Information display method and device, electronic equipment, storage medium and product

Abstract

The embodiment of the invention discloses an information display method and device, electronic equipment, a storage medium and a product. The method comprises the steps of obtaining to-be-displayed information on a to-be-displayed floor to be displayed to a target page; determining a target configuration parameter of the to-be-displayed floor based on the to-be-displayed information and a pre-trained floor configuration model; wherein the target configuration parameter is used for configuring a display style of the to-be-displayed floor; and based on the target configuration parameter, adding the to-be-displayed information to a to-be-displayed floor of the target page to display the to-be-displayed information. According to the technical scheme, operation personnel do not need to participate, the configuration efficiency and accuracy of the to-be-displayed floors are improved, and the floor configuration cost can be reduced.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of Internet technology, and in particular to an information display method, device, electronic device, storage medium, and product. Background Art

[0002] With the rapid development of the Internet economy, all kinds of information can be displayed through Internet platforms. Operators need to build display pages based on the content to be displayed so that the relevant pages can be displayed to users for browsing.

[0003] In the prior art, the display style for each floor on a display page requires manual determination and configuration by operators. The display information is then populated onto the floor according to the determined display style to complete the information display operation. However, during the implementation of the present invention, it was discovered that the prior art has at least the following technical issues: manual configuration is inefficient and prone to errors, and determining the styles for different floors requires high design skills from operators, resulting in increased costs. Summary of the Invention

[0004] The embodiments of the present invention provide an information display method, device, electronic device, storage medium and product to achieve the purpose of improving the configuration efficiency and accuracy of floors to be displayed and reducing the cost of floor configuration.

[0005] According to one aspect of the present invention, there is provided an information display method, comprising:

[0006] Obtain the information to be displayed on the display layer to be displayed on the target page;

[0007] Determining target configuration parameters of the floor to be displayed based on the information to be displayed and a pre-trained floor configuration model; wherein the target configuration parameters are used to configure the display style of the floor to be displayed;

[0008] Based on the target configuration parameters, the information to be displayed is added to the to-be-displayed floor of the target page to display the information to be displayed.

[0009] According to another aspect of the present invention, there is provided an information display device, the device comprising:

[0010] An information acquisition module is used to acquire information to be displayed on a floor to be displayed on a target page;

[0011] A parameter determination module, configured to determine target configuration parameters of the floor to be displayed based on the information to be displayed and a pre-trained floor configuration model; wherein the target configuration parameters are used to configure the display style of the floor to be displayed;

[0012] An information adding module is used to add the information to be displayed to the to-be-displayed floor of the target page based on the target configuration parameters, so as to display the information to be displayed.

[0013] According to another aspect of the present invention, an electronic device is provided, comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can perform the information display method described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the information display method described in any embodiment of the present invention when executed.

[0018] According to another aspect of the present invention, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the information display method according to any embodiment of the present invention is implemented.

[0019] The technical solution of the embodiment of the present invention determines the target configuration parameters of the floor to be displayed by obtaining the information to be displayed on the floor to be displayed that needs to be displayed on the target page and a pre-trained floor configuration model, thereby automatically determining the target configuration parameters for configuring the display style of the floor to be displayed through the floor configuration model without the intervention of operating personnel; and based on the determined target configuration parameters, the information to be displayed is added to the floor to be displayed on the target page to complete the display of the information to be displayed. Since no human intervention is required in the process, the configuration efficiency and accuracy of the floor to be displayed are improved, which is conducive to reducing the floor configuration cost.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 is a flow chart of an information display method provided according to an embodiment of the present invention;

[0023] Figure 2 This is a display effect diagram of a floor to be displayed provided according to an embodiment of the present invention;

[0024] Figure 3 is a flowchart of another information display method provided according to an embodiment of the present invention;

[0025] Figure 4 is a flowchart of another information display method provided according to an embodiment of the present invention;

[0026] Figure 5 is a schematic diagram of a model training process provided according to an embodiment of the present invention;

[0027] Figure 6 is a structural diagram of an information display device provided according to an embodiment of the present invention;

[0028] Figure 7 It is a structural diagram of an electronic device for implementing the information display method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "etc." and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] It should be noted that the collection, collection, updating, analysis, processing, use, transmission, and storage of user personal information involved in the technical solutions disclosed herein comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken with respect to user personal information to prevent unauthorized access to user personal information data and maintain the security of user personal information and network security.

[0032] Before introducing the technical solution, an example explanation of the application scenario can be given first. This technical solution can be applied to the scenario of adding information to be displayed on the floors on the information display page; the floor is a page composition unit composed of layout, elements and data; different information can be displayed on each floor, so that by designing multiple floors on the information display page, the display information or services on the information display page can be enriched, and diversified information display can be performed to the user. Exemplarily, the information display page can be a page such as an item explanation page and an activity display page provided by the e-commerce platform, and each floor displays the introduction information of an item, or the activity description of an activity. In the process of displaying the information to be displayed on the floor to be displayed, the display style of the floor can be configured, and the information to be displayed can be rendered to the floor to be displayed to complete the display of the information to be displayed. Based on this technical solution, the target configuration parameters of the floor to be displayed in the target page can be determined through the floor configuration model, so that the operator does not need to manually design it, which improves the configuration efficiency and accuracy of the floor to be displayed, and helps to reduce the floor configuration cost.

[0033] Figure 1 This is a flow chart of an information display method provided according to an embodiment of the present invention. This embodiment is applicable to determining target configuration parameters for a floor to be displayed on a target page, and displaying the information to be displayed on the floor to be displayed according to the target configuration parameters. This method can be performed by an information display device, which can be implemented in hardware and / or software.

[0034] like Figure 1As shown, the method of this embodiment may specifically include:

[0035] S110: Acquire information to be displayed on a floor to be displayed on a target page.

[0036] The target page can be a webpage used to display information to users; for example, it can be an item display page provided by an e-commerce platform, or an interactive communication page displayed on a social media platform. Different levels can be designed for the target page based on the type of information to be displayed. Levels on the target page that do not display information or require adjustment are designated as levels to be displayed.

[0037] In actual applications, you can first create all the floors in the target page and then configure the display style of the floors. Alternatively, to improve efficiency, you can configure the newly created floors simultaneously after creating them. The following describes the process of obtaining the display information for these two scenarios.

[0038] 1. When configuring after all creation, you can set the configuration method of the floors and the method of obtaining the information to be displayed for each floor to be displayed based on the actual needs of the display order and display location of the display information.

[0039] Specifically, when there can be multiple floors to be displayed and the display order and position of the information are not required, multiple floors to be displayed can be configured in batches; during batch configuration, the floors on the target page that have not displayed information are used as floors to be displayed, the number of floors to be displayed is used as the target number, and the preset display information consistent with the target number is selected from the pre-stored preset display information as the information to be displayed; the selection method can be random selection, selection according to the type of preset display information, or selection according to the amount of information to be displayed.

[0040] In addition, if there are requirements for the order and location of information display, each floor to be displayed can be configured one by one. When configuring one by one, the method for obtaining the information to be displayed can be: the page currently displayed to the operation and maintenance terminal is used as the target page, and in response to the selection trigger operation of a floor on the target page, the selected floor is used as the floor to be displayed; wherein, the selected floor can be a floor for which information is not displayed, or a floor for which the displayed information needs to be replaced; in response to the information input operation for the floor to be displayed, the information to be displayed for the floor to be displayed is determined based on the input information. For example, the input information can be an information identifier corresponding to the preset display information, and the preset display information corresponding to the information identifier is obtained as the information to be displayed. Alternatively, the input information can be directly used as the information to be displayed.

[0041] 2. When a new floor of the target page is synchronously configured, the specific implementation method of obtaining the information to be displayed on the floor to be displayed on the target page may include: in response to the configuration trigger operation of the new floor in the target page, the new floor is used as the floor to be displayed, and the information to be displayed on the floor to be displayed is obtained.

[0042] Specifically, the configuration trigger operation for a new floor may be: an operation of displaying the new floor on the target page; or a click operation on a one-key configuration control; wherein the one-key configuration control is a control for configuring the newly created floor.

[0043] In this embodiment, in response to a configuration trigger operation for a newly created floor on a target page, the newly created floor associated with the configuration trigger operation may be designated as a floor to be displayed. The method for obtaining the information to be displayed for the floor to be displayed may include generating an information acquisition request corresponding to the newly created floor, sending the information acquisition request to an operations terminal, and using the feedback information sent by the operations terminal as the information to be displayed for the newly created floor. Alternatively, the floor type of the newly created floor may be determined, and pre-set display information matching the floor type may be selected from pre-stored pre-set display information as the information to be displayed.

[0044] For example, a floor type may include at least one of an event display type, a video display type, an item introduction type, and a news broadcast type. Preset display information may include at least one of event information, video information, item introduction information, and news information. For example, if the floor type of a newly created floor is determined to be an event display type, then event information matching the event display type may be selected as the information to be displayed.

[0045] It should be noted that when creating a new floor, the floor type of the created floor can be set, and the floor type can be recorded and stored. When determining the floor type of the new floor, the stored record can be directly read. Alternatively, different areas in the target page correspond to different types of floors. For example, the target page can be divided into three areas, which are used to place floors of event display type, item introduction type, and news broadcast type respectively. When determining the floor type of a new floor, the floor type corresponding to the regional location of the new floor can be used as the floor type of the new floor.

[0046] This embodiment configures the newly created floors through a one-click configuration control, eliminating the need for operators to operate step by step, avoiding human errors, and helping to improve user convenience; and synchronously configuring the newly created floors helps to improve the efficiency of floor configuration in the target page.

[0047] S120 : Determine target configuration parameters of the floor to be displayed based on the information to be displayed and a pre-trained floor configuration model.

[0048] The target configuration parameters are used to configure the display style of the floor to be displayed. For example, the target configuration parameters include floor style parameters for configuring the floor's appearance and display format parameters for configuring the display format of the information to be displayed on the floor to be displayed. Floor style parameters include at least one of floor margins, background color, corner shape, and floor height. For example, floor margins include card margins, top and bottom margins, and left and right margins. Floor style parameters may also include the width of the floor's border.

[0049] In this embodiment, when determining target configuration parameters, a display feature vector corresponding to the information to be displayed can be determined, and a pre-created request interface corresponding to the floor to be displayed can be called. Through this request interface, a pre-trained floor configuration model can be invoked to process the display feature vector and determine the target configuration parameters for the floor to be displayed. Specifically, the information to be displayed includes at least one of textual information and image information. Based on the information to be displayed and the pre-trained floor configuration model, determining the target configuration parameters for the floor to be displayed can be achieved by: determining a target encoder corresponding to the information to be displayed from at least one pre-generated encoder; inputting the information to be displayed into the target encoder to obtain a display feature vector corresponding to the information to be displayed; and inputting the display feature vector into the pre-trained floor configuration model to obtain the target configuration parameters corresponding to the information to be displayed.

[0050] Among them, the target encoder includes at least one of an image encoder and a text encoder; the image encoder is used to encode image information and can be a convolutional neural network; the text encoder is used to encode text information and can be a transformer network (Transformer).

[0051] In this embodiment, based on the attributes of the information to be displayed, a pre-generated encoder corresponding to the attribute can be determined as the target encoder. Specifically, when the information to be displayed is text information, a text encoder can be used as the target encoder; when the information to be displayed is image information, an image encoder can be used as the target encoder.

[0052] After determining the target encoder, to better reflect the characteristic information contained in the information to be displayed and input it into the floor configuration model, the information to be displayed can be input into the target encoder, and the output vector of the target encoder can be used as the display feature vector corresponding to the information to be displayed. The display feature vector is a feature vector that reflects the characteristics of the information to be displayed. Furthermore, by inputting the display feature vector into a pre-trained floor configuration model, the target configuration parameters corresponding to the information to be displayed are determined based on the output of the floor configuration model.

[0053] This embodiment adopts different target encoders for different types of information to be displayed, so that matching target configuration parameters can be determined for different types of information to be displayed, and then different types of information to be displayed can be displayed on the floors to be displayed, which is conducive to improving the flexibility and effectiveness of displaying information on the floors to be displayed.

[0054] In a specific implementation, the floor configuration model can be a neural network model. Based on the output of the floor configuration model, the target configuration parameters corresponding to the information to be displayed can be determined by inputting the display feature vector into a pre-trained floor configuration model and using the configuration parameters output by the floor configuration model as the target configuration parameters for the floor to be displayed.

[0055] Alternatively, the floor configuration model may be a clustering model. When determining the target configuration parameters, the display feature vector corresponding to the information to be displayed may be input into a pre-trained floor configuration model, and the target configuration parameters corresponding to the floor to be displayed may be determined based on the classification results output by the floor configuration model.

[0056] When the floor configuration model is a clustering model, to improve the accuracy of classification results and the clustering effect of the information to be displayed, features in the display feature vector that contribute to clustering can be highlighted before inputting the display feature vector into the floor configuration model. Alternatively, inputting the display feature vector into a pre-trained floor configuration model to obtain target configuration parameters corresponding to the information to be displayed can be achieved by: inputting the display feature vector into a pre-trained clustering network, updating the display feature vector based on the obtained output vector; and inputting the updated display feature vector into the pre-trained floor configuration model to obtain target configuration parameters corresponding to the information to be displayed.

[0057] Among them, the clustering network can be composed of a three-layer multi-layer perceptron network.

[0058] In this embodiment, the display feature vector can be input into a pre-trained clustering network to obtain the clustering network's output vector. It should be noted that the clustering network can act as a feature extractor, further extracting features from the display feature vector to extract features that are more conducive to clustering. The output vector obtained by the clustering network is more likely to reflect features that facilitate clustering than the display feature vector. Furthermore, the output vector can be updated to a display feature vector, which is then input into the floor configuration model. Based on the classification results of the floor configuration model, the target configuration parameters corresponding to the information to be displayed are determined.

[0059] In this embodiment, the output vector obtained by the clustering network is used to update the display feature vector, so that the updated display feature vector can fully reflect the features that are conducive to clustering, thereby helping to improve the accuracy of the classification results; and, the clustering network can achieve a dimensionality reduction effect, which is convenient for improving the efficiency of subsequent clustering operations.

[0060] S130: Based on the target configuration parameters, add the information to be displayed to the to-be-displayed floor of the target page to display the information to be displayed.

[0061] The target configuration parameters include floor style parameters and display format parameters for the information to be displayed; floor style parameters include at least one of floor margins, background color, corner shape, and floor height; the information to be displayed may be configuration text, which includes text and image links to be displayed on the floor to be displayed. The text and image to be displayed on the floor to be displayed can be obtained through the configuration text. For example, the configuration text may be in the JSON (JavaScript Object Notation) format.

[0062] In a specific implementation, at least one of the floor margin, background color, corner shape, and floor height of the floor to be displayed can be configured according to the floor display parameters. The information to be displayed is added to the floor to be displayed after being adjusted according to the floor display parameters, thereby performing a display operation on the information to be displayed.

[0063] Optionally, based on the target configuration parameters, the information to be displayed is added to the floor to be displayed of the target page, including: rendering the information to be displayed into a picture to be displayed based on the floor style parameters and the display format parameters; and adding the picture to be displayed to the floor to be displayed of the target page.

[0064] In a specific implementation, the display format of the information to be displayed on the floor to be displayed can be adjusted according to the display format parameters. For example, the display format parameters may include at least one of the font, font size, position, image color, and image size of the information to be displayed on the floor to be displayed. The text and images corresponding to the adjusted information to be displayed are rendered into images that match the floor style parameters and used as the images to be displayed. The images to be displayed can then be directly added to the floor to be displayed on the target page. For example, the images to be displayed can be images or multimedia pages created using HTML5 (Hypertext Markup Language, Version 5).

[0065] In order to more clearly show the display effect of the floor to be displayed on the display information, please refer to Figure 2 . Figure 2In the example, the displayed information is a description of item A. After the floor is configured, the corners are rounded. A shadow background is used for the image corresponding to the displayed information to highlight the content. The text corresponding to the displayed information is highlighted in bold.

[0066] This embodiment provides a method for displaying information to be displayed on a floor to be displayed. The image to be displayed is determined by using floor style parameters and display format parameters, so that the image to be displayed can better highlight the characteristics of the information to be displayed and effectively display the information to be displayed.

[0067] The technical solution of the embodiment of the present invention determines the target configuration parameters of the floor to be displayed by obtaining the information to be displayed on the floor to be displayed that needs to be displayed on the target page and a pre-trained floor configuration model, thereby automatically determining the target configuration parameters for configuring the display style of the floor to be displayed through the floor configuration model without the intervention of operating personnel; and based on the determined target configuration parameters, the information to be displayed is added to the floor to be displayed on the target page to complete the display of the information to be displayed. Since no human intervention is required in the process, the configuration efficiency and accuracy of the floor to be displayed are improved, which is conducive to reducing the floor configuration cost.

[0068] Figure 3 This is a flow chart of another information display method provided according to an embodiment of the present invention. Based on the above embodiment, this embodiment provides a method for determining the target configuration parameters of the floor to be displayed: determining the target cluster corresponding to the information to be displayed through the floor configuration model, and determining the alternative configuration parameters based on the target cluster, and determining the target configuration parameters corresponding to the floor to be displayed from the alternative configuration parameters. The explanations of the terms that are the same or corresponding to the above embodiments are not repeated here. Figure 3 As shown, the method includes:

[0069] S210: Acquire information to be displayed on a floor to be displayed on a target page.

[0070] S220 : Based on the information to be displayed and the pre-trained floor configuration model, determine a target cluster corresponding to the information to be displayed; and use the sample configuration parameters corresponding to the target cluster as candidate configuration parameters among the pre-stored sample configuration parameters.

[0071] Among them, the floor configuration model includes a Gaussian mixture model.

[0072] Specifically, the display feature vector corresponding to the information to be displayed can be input into the floor configuration model. The floor configuration model then determines a target cluster corresponding to the information to be displayed from at least one predetermined cluster. Each cluster corresponds to at least one sample configuration parameter, which is the actual configuration parameter of the displayed floor. For example, the current configuration parameters of the displayed floor on the target page can be selected as the sample configuration parameters.

[0073] Optionally, the actual floor style parameters of the displayed floor and the actual display format parameters of the displayed information corresponding to the displayed floor. After determining the target cluster, at least one sample configuration parameter corresponding to the target cluster can be used as an alternative configuration parameter.

[0074] S230: Determine target configuration parameters corresponding to the floor to be displayed from among the candidate configuration parameters.

[0075] In a specific implementation, any candidate configuration parameter can be used as the target configuration parameter corresponding to the floor to be displayed. Alternatively, the target configuration parameter corresponding to the floor to be displayed can be determined based on the number of candidate configuration parameters.

[0076] Specifically, when the number of alternative configuration parameters is less than or equal to the first preset number, recommendation information containing each alternative configuration parameter can be generated and sent to the operation terminal for display. Based on the configuration confirmation information sent by the operation terminal, the alternative configuration parameters that match the configuration confirmation information are determined among the alternative configuration parameters as the target configuration parameters, thereby simplifying the configuration process while combining the actual needs of the operator.

[0077] In addition, the implementation method for determining the target configuration parameters corresponding to the floor to be displayed among the alternative configuration parameters can also be: when the number of alternative configuration parameters is greater than a first preset number, determining the actual impact degree value generated by the alternative reference floors corresponding to the alternative configuration parameters within a preset time period; based on the actual impact degree value, determining the target configuration parameters corresponding to the floor to be displayed among the alternative configuration parameters.

[0078] The first preset number is a positive integer. The actual influence value includes at least one of the exposure rate and the order conversion rate of the candidate reference floor.

[0079] It should be noted that, when there are a large number of alternative configuration parameters, in order to minimize the workload of operators, the target configuration parameters can be automatically determined directly based on the alternative configuration parameters.

[0080] Specifically, the displayed floors corresponding to the alternative configuration parameters can be used as alternative reference floors. The actual impact value generated by the alternative reference floors corresponding to each alternative configuration parameter within a preset time period can be determined. The preset time period can be the week or day closest to the current time. The actual impact value reflects the degree of influence that the information displayed on the alternative reference floor has on users within the preset time period. A higher actual impact value indicates that the floor configured using the alternative configuration parameters for that alternative reference floor has received more user attention; conversely, a lower actual impact value indicates that the floor configured using the alternative configuration parameters for that alternative reference floor has received less user attention.

[0081] To attract more user attention to the information to be displayed, target configuration parameters corresponding to the floor to be displayed can be determined from the candidate configuration parameters based on the actual influence value of each candidate reference floor. For example, the candidate configuration parameters corresponding to the candidate reference floor with the highest actual influence value can be used as the target configuration parameters. For example, if the actual influence value is the exposure rate of the candidate reference floor, the candidate configuration parameters corresponding to the candidate reference floor with the highest exposure rate can be used as the target configuration parameters.

[0082] Furthermore, when there are multiple maximum real impact values, the target configuration parameters can be determined based on the display order of the alternative reference floors corresponding to the real impact values ​​in the display page. For example, a and b are equal and both have the maximum real impact values. Then the alternative reference floor 1 corresponding to a and the alternative reference floor 2 corresponding to b can be determined, and the display order of alternative reference floor 1 and alternative reference floor 2 in the display page can be compared. If the display order of alternative reference floor 1 is earlier than that of alternative reference floor 2, it means that alternative reference floor 1 has an advantage in the display order. When the real impact values ​​are the same, it means that configuring according to the alternative configuration parameters of alternative reference floor 2 is more likely to attract the user's attention, and the alternative configuration parameters corresponding to alternative reference floor 2 can be used as the target configuration parameters.

[0083] This embodiment takes into account the impact of configuration parameters on users and determines target configuration parameters according to the actual impact value, so that the information to be displayed can attract more attention from users and be fully displayed.

[0084] In this embodiment, based on the actual influence value, the implementation method of determining the target configuration parameter corresponding to the to-be-displayed floor from the alternative configuration parameters may include: for each alternative configuration parameter, based on a pre-set first weight and a second weight, performing weighted averaging on the exposure rate and the order conversion rate of the alternative reference floor corresponding to the alternative configuration parameter to obtain the influence average value corresponding to the alternative configuration parameter; and determining the target configuration parameter corresponding to the to-be-displayed floor from a second preset number of alternative configuration parameters with the largest influence average value.

[0085] When the actual influence value includes the exposure rate and order conversion rate of the alternative reference floor, in order to comprehensively consider various influencing factors and accurately determine the target configuration parameters, a first weight corresponding to the exposure rate and a second weight corresponding to the order conversion rate can be pre-set. The first weight is used to reflect the importance of the exposure rate, and the second weight is used to reflect the importance of the order conversion rate. Those skilled in the art may set the specific values ​​of the first and second weights based on actual application conditions, and this embodiment does not limit this.

[0086] In a specific implementation, for each candidate configuration parameter, a weighted average of the exposure rate and order conversion rate corresponding to the candidate configuration parameter can be calculated based on the first weight and the second weight to obtain the average impact value corresponding to the candidate configuration parameter. The average impact value reflects the comprehensive impact of the information displayed by the candidate configuration parameter on users.

[0087] To increase the impact of the displayed information on users, a target configuration parameter corresponding to the displayed floor can be determined from a second preset number of alternative configuration parameters with the greatest average impact. The second preset number is a positive integer. For example, if the second preset number is 1, the alternative configuration parameter with the greatest average impact can be determined as the target configuration parameter.

[0088] S240: Based on the target configuration parameters, the information to be displayed is added to the to-be-displayed floor of the target page to display the information to be displayed.

[0089] In this embodiment, target configuration parameters are determined by comprehensively considering the impact of configuration parameters on both the exposure rate and order conversion rate of displayed information. This facilitates accurate and effective determination of target configuration parameters while simultaneously increasing user attention to the displayed information. Furthermore, matching target configuration parameters can be determined for different displayed information and floors, enabling diverse display methods for different floors, thereby increasing the diversity and flexibility of the target page's display.

[0090] Figure 4 This is a flow chart of another information display method provided according to an embodiment of the present invention. Based on the above embodiment, this embodiment provides a method for determining the target configuration parameters of the floor to be displayed: determining the target cluster corresponding to the information to be displayed through the floor configuration model, and determining the alternative configuration parameters based on the target cluster, and determining the target configuration parameters corresponding to the floor to be displayed from the alternative configuration parameters. The explanations of the terms that are the same or corresponding to the above embodiments are not repeated here. Figure 4 As shown, the method includes:

[0091] S310 , obtaining a first sample data set; wherein the first sample data set includes a plurality of first training samples, and the first training sample includes a first text and a first image on a floor with the first text.

[0092] In this embodiment, the displayed image corresponding to the displayed floor can be used as the first image, and the text displayed in the displayed floor can be used as the first text. For example, the first image can be a screenshot of the displayed floor.

[0093] When obtaining the first training samples, different first training samples may be obtained from different display pages, different display positions, and different floor types, thereby improving the comprehensiveness of the first training samples.

[0094] S320. For each first training sample, determine the first text vector corresponding to the first text in the first training sample, and the first image vector corresponding to the first text, input the first text vector into the first configuration model to be trained, and input the first image vector into the second configuration model to be trained, and obtain the text probability distribution and the image probability distribution respectively.

[0095] Wherein, the first configuration model to be trained and the second configuration model to be trained include Gaussian mixture models;

[0096] In this embodiment, for each first training sample, the first image vector of the first image can be determined by a pre-trained image encoder; and the first text vector of the first text can be determined by a pre-trained text encoder corresponding to the image encoder.

[0097] Furthermore, to improve the training accuracy of the configuration model to be trained, the first text vector can be input into the clustering network to be trained, and the first vector output by the clustering network to be trained can be updated to the first text vector. Furthermore, the first image vector corresponding to the first text vector can be input into the clustering network to be trained, and the second vector output by the clustering network to be trained can be updated to the first image vector. The updated first text vector can be input into the first configuration model to be trained to obtain a text probability distribution; the updated first image vector can be input into the second configuration model to be trained to obtain an image probability distribution.

[0098] The text probability distribution is used to reflect the probability distribution of the first text belonging to different clusters; the image probability distribution is used to reflect the probability distribution of the first image belonging to different clusters.

[0099] S330. Based on the text probability distribution and the image probability distribution, the first configuration model to be trained and the second configuration model to be trained are trained, and the convergence of the first loss function value is used as the first training goal to obtain the floor configuration model through training.

[0100] The first loss function is a relative entropy loss function, for example, a JS divergence function.

[0101] In this embodiment, the JS divergence between the text probability distribution and the image probability distribution can be calculated as the first loss function value, and the first configuration model to be trained and the second configuration model to be trained are iteratively trained using the first loss function. Specifically, the parameters of the first configuration model to be trained and the second configuration model to be trained are updated through a preset optimization algorithm until the first loss function value converges, and then the iteration is stopped. Exemplarily, the preset optimization algorithm may be a gradient descent algorithm, and the condition for determining whether the first loss function value converges is: when the decrease value of the first loss function value is less than a preset threshold, it is determined that the first loss function value converges. For example, the preset threshold may be 0.001. Furthermore, when the current number of iterations reaches the maximum number of iterations, the iterative process is stopped.

[0102] In a specific implementation, the first or second trained configuration model after the iteration is stopped is used as the floor configuration model. It should be noted that the specific trained configuration model to be used as the floor configuration model can be determined based on the actual application scenario. For example, in an actual application, if text information needs to be displayed on the floor, the first trained configuration model corresponding to the first text can be used as the floor configuration model.

[0103] Furthermore, during the training of the configuration model to be trained, the cluster network to be trained can be trained simultaneously. For example, when iteratively training the first and second configuration models to be trained using a first loss function, the parameters of the cluster network to be trained are updated based on the first loss value and a preset optimization algorithm until a first training objective is met. Iterative training is then terminated to obtain a cluster network.

[0104] In order to clearly explain the process of determining the value of the first loss function, we take the JS divergence function as an example to illustrate the first loss function. The first loss function D obtained based on the text probability distribution and the image probability distribution is:

[0105]

[0106] Where p(x) is the text probability distribution of the first text vector obtained by the first configuration model to be trained, and q(x) is the image distribution probability of the first image vector obtained by the second configuration model to be trained. m(x) is the average of p(x) and q(x).

[0107] This embodiment provides a method for training a configuration model to be trained, thereby obtaining a floor configuration model, which is conducive to realizing multimodal floor clustering.

[0108] S340: Acquire the information to be displayed on the floor to be displayed on the target page.

[0109] S350: Determine target configuration parameters of the floor to be displayed based on the information to be displayed and the pre-trained floor configuration model.

[0110] S360: Based on the target configuration parameters, the information to be displayed is added to the to-be-displayed floor of the target page to display the information to be displayed.

[0111] In this embodiment, before determining the first text vector corresponding to the first training sample and the first image vector of the first image corresponding to the first text, it also includes: obtaining a second sample data set; wherein the second sample data set includes multiple second training samples, the second training sample includes a second text, and a second image corresponding to the second text in the floor; for each second training sample, determining the second text vector corresponding to the second text in the second training sample based on the text encoder to be trained, and determining the second image vector corresponding to the second image in the second training sample based on the image encoder to be trained; based on the contrastive learning method, the second image vector and the second text vector, training the image encoder to be trained and the text encoder to be trained, taking the convergence of the second loss function value as the second training target, and training to obtain a target image encoder and a target text encoder; determining the first text vector corresponding to the first text in the first training sample and the first image vector corresponding to the first text, including: inputting the first text into the trained text encoder to obtain the first text vector corresponding to the first text; inputting the first image into the trained image encoder to obtain the first image vector corresponding to the first image.

[0112] Among them, the second loss function is the contrastive learning loss function.

[0113] It should be noted that before training the floor configuration model, the text encoder and the image encoder need to be trained so that a group of images and texts with an associated relationship can obtain a text vector through the trained text encoder, and after obtaining the image vector through the image encoder, the semantic space distance between the image vector and the text vector is less than the preset distance, so that a group of associated image vectors and text vectors have a high degree of similarity.

[0114] In a specific implementation, the displayed image corresponding to the displayed floor can be used as the first image, and the text displayed on the displayed floor can be used as the first text. For example, the second image can be a screenshot of the displayed floor. The first sample dataset can be directly used as the second sample dataset to train the encoder.

[0115] In this embodiment, the text encoder to be trained includes a transformer network, and the image encoder to be trained includes a convolutional neural network. The text encoder to be trained and the image encoder to be trained can be trained synchronously. Figure 5 is a schematic diagram of a model training process provided according to an embodiment of the present invention; Figure 5 It can be seen that when training the text encoder to be trained and the image encoder to be trained, for each second training sample, the second text can be input into the text encoder to be trained to obtain a second text vector; the second image can be input into the image encoder to be trained to obtain a second image vector. The association relationship between the second text vector and the second image vector is learned through the contrastive learning method of CLIP (Contrastive Language-Image Pre-training). Specifically, through the contrastive learning method of CLIP, the parameters in the image encoder to be trained and the text encoder to be trained are adjusted, so that the distance between the image vector and the text vector with an association relationship in the common semantic space is shortened, while the distance between the image vector and the text vector without an association relationship in the semantic space is increased. The cosine similarity between the second text vector and the second image vector can be used as the distance between the second text vector and the second image vector in the semantic space.

[0116] Furthermore, each time based on the second text vector and the second image vector, a second loss function value of the image encoder to be trained and the text encoder to be trained is determined, and the convergence of the second loss function value is used as the second training goal to obtain the trained image encoder and text encoder. The purpose of the second loss function is to minimize the distance between associated image vectors and text vectors while maximizing the distance between unassociated image vectors and text vectors, so that the encoder learns better representations of images and text. The second loss function value can be determined as follows:

[0117]

[0118] Among them, L3 is the second loss function value, L1 is the contrast loss value from the second image vector of the second training sample currently being processed to the second text vector, and L2 is the contrast loss value from the second text vector of the second training sample currently being processed to the second image vector.

[0119]

[0120] Wherein, N is the number of second training samples, i represents the second training sample currently being processed, and j represents the other second training samples except the second training sample currently being processed; cos(I i ,T i) represents the second image vector I currently being processed i and the second text vector T i The cosine similarity of τ is the temperature parameter used to scale the similarity value. i ,T j ) represents the cosine similarity between the second image vector of the second training sample currently being processed and the second text vectors of other second training samples.

[0121]

[0122] Among them, cos(I j ,T i ) represents the cosine similarity between the second text vector of the second training sample currently being processed and the second image vectors of other second training samples.

[0123] Furthermore, after the image encoder and text encoder are trained, Figure 5 As shown, when training the first and second configuration models to be trained, the first text can be input into the trained text encoder to obtain a first text vector corresponding to the first text; the first image can be input into the trained image encoder to obtain a first image vector corresponding to the first image. Text feature representation is performed using the first text vector, and image feature representation is performed using the first image vector. The obtained first text vector can be input into the first configuration model to be trained to obtain a text clustering result, i.e., a text probability distribution; the first image vector can be input into the second configuration model to be trained to obtain an image clustering result, i.e., an image probability distribution. The first and second configuration models to be trained are trained using the first loss function, the text clustering results, and the image clustering results, with the convergence of the first loss function being the first training objective, thereby obtaining a floor configuration model.

[0124] This embodiment trains the image encoder and the text encoder through a comparative learning method, thereby shortening the distance between text vectors and image vectors with an associated relationship and increasing the distance between text vectors and image vectors without an associated relationship, which is conducive to better representation of text and images, and thus improves the training accuracy of the training configuration model.

[0125] Figure 6 This is a schematic diagram of the structure of an information display device provided according to an embodiment of the present invention, which is used to execute the information display method provided in any of the above embodiments. This device and the information display method of each of the above embodiments belong to the same inventive concept. For details not fully described in the embodiments of the information display device, please refer to the embodiments of the above information display method. Figure 6 As shown, the device includes:

[0126] The information acquisition module 10 is used to acquire the information to be displayed on the display floor to be displayed on the target page;

[0127] The parameter determination module 11 is used to determine the target configuration parameters of the floor to be displayed based on the information to be displayed and the pre-trained floor configuration model; wherein the target configuration parameters are used to configure the display style of the floor to be displayed;

[0128] The information adding module 12 is used to add the information to be displayed to the to-be-displayed floor of the target page based on the target configuration parameters, so as to display the information to be displayed.

[0129] Based on any optional technical solution in the embodiment of the present invention, optionally, the floor configuration model includes a Gaussian mixture model parameter determination module 11 including:

[0130] A target cluster determination submodule is used to determine the target cluster corresponding to the information to be displayed based on the information to be displayed and the pre-trained floor configuration model;

[0131] The candidate configuration parameter determination submodule is used to select the sample configuration parameters corresponding to the target cluster from the pre-stored sample configuration parameters as candidate configuration parameters; wherein the sample configuration parameters are the actual configuration parameters of the displayed floors;

[0132] The target configuration parameter determination submodule is used to determine the target configuration parameter corresponding to the floor to be displayed from the candidate configuration parameters.

[0133] Based on any optional technical solution in the embodiments of the present invention, optionally, the target configuration parameter determination submodule includes:

[0134] a real impact value determining unit, configured to determine, when the number of the candidate configuration parameters is greater than a first preset number, real impact values ​​generated by the candidate reference floors corresponding to the candidate configuration parameters within a preset time period;

[0135] The target configuration parameter determination unit is configured to determine the target configuration parameter corresponding to the to-be-displayed floor from among the candidate configuration parameters based on the real impact degree value.

[0136] Based on any optional technical solution in the embodiment of the present invention, optionally, the real influence value includes at least one of the exposure rate and the order conversion rate of the candidate reference floor;

[0137] The target configuration parameter determination unit includes:

[0138] The influence average value determination subunit is configured to perform a weighted average processing on the exposure rate and order conversion rate of the alternative reference floor corresponding to each alternative configuration parameter based on a pre-set first weight and a pre-set second weight, to obtain the influence average value corresponding to the alternative configuration parameter; wherein the first weight is used to reflect the importance of the exposure rate, and the second weight is used to reflect the importance of the order conversion rate;

[0139] The target configuration parameter determination subunit is configured to determine the target configuration parameter corresponding to the to-be-displayed floor from a second preset number of candidate configuration parameters that have the greatest impact on the average value.

[0140] Based on any optional technical solution in the embodiment of the present invention, optionally, the information to be displayed includes at least one of text information and image information;

[0141] The parameter determination module 11 includes:

[0142] An encoder determination submodule, configured to determine a target encoder corresponding to the information to be displayed from at least one pre-generated encoder; wherein the target encoder includes at least one of an image encoder and a text encoder;

[0143] An information input submodule, configured to input the information to be displayed into the target encoder to obtain a display feature vector corresponding to the information to be displayed;

[0144] The vector input submodule is used to input the display feature vector into the pre-trained floor configuration model to obtain the target configuration parameters corresponding to the information to be displayed.

[0145] Based on any optional technical solution in the embodiments of the present invention, optionally, the vector input submodule includes:

[0146] a first vector input unit, configured to input the display feature vector into a pre-trained clustering network and update the display feature vector based on the obtained output vector;

[0147] The second vector input unit is used to input the updated display feature vector into the pre-trained floor configuration model to obtain target configuration parameters corresponding to the information to be displayed.

[0148] Based on any optional technical solution in the embodiment of the present invention, optionally, the target configuration parameter includes a floor style parameter and a display format parameter of the information to be displayed; the floor style parameter includes at least one of a floor margin, a background color, a corner shape, and a floor height;

[0149] The information adding module 12 includes:

[0150] The image rendering submodule is used to render the information to be displayed into images to be displayed based on the floor style parameters and display format parameters;

[0151] The picture adding submodule is used to add the picture to be displayed to the to-be-displayed floor of the target page.

[0152] Based on any optional technical solution in the embodiment of the present invention, optionally, the information acquisition module 10 includes:

[0153] The information acquisition submodule is used to respond to the configuration trigger operation of the new floor in the target page, take the new floor as the floor to be displayed, and obtain the information to be displayed of the floor to be displayed.

[0154] Based on any optional technical solution in the embodiments of the present invention, optionally, the method further includes:

[0155] A first data set acquisition module is configured to acquire a first sample data set before determining target configuration parameters of a floor to be displayed based on the information to be displayed and a pre-trained floor configuration model; wherein the first sample data set includes a plurality of first training samples, each of which includes a first text and a first image on a floor corresponding to the first text;

[0156] A first vector determination module is configured to determine, for each first training sample, a first text vector corresponding to a first text in the first training sample and a first image vector corresponding to a first text, input the first text vector into a first configuration model to be trained, and input the first image vector into a second configuration model to be trained, to obtain a text probability distribution and an image probability distribution, respectively; wherein the first configuration model to be trained and the second configuration model to be trained include Gaussian mixture models;

[0157] The first model training module is used to train the first configuration model to be trained and the second configuration model to be trained based on the text probability distribution and the image probability distribution, and take the convergence of the first loss function value as the first training goal to train the floor configuration model; wherein the first loss function is a relative entropy loss function.

[0158] Based on any optional technical solution in the embodiments of the present invention, optionally, the method further includes:

[0159] a second data set acquisition module, configured to acquire a second sample data set before determining a first text vector corresponding to a first text in a first training sample and a first image vector corresponding to a first text; wherein the second sample data set includes a plurality of second training samples, each of the second training samples including a second text and a second image corresponding to the second text in a floor;

[0160] a second vector determination module configured to determine, for each second training sample, a second text vector corresponding to a second text in the second training sample based on the to-be-trained text encoder, and to determine a second image vector corresponding to a second image in the second training sample based on the to-be-trained image encoder;

[0161] A second model training module is configured to train the image encoder to be trained and the text encoder to be trained based on a contrastive learning method, the second image vector and the second text vector, and to train the image encoder and the text encoder using convergence of the second loss function as a second training objective; wherein the second loss function is a contrastive learning loss function;

[0162] The first vector determination module includes:

[0163] A first vector determination submodule, configured to input a first text into a trained text encoder to obtain a first text vector corresponding to the first text;

[0164] The second vector determination submodule is used to input the first image into the trained image encoder to obtain a first image vector corresponding to the first image.

[0165] The technical solution of the embodiment of the present invention determines the target configuration parameters of the floor to be displayed by obtaining the information to be displayed on the floor to be displayed that needs to be displayed on the target page and a pre-trained floor configuration model, thereby automatically determining the target configuration parameters for configuring the display style of the floor to be displayed through the floor configuration model without the intervention of operating personnel; and based on the determined target configuration parameters, the information to be displayed is added to the floor to be displayed on the target page to complete the display of the information to be displayed. Since no human intervention is required in the process, the configuration efficiency and accuracy of the floor to be displayed are improved, which is conducive to reducing the floor configuration cost.

[0166] It is worth noting that in the embodiment of the above-mentioned information display device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0167] Figure 7: is a structural diagram of an electronic device that implements the information display method of an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0168] like Figure 7 As shown, the electronic device 20 includes at least one processor 21, and a memory connected to the at least one processor 21, such as a read-only memory (ROM) 22, a random access memory (RAM) 23, etc., wherein the memory stores a computer program that can be executed by the at least one processor, and the processor 21 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 22 or the computer program loaded from the storage unit 28 to the random access memory (RAM) 23. Various programs and data required for the operation of the electronic device 20 can also be stored in the RAM 23. The processor 21, ROM 22 and RAM 23 are connected to each other via a bus 24. An input / output (I / O) interface 25 is also connected to the bus 24.

[0169] Multiple components in the electronic device 20 are connected to the I / O interface 25, including an input unit 26, such as a keyboard, a mouse, etc.; an output unit 27, such as various types of displays, speakers, etc.; a storage unit 28, such as a magnetic disk, an optical disk, etc.; and a communication unit 29, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 29 allows the electronic device 20 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0170] The processor 21 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 21 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 21 executes the various methods and processes described above, such as the information presentation method.

[0171] In some embodiments, the information display method can be implemented as a computer program that is tangibly contained in a computer-readable storage medium, such as the storage unit 28. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 20 via the ROM 22 and / or the communication unit 29. When the computer program is loaded into the RAM 23 and executed by the processor 21, one or more steps of the information display method described above can be performed. Alternatively, in other embodiments, the processor 21 can be configured to perform the information display method in any other appropriate manner (e.g., by means of firmware).

[0172] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0173] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0174] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0175] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0176] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0177] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0178] This embodiment also provides a computer program product, including a computer program, which, when executed by a processor, implements the information display method provided in any embodiment of the present application.

[0179] The computer program product may be implemented by writing computer program code for performing the operations of the present invention in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0180] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0181] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. An information display method, characterized in that: include: Obtain the information to be displayed on the display layer to be displayed on the target page; Determining target configuration parameters of the floor to be displayed based on the information to be displayed and a pre-trained floor configuration model; wherein the target configuration parameters are used to configure the display style of the floor to be displayed; Based on the target configuration parameters, the information to be displayed is added to the to-be-displayed floor of the target page to display the information to be displayed.

2. The method according to claim 1, characterized in that The floor configuration model includes a Gaussian mixture model, and determining target configuration parameters of the floor to be displayed based on the information to be displayed and the pre-trained floor configuration model includes: Based on the information to be displayed and the pre-trained floor configuration model, determining a target cluster corresponding to the information to be displayed; Among the pre-stored sample configuration parameters, the sample configuration parameters corresponding to the target cluster are used as candidate configuration parameters; wherein the sample configuration parameters are the actual configuration parameters of the displayed floors; Among the candidate configuration parameters, target configuration parameters corresponding to the floor to be displayed are determined.

3. The method according to claim 2, characterized in that Determining the target configuration parameters corresponding to the floor to be displayed from the candidate configuration parameters includes: In a case where the number of the candidate configuration parameters is greater than a first preset number, determining actual impact values ​​of the candidate reference floors corresponding to the candidate configuration parameters within a preset time period; Based on the actual impact value, a target configuration parameter corresponding to the to-be-displayed floor is determined from the candidate configuration parameters.

4. The method according to claim 3, characterized in that The real influence value includes at least one of the exposure rate and order conversion rate of the candidate reference floor; The step of determining the target configuration parameter corresponding to the to-be-displayed floor from the candidate configuration parameters based on the real impact value includes: For each of the alternative configuration parameters, based on a pre-set first weight and a pre-set second weight, a weighted average processing is performed on the exposure rate and the order conversion rate of the alternative reference floor corresponding to the alternative configuration parameter to obtain an average impact value corresponding to the alternative configuration parameter; wherein the first weight is used to reflect the importance of the exposure rate, and the second weight is used to reflect the importance of the order conversion rate; The target configuration parameter corresponding to the to-be-displayed floor is determined from the second preset number of candidate configuration parameters having the largest influence on the average value.

5. The method according to claim 1, characterized in that The information to be displayed includes at least one of text information and image information; The determining, based on the information to be displayed and a pre-trained floor configuration model, target configuration parameters of the floor to be displayed includes: Determining a target encoder corresponding to the information to be displayed from at least one pre-generated encoder; wherein the target encoder includes at least one of an image encoder and a text encoder; Inputting the information to be displayed into the target encoder to obtain a display feature vector corresponding to the information to be displayed; The display feature vector is input into the pre-trained floor configuration model to obtain the target configuration parameters corresponding to the information to be displayed.

6. The method according to claim 5, characterized in that The step of inputting the display feature vector into the pre-trained floor configuration model to obtain the target configuration parameters corresponding to the information to be displayed includes: Inputting the display feature vector into a pre-trained clustering network, and updating the display feature vector based on the obtained output vector; The updated display feature vector is input into the pre-trained floor configuration model to obtain the target configuration parameters corresponding to the information to be displayed.

7. The method according to claim 1, characterized in that The target configuration parameters include floor style parameters and display format parameters of the information to be displayed; the floor style parameters include at least one of floor margin, background color, corner shape and floor height; The adding the information to be displayed to the floor to be displayed of the target page based on the target configuration parameters includes: Rendering the information to be displayed into a picture to be displayed based on the floor style parameter and the display format parameter; Add the picture to be displayed to the floor to be displayed of the target page.

8. The method according to claim 1, characterized in that The step of obtaining the information to be displayed on the floor to be displayed on the target page includes: In response to a configuration triggering operation on a newly created floor in the target page, the newly created floor is used as the floor to be displayed, and the to-be-displayed information of the floor to be displayed is obtained.

9. The method according to claim 1, characterized in that Before determining the target configuration parameters of the floor to be displayed based on the information to be displayed and the pre-trained floor configuration model, the method further includes: Acquire a first sample data set; wherein the first sample data set includes a plurality of first training samples, and the first training samples include a first text and a first image on a floor with the first text; For each of the first training samples, determining a first text vector corresponding to a first text in the first training sample and a first image vector corresponding to a first text, inputting the first text vector into a first configuration model to be trained, and inputting the first image vector into a second configuration model to be trained, to obtain a text probability distribution and an image probability distribution, respectively; wherein the first configuration model to be trained and the second configuration model to be trained include Gaussian mixture models; Based on the text probability distribution and the image probability distribution, the first configuration model to be trained and the second configuration model to be trained are trained, and the convergence of the first loss function value is used as the first training goal to obtain the floor configuration model through training; wherein the first loss function is a relative entropy loss function.

10. The method according to claim 9, characterized in that Before determining the first text vector corresponding to the first text in the first training sample and the first image vector of the first image corresponding to the first text, the method further includes: Acquire a second sample data set; wherein the second sample data set includes a plurality of second training samples, and the second training samples include a second text and a second image on a floor with the second text; For each second training sample, determining a second text vector corresponding to a second text in the second training sample based on a text encoder to be trained, and determining a second image vector corresponding to a second image in the second training sample based on an image encoder to be trained; Based on the contrastive learning method, the second image vector, and the second text vector, the image encoder to be trained and the text encoder to be trained are trained, with convergence of the second loss function value as a second training objective, to obtain the image encoder and the text encoder through training; wherein the second loss function is a contrastive learning loss function; The determining of a first text vector corresponding to a first text in the first training sample and a first image vector corresponding to a first image of the first text includes: Inputting the first text into the trained text encoder to obtain a first text vector corresponding to the first text; The first image is input into a trained image encoder to obtain a first image vector corresponding to the first image.

11. An information display device, characterized in that: include: An information acquisition module is used to acquire information to be displayed on a floor to be displayed on a target page; a parameter determination module, configured to determine target configuration parameters of the floor to be displayed based on the information to be displayed and a pre-trained floor configuration model; wherein the target configuration parameters are used to configure the display style of the floor to be displayed; An information adding module is used to add the information to be displayed to the to-be-displayed floor of the target page based on the target configuration parameters, so as to display the information to be displayed.

12. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor. The computer program is executed by the at least one processor to enable the at least one processor to perform the information presentation method according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the information display method according to any one of claims 1 to 10 when executed.

14. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the information presentation method according to any one of claims 1 to 10.

Images