further configured to display a second background image based on the fifth feature data, the first weight, and the fourth feature data.

[0189] Optionally, the processor 1010 is further configured to: calculate a first score for each background image based on the fourth feature data and the sixth feature data of each background image; determine N1 background images, where N1 is a positive integer, based on the first scores; acquire the sixth feature data of S first historical background images, where the user's historical behavior data includes the sixth feature data of the S first historical background images, where S is a positive integer; calculate a second score for each of the N1 background images based on the sixth feature data of the S first historical background images; obtain a third score for each of the N1 background images based on the first score and the second score; and determine the background image corresponding to the highest third score as the first background image.

[0190] Optionally, the processor 1010 is further configured to acquire the seventh feature data of N2 first users and the historical behavior data of the N2 first users, wherein the first feature data matches the seventh feature data of the N2 first users; determine the historical behavior data of the N2 first users as the historical behavior data of the user; determine N2×k second historical background images based on the historical behavior data of the user, where k is a positive integer; calculate the fourth score of the N2×k second historical background images based on the matching degree between the seventh feature data and the first feature data; accumulate the fourth scores of the same second historical background image; and determine the second historical background image corresponding to the highest fourth score as the first background image.

[0191] In summary, the purpose of this application is to propose a method for generating personalized background images based on users' historical information flow behavior, thereby improving user experience and increasing user stickiness in information flow scenarios. Utilizing browsing data from information flow scenarios, a deep neural network is constructed to generate vector representations of users and background images, mapping them to the same vector space. The relevance can be measured by vector distance. Specifically, user vectors are generated using user sequences; the more recent the browsing data, the greater its influence on the user, better adapting to changes in user interests. For new users whose user sequences are unavailable, a user collaboration approach is adopted to provide them with background images. By comprehensively considering the relevance and diversity of background images, a better user experience is provided. Furthermore, addressing situations where user-background image interaction data is lacking and direct modeling of users and background images is impossible, this application uses a dual-tower model, sampling user browsing data as a bridge, and simultaneously constructs an offline index to accelerate retrieval.

[0192] It should be understood that, in this embodiment, the input unit 1004 may include a graphics processing unit (GPU) 10041 and a microphone 10042. The GPU 10041 processes image data of still images or video images obtained by an image capture device (such as a camera) in video image capture mode or image capture mode. The display unit 1006 may include a display panel 10061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit 1007 includes at least one of a touch panel 10071 and other input devices 10072. The touch panel 10071 is also called a touch screen. The touch panel 10071 may include a touch detection device and a touch controller. Other input devices 10072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be described in detail here. The memory 1009 can be used to store software programs and various data, including but not limited to applications and motion systems. Processor 1010 may integrate an application processor and a modem processor. The application processor mainly handles the action system, user page, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into processor 1010.

[0193] The memory 1009 can be used to store software programs and various data. The memory 1009 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 1009 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 1009 in this embodiment includes, but is not limited to, these and any other suitable types of memory.

[0194] The processor 1010 may include one or more processing units; optionally, the processor 1010 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into the processor 1010.

[0195] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described image display method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0196] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0197] This application also provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various processes of the above-described image display method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0198] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0199] This application provides a computer program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the above-described image display method embodiments, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0200] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0201] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0202] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. An image display method, characterized in that, The method includes: Receive the first input to the first control; In response to the first input, a first background image matching at least one of the first feature data and the historical behavior data is obtained based on the user's first feature data and the user's historical behavior data; the first feature data is used to represent the user's basic profile features; the user's historical behavior data is used to represent the semantic features of the information the user browses. When the first page indicated by the first control is displayed, the first background image is displayed; The first page includes at least one second control for indicating details. The step of obtaining a first background image matching at least one of the user's first feature data and historical behavior data includes: Based on the user's historical behavior data, determine L consecutive instances of second input to the second control from the historical behavior, where L is a positive integer; If at least two input time information of at least two consecutive second inputs are within a first time range, the input behaviors corresponding to the at least two consecutive second inputs are divided into a first window; and if the input time information of any second input is not within the first time range from the input time information of the adjacent second inputs, the input behavior corresponding to any second input is divided into a second window, resulting in m windows, where m is a positive integer, and the m windows include at least one of the first window and the second window; the input time information of the second input is the moment when the second input is performed; For each window, the third feature data of the window is obtained based on the second feature data of the details content indicated by the second control corresponding to the second input in the window. The user's historical behavior data includes the second feature data. The second feature data is used to represent the semantic features of the details content. The third feature data of the window is the average value of the second feature data. For each window, the weight of the window is determined based on the first input time information and the first time information in the window, wherein the first input time information is later than the other input time information in the window; the first time information is the current time information; the magnitude and stability of the window's weight are negatively correlated with the time distance from the current time, and the rate of decrease of the weight is positively correlated with the time distance; The fourth feature data is obtained based on the third feature data of each window and the weight of each window; the fourth feature data is obtained by weighted summation of the third feature data of each window and the weight of each window. A first background image matching the fourth feature data is determined.

2. The method according to claim 1, characterized in that, The at least one second control includes a third control, and after displaying the first background image when the first page indicated by the first control is displayed, the method further includes: Receive third input to a third control; In response to the third input, the first details indicated by the third control are displayed; When returning from the first details content to the first page, obtain the fifth feature data of the first details content and the first weight corresponding to the first details content; The second background image is displayed based on the fifth feature data, the first weight, and the fourth feature data.

3. The method according to claim 1, characterized in that, The determination of the first background image matching the fourth feature data includes: Based on the fourth feature data and the sixth feature data of each background image, calculate the first score of each background image; the first score is the similarity between the fourth feature data and the sixth feature data of each background image. Based on the first scores, N1 background images are determined from the background images, where N1 is a positive integer. Obtain the sixth feature data of each of the S first historical background images, wherein the user's historical behavior data includes the sixth feature data of each of the S first historical background images, and S is a positive integer; For each of the N1 background images, a second score is calculated based on the sixth feature data of each of the S first historical background images; wherein, for any background image, the semantic similarity between the background image and a first historical background image is calculated, and the semantic similarity is subtracted from 1 to obtain the semantic gap value between the two images, and the average of the S semantic gap values ​​is calculated, and the average value is the second score of the background image. For each of the N1 background images, a third score is obtained based on the first score and the second score; The background image corresponding to the highest third score is determined as the first background image.

4. The method according to claim 1, characterized in that, Before obtaining a first background image matching at least one of the first feature data and the historical behavior data based on the user's first feature data and the user's historical behavior data, the method further includes: Obtain the seventh feature data of N2 first users and the historical behavior data of the N2 first users. The first feature data matches the seventh feature data of the N2 first users. The first user is the user with the closest user vector distance among the top consumers in the background image push scene. The historical behavior data of the N2 first users are determined as the historical behavior data of the user; The step of obtaining a first background image that matches at least one of the first feature data and the historical behavior data based on the user's first feature data and the user's historical behavior data includes: Based on the user's historical behavior data, determine N2 k second historical background images, where k is a positive integer; k is the number of historical background images most recently pushed to the first user in the history; N2 There are duplicate historical background images among the k second historical background images; The N2 is calculated based on the matching degree between the seventh feature data and the first feature data. The fourth score of k second historical background images; the matching degree is the similarity between the seventh feature data and the first feature data; The fourth score is: in, The fourth score of the k second historical background images, The matching degree between the seventh feature data and the first feature data of i first users, where k is the number of historical background images most recently pushed to the first user in the history; The fourth score is accumulated from the same second historical background image; The second historical background image corresponding to the highest fourth score is determined as the first background image.

5. An image display device, characterized in that, The device includes: The first receiving module is used to receive the first input to the first control; A first acquisition module is configured to, in response to the first input, acquire a first background image that matches at least one of the first feature data and the historical behavior data, based on the user's first feature data and the user's historical behavior data; the first feature data is used to represent the user's basic profile features; the user's historical behavior data is used to represent the semantic features of the information the user browses. The first display module is configured to display the first background image when the first page indicated by the first control is displayed; The first page includes at least one second control, which is used to indicate details. The first acquisition module includes: The first determining unit is used to determine, based on the user's historical behavior data, L consecutive second inputs to the second control in the historical behavior, where L is a positive integer; The partitioning unit is configured to partition the input behavior corresponding to at least two adjacent second inputs into a first window when at least two input time information of the second inputs are within a first time range; and to partition the input behavior corresponding to any second input into a second window when the input time information of any second input and the input time information of adjacent second inputs are not within the first time range, thereby obtaining m windows, where m is a positive integer, and the m windows include at least one of the first window and the second window; the input time information of the second input is the moment when the second input is performed; The first processing unit is configured to, for each window, obtain third feature data of the window based on the second feature data of the details content indicated by the second control corresponding to the second input in the window, wherein the user's historical behavior data includes the second feature data; the second feature data is used to represent the semantic features of the details content; and the third feature data of the window is the average value of the second feature data. The second determining unit is used to determine the weight of each window based on the first input time information and the first time information in the window, wherein the first input time information is later than the other input time information in the window; the first time information is the current time information; the magnitude and stability of the window's weight are negatively correlated with the time distance from the current time, and the rate of decrease of the weight is positively correlated with the time distance; The second processing unit is used to obtain fourth feature data based on the third feature data of each window and the weight of each window; the fourth feature data is obtained by weighted summation of the third feature data of each window and the weight of each window. The third determining unit is used to determine the first background image that matches the fourth feature data.

6. The apparatus according to claim 5, characterized in that, The at least one second control includes a third control, and the device further includes: The second receiving module is used to receive third input to the third control; The second display module is used to display the first details indicated by the third control in response to the third input; The second acquisition module is used to acquire the fifth feature data of the first details content and the first weight corresponding to the first details content when returning from the first details content to the first page; The third display module is used to display the second background image based on the fifth feature data, the first weight, and the fourth feature data.

7. The apparatus according to claim 5, characterized in that, The third determining unit includes: The first calculation subunit is used to calculate the first score of each background image based on the fourth feature data and the sixth feature data of each background image; the first score is the similarity between the fourth feature data and the sixth feature data of each background image. The first determining subunit is used to determine N1 background images from the background images based on the first scores, where N1 is a positive integer. The acquisition subunit is used to acquire the sixth feature data of each of the S first historical background images, wherein the user's historical behavior data includes the sixth feature data of each of the S first historical background images, and S is a positive integer; The second calculation subunit is used to calculate the second score of each of the N1 background images based on the sixth feature data of each of the S first historical background images; wherein, for any background image, the semantic similarity between the background image and a first historical background image is calculated, the semantic similarity is subtracted from 1 to obtain the semantic gap value between the two images, and the average of the S semantic gap values ​​is calculated, the average value being the second score of the background image. The processing subunit is used to obtain a third score for each of the N1 background images based on the first score and the second score. The second determining subunit is used to determine the background image corresponding to the highest third score as the first background image.

8. The apparatus according to claim 5, characterized in that, The device further includes: The third acquisition module is used to acquire the seventh feature data of N2 first users and the historical behavior data of the N2 first users. The first feature data matches the seventh feature data of the N2 first users. The first user is the user with the closest user vector distance among the top consumers in the push background image scene. The determination module is used to determine the historical behavior data of the N2 first users as the historical behavior data of the user; The first acquisition module includes: The fourth determining unit is used to determine N2 based on the user's historical behavior data. k second historical background images, where k is a positive integer; k is the number of historical background images most recently pushed to the first user in the history; N2 There are duplicate historical background images among the k second historical background images; The calculation unit is configured to calculate N2 based on the matching degree between the seventh feature data and the first feature data. The fourth score of k second historical background images; the matching degree is the similarity between the seventh feature data and the first feature data; The fourth score is: in, The fourth score of the k second historical background images, The matching degree between the seventh feature data and the first feature data of i first users, where k is the number of historical background images most recently pushed to the first user in the history; An accumulation unit is used to accumulate the fourth score of the same second historical background image; The fifth determining unit is used to determine the second historical background image corresponding to the highest fourth score as the first background image.

9. An electronic device, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the image display method as described in any one of claims 1 to 4.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the image display method as described in any one of claims 1 to 4.

Images