Information display method and device, storage medium and program product

Abstract

The embodiment of the invention provides an information display method and device, a storage medium and a program product. In the embodiment of the invention, the candidate information is not directly displayed in the display form corresponding to the information system to which the candidate information belongs, but the unique target display form of the candidate information is determined according to the attribute information of the candidate information, and the target information is displayed in the unique target display form after the target information is selected from the multiple pieces of candidate information. In the process of determining the target display form, it can be ensured that candidate information belonging to multiple information systems at the same time can be displayed in the unique target display form instead of being repeatedly displayed in multiple different display forms, and simple duplicate removal processing is not needed, so that it can be ensured that the display form is not directly influenced by the information system to which the display form belongs, and the display efficiency is improved. For example, the method is not affected by the bid information of the advertisement system, and meets the natural bid independence, thereby meeting the excitation compatibility between different information systems, and achieving the balance between the platform value and the user experience.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to an information display method, device, storage medium and program product. Background Art

[0002] Internet platforms such as search platforms, social platforms, and e-commerce platforms usually use a combination of advertising systems and recommendation systems to recommend information to users. The advertising system is responsible for selecting information paid for by advertisers from the advertising information library, and the recommendation system is responsible for selecting information recommended to users from the regular information library based on user preferences. Then, a fusion mechanism is used to allocate the information recommended by the two systems to limited display positions, resulting in a final list of information displayed to users.

[0003] In actual applications, the information list displayed to users may have the problem of duplicate display, which will affect the diversity of the information display results; if the information list is simply deduplicated, it will be difficult to balance the system's platform value and user experience. Summary of the invention

[0004] Multiple aspects of the present application provide an information display method, device, storage medium and program product to solve the problem of repeated display information and achieve a balance between platform value and user experience.

[0005] An embodiment of the present application provides an information display method, including: in response to an information display request, obtaining multiple candidate information from multiple information systems of a target platform, the candidate information including first attribute information unrelated to the multiple information systems, and second attribute information corresponding to the multiple information systems, and different information systems correspond to different display forms; determining target display forms of the multiple candidate information according to the first attribute information and the multiple second attribute information of the multiple candidate information, the target display forms of the candidate information being the same as or different from the display forms corresponding to the information systems to which the candidate information belongs; selecting target information from the multiple candidate information; and returning the target information to a requesting end of the information display request, so that the requesting end displays the target information in the target display form of the target information.

[0006] The embodiment of the present application also provides an information display method, including: in response to an information display request, obtaining multiple candidate information from multiple information systems of a target platform, the candidate information including first attribute information unrelated to the multiple information systems, and second attribute information corresponding to the multiple information systems, different information systems corresponding to different display forms; determining target display forms of the multiple candidate information based on the first attribute information and the multiple second attribute information of the multiple candidate information, the target display forms of the candidate information being the same as or different from the display forms corresponding to the information systems to which the candidate information belongs; selecting target information from the multiple candidate information and displaying the target information in the target display form of the target information.

[0007] An embodiment of the present application also provides a product information display method, including: displaying a first page, the first page including search entry information; in response to a search operation initiated through the search entry information, obtaining multiple candidate product information adapted to the search term from an advertising system and a recommendation system; the candidate product information includes product attribute information, and marketing attribute information corresponding to the advertising system and the recommendation system respectively; determining a target display form of the multiple candidate product information based on the product attribute information and the marketing attribute information of the multiple candidate product information, the target display form being an advertising display form or a natural display form; selecting target product information from the multiple candidate product information, and displaying the target product information on a second page in the target display form of the target product information.

[0008] The embodiment of the present application also provides a page display method, including: responding to a start request for a target application, obtaining multiple candidate product information adapted to user attribute information from an advertising system and a recommendation system; the candidate product information includes product attribute information, and marketing attribute information corresponding to the advertising system and the recommendation system respectively; determining a target display form of the multiple candidate product information based on the product attribute information and the marketing attribute information of the multiple candidate product information, the target display form being an advertising display form or a natural display form; selecting target product information from the multiple candidate product information, and displaying the target product information on the homepage of the target application in the target display form of the target product information.

[0009] An embodiment of the present application also provides an electronic device, including: a memory and a processor; the memory is used to store a computer program; the processor is coupled to the memory and is used to execute the computer program to implement each step in the information display method and the product information display method provided in the embodiment of the present application.

[0010] The embodiment of the present application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor implements each step of the information display method and the product information display method provided in the embodiment of the present application.

[0011] The embodiment of the present application also provides a computer program product, including a computer program / instruction. When the computer program / instruction is executed by a processor, the processor implements each step of the information display method and the product information display method provided in the embodiment of the present application.

[0012] In an embodiment of the present application, the target platform provides multiple information systems, and the same candidate information may come from (or be referred to as "belonging to") one or more information systems. When displaying information, it is not directly displayed in the display form corresponding to the information system to which the candidate information belongs, but the unique target display form of the candidate information is determined based on the first attribute information of the candidate information that is independent of the multiple information systems and the multiple second attribute information related to the multiple information systems, and the target information is selected from the multiple candidate information and displayed in the unique target display form. In the process of determining the target display form, it can be ensured that the candidate information belonging to multiple information systems at the same time can be displayed in the unique target display form, and will not be repeatedly displayed in multiple different display forms. At the same time, the process of determining the target display form is not a simple deduplication process. In this process, it can be ensured that the display form of the candidate information is not directly affected by the information system to which it belongs, for example, it is not affected by the bidding information of the advertising information itself, so as to meet the natural bidding independence, and then meet the incentive compatibility between different information systems and the target platform, so as to achieve a balance between platform value and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0014] Figure 1a A flowchart of an information display method provided for an exemplary embodiment of the present application;

[0015] Figure 1b A flowchart of another information display method provided for an exemplary embodiment of the present application;

[0016] Figure 1c A schematic diagram of a scenario of a method for displaying commodity information provided by an exemplary embodiment of the present application;

[0017] Figure 1d A schematic diagram of a scenario of a page display method provided for an exemplary embodiment of the present application;

[0018] Figure 2a An architectural diagram of an information display method provided for an exemplary embodiment of the present application;

[0019] Figure 2b A structural diagram of a determined information display form provided for an exemplary embodiment of the present application;

[0020] Figure 3 A schematic diagram of the structure of an information display device provided for an exemplary embodiment of the present application;

[0021] Figure 4 A schematic structural diagram of an electronic device provided for an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0023] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0024] The various models involved in this application (including but not limited to language models or large models) are in compliance with relevant laws and standards.

[0025] In current Internet platforms (e.g., e-commerce platforms), the information displayed to users can be divided into two categories: one is the information that advertisers (e.g., information providers) want to promote, called advertising information; the other is the information that Internet platforms intelligently recommend to users based on user favorites, historical browsing information, or search terms, called natural information. Among them, advertisers can provide bidding information to the platform to increase the probability of displaying advertising information, while natural information in the recommendation system does not need to provide bidding information.

[0026] In order to optimize the information display effect and enhance the value of the Internet platform, the Internet platform usually independently screens out candidate advertising results and candidate natural results through the advertising system and recommendation system, merges the candidate advertising results and candidate natural results (also known as mixed sorting), and distributes them to limited display positions for display according to the mixed sorting.

[0027] There are two fusion methods:

[0028] Method 1: Assuming that there is no duplication between the candidate advertising information and the candidate natural information, the ranking scores are calculated for the candidate advertising information and the candidate natural information respectively, and the display positions are allocated according to the ranking scores from high to low. The natural ranking score of the candidate natural information represents the user experience of the platform users. The higher the ranking score, the better the user experience. The advertising ranking score of the candidate advertising information can comprehensively reflect the user experience and bidding information of the platform users. For example, this fusion method can be achieved through a unified generalized second price auction (uGSP).

[0029] Method 2: When there is duplicate information in the candidate natural information and the candidate advertising information, in order to avoid the duplicate information being displayed repeatedly in different display forms, a simple deduplication process can be performed on the candidate advertising information and the candidate natural results. For example, the candidate advertising information in the duplicate information is deleted, or the candidate natural information in the duplicate information is deleted.

[0030] Regardless of which of the above methods is used, the above integration methods do not take into account the advertiser's utility and incentive compatibility, which will make it difficult to balance the platform value and user experience.

[0031] Among them, advertiser utility refers to the fact that each advertiser hopes to maximize his or her own value through real bidding. For example, advertisers hope to maximize the total value brought by the display of advertising results and natural results minus the cost of advertising. The incentive fusion property means that advertisers can maximize their own profits when they make real bids according to their own estimated values.

[0032] For example, each user click will bring a certain value to the advertiser, which can be converted into a certain amount v, such as v in yuan. When the bid information of other advertisers is fixed, the bid information submitted by the current advertiser is b, and the click-through rate of the advertising information and natural information corresponding to the current advertiser can be represented by x(b) and y(b). If the fusion mechanism displays the information of the advertiser as advertising information, then x(b) is the click-through rate of the information, and y(b) is 0; if the fusion mechanism displays the information of the advertiser as natural information, then y(b) is the click-through rate of the information, and x(b) is 0; if the fusion mechanism does not display the information of the advertiser, then x(b) and y(b) are both 0. In addition, if the fusion mechanism displays the information of the advertiser as advertising information, the pricing (cost information) can be set for the advertising information, recorded as p(b). If the advertising information is clicked by the user, the advertiser can pay the platform a fee of p(b). The advertiser's expected utility is defined as (x(b)+y(b))*vx(b)*p(b), where "*" represents multiplication, that is, the total value of the clicks on the following two display forms minus the cost paid is expected to be maximized. The incentive compatibility property of the fusion mechanism requires that when the advertiser's actual bid b=v, the advertiser's expected utility can be maximized, that is, (x(b)+y(b))*vx(b)*p(b) reaches the maximum value when b=v. When the fusion mechanism satisfies the incentive compatibility property, the advertiser has no motivation to falsely report the bid b (e.g., lower the bid b), so it can be assumed that the advertiser always uses the real bid. Therefore, it can be considered that the bid distribution is irrelevant to the specific design of the fusion mechanism.

[0033] In the embodiments of the present application, a solution is also provided, which can be applied to e-commerce scenarios including advertising systems and recommendation systems to solve the balance problem between platform value and user experience, but is not limited to this, and can also be applied to various Internet platforms including multiple information systems, such as search platforms, social platforms, and online education platforms. For the convenience of distinction and description, in the embodiments of the present application, the various Internet platforms listed here are collectively referred to as target platforms.

[0034] In the solution provided in the embodiment of the present application, the target platform provides multiple information systems. The same candidate information may come from (or be referred to as "belonging to") one or more information systems. When displaying information, it is not directly displayed in the display form corresponding to the information system to which the candidate information belongs. Instead, a unique target display form of the candidate information is determined based on the first attribute information of the candidate information that is independent of the multiple information systems and multiple second attribute information related to the multiple information systems, and the target information is selected from the multiple candidate information and displayed in the unique target display form. In the process of determining the target display form, it can be ensured that the candidate information belonging to multiple information systems at the same time can be displayed in the unique target display form, and will not be repeatedly displayed in multiple different display forms. At the same time, the process of determining the target display form is not a simple deduplication process. In this process, it can be ensured that the display form of the candidate information is not directly affected by the information system to which it belongs, for example, it is not affected by the bidding information of the advertising information itself, so as to meet the natural bidding independence, and then meet the incentive compatibility between different information systems and the target platform, so as to achieve a balance between platform value and user experience.

[0035] Among them, natural bid independence means that the display form of candidate information is not directly affected by the information system to which it belongs. For example, when the target display form of multiple candidate information is determined, changing the bid information of the advertising information does not affect the target display form of the candidate information. On the basis that the information display method satisfies natural bid independence, setting appropriate bid information for the advertising information can meet the incentive compatibility property and take into account the multi-party benefits of the Internet platform, advertisers and platform users.

[0036] The following is a detailed description of the solution provided by the embodiment of the present application in conjunction with the accompanying drawings. It is noted that the solution provided by the embodiment of the present application can be applied to server devices or terminal devices, without limitation. The server devices may include but are not limited to: conventional servers, cloud servers or server arrays, etc., and the terminal devices may include but are not limited to: desktop computers, laptops, smart phones or IOT (Internet of Things) devices, etc. Figure 1a The embodiment shown is applied to the server side. Figure 1b The illustrated embodiment is applied to a terminal device.

[0037] Figure 1a The following is a flow chart of an information display method provided by an exemplary embodiment of the present application. Figure 1a As shown, the system includes:

[0038] 101a. In response to an information display request, multiple candidate information is obtained from multiple information systems of the target platform, where the candidate information includes first attribute information irrelevant to the multiple information systems and multiple second attribute information corresponding to the multiple information systems, and different information systems correspond to different display forms;

[0039] 102a. Determine target display forms of the plurality of candidate information according to the first attribute information and the second attribute information of the plurality of candidate information, wherein the target display forms of the candidate information are the same as or different from the display forms corresponding to the information system to which the candidate information belongs;

[0040] 103a. Select target information from multiple candidate information, and return the target information to the request end of the information display request, so that the request end can display the target information in the target display form of the target information.

[0041] In this embodiment, the terminal device is mainly used to interact with the users corresponding to the Internet platform (C-end users) and display the target information returned by the server to the users.

[0042] Among them, various applications can be run on the terminal device. For example, the application may include but not limited to: shopping applications, social applications, online learning applications, and search engine applications. Among them, different applications may correspond to different Internet platforms. For example, shopping applications correspond to e-commerce platforms, social applications correspond to social platforms, online learning applications correspond to online education platforms, and search engine applications correspond to search platforms. Among them, for the convenience of description and distinction, the subsequent description is based on the target platform corresponding to the target application as an example.

[0043] In this embodiment, the target platform corresponds to multiple information systems, and the number of information systems can be 2, 3 or more, and there is no limitation on this. Depending on the target platform, the types of information included in the information system are also different. For example, for a shopping platform, the information system may include product information. For a social platform, each information system may include social information such as conversation information, status update information, link sharing information, or comments and interactive information; for a search platform, each information system may include: news information, question and answer information, map and location information, and other search information.

[0044] In this embodiment, different information systems correspond to different display forms. Among them, the display form refers to the specific form of presenting information, and the display form can be diverse. For example, the display form may include, but is not limited to: lists, cards, detail pages, smart recommendation columns, pop-up prompts, interactive components (such as carousels), etc. For another example, different display forms can also be reflected by different identification information. For example, the display form corresponding to the advertising results can be reflected by displaying "advertisement" in the display area of ​​the information, and the display form corresponding to the natural results can be reflected by displaying "natural" in the display area of ​​the information. Of course, "natural" may not be displayed for natural results.

[0045] In this embodiment, the server device can respond to the information display request and obtain multiple candidate information from multiple information systems corresponding to the target platform. For example, a target application is running on the terminal device, and the target application provides a search page. The terminal device responds to the user's input operation on the information display page to obtain the search term; wherein the input operation can be a voice input operation or a text input operation, etc. In response to the information display request initiated by the user, the terminal device sends the search term to the server to initiate an information display request to the server; the server responds to the information display request and obtains multiple candidate information from multiple information systems corresponding to the target platform. For another example, the terminal device can initiate an information display request to the server in response to the start operation for the target application. Among them, the information display request includes: user browsing history, purchase history, favorites and other user behavior data. The server can obtain multiple candidate information from multiple information systems corresponding to the target platform based on the user behavior data; or the information display request includes user identification information, and the server obtains user behavior data based on the user identification information, and obtains multiple candidate information from multiple information systems corresponding to the target platform based on the user behavior data.

[0046] The number of the multiple candidate information may be 20, 30, 50, etc., and there is no limitation on this.

[0047] In the process of obtaining multiple candidate information from multiple information systems of the target platform, a certain candidate information may be matched from multiple information systems at the same time, that is, multiple information systems can obtain the candidate information, and the display form of the candidate information is different for different information systems. In the process of displaying the candidate information, it is impossible to determine which information system corresponds to the display form in which the candidate information is displayed.

[0048] Based on this, in the embodiment of the present application, the information display method includes a display form decision part and an information display decision part, such as Figure 2aAs shown. The unique display form of the candidate information is determined by the display form decision part, and the target information to be finally displayed among the candidate information is determined by the information display decision part. It should be noted that in the information display decision part, the target information can be directly selected from multiple candidate information (for example, the target information is randomly selected), or the display order of multiple candidate information can be determined and then the target information is selected according to the display order, and there is no limitation on this.

[0049] The following is an introduction to the above two parts respectively.

[0050] (1) Display form decision part: that is, determining the target display forms of the plurality of candidate information according to the first attribute information and the second attribute information of the plurality of candidate information, wherein the target display forms of the plurality of candidate information are the same as or different from the display forms corresponding to the information system to which the candidate information belongs.

[0051] Among them, the target display form is one of the display forms corresponding to multiple information systems. If the candidate information comes from information system R1 and also from information system R2, if the target display form of the candidate information is the display form corresponding to information system R1, then for information system R1, the target display form of the candidate information is the same as the display form of information system R1, and the target display form of the candidate information is different from the display form of information system R2.

[0052] For example, taking the case where multiple information systems are implemented as two information systems, for information display requests, the candidate information obtained from information system A1 includes {B1, B2, B3}, and the candidate information obtained from information system A2 includes {B2, B3, B4}. Among them, candidate information B2 and candidate information B3 belong to both information system A1 and information system A2. The "multiple candidate information" may include {B1, B2, B3, B4}, and the target display form of candidate information B1 to candidate information B4 may be determined based on the first attribute information and the second attribute information of candidate information B1 to candidate information B4. The target display form of candidate information B1 may be the same as the display form of information system A1; the target display form of candidate information B2 may be the same as the display form of information system A2, but different from the display form of information system A1; the target display form of candidate information B3 may be the same as the display form of information system A1, but different from the display form of information system A2; the target display form of candidate information B4 may be the same as the display form of information system A2.

[0053] For example, the display form corresponding to information system A1 is the advertising display form, and the display form corresponding to information system A2 is the natural display form. For another example, the display form corresponding to information system A1 is the smart recommendation bar, pop-up window prompts, interactive components (such as carousels), etc., and the display form corresponding to information system A2 is the list display.

[0054] It should be noted that the target display form of each candidate information is unique. For example, the target display form of each candidate information can be an advertising form or a natural form, but it will not be displayed twice in the same request, that is, it will not be displayed twice in both advertising form and natural form at the same time.

[0055] Each candidate information includes first attribute information and multiple second attribute information. The first attribute information is attribute information that is irrelevant to the multiple information systems, and the first attribute information is data describing the characteristics of the information itself. The second attribute information is attribute information corresponding to the multiple information systems, that is, each information system corresponds to the second attribute information.

[0056] Among them, the first attribute information of the candidate information may include but is not limited to: the title or name of the information, the specific content or description of the information, the creator of the information, the date and time of information release, the source of the information, the category or label of the information, and the keywords in the information. Depending on the target platform, the candidate information is different, and the first attribute information is also different. For example, the target platform is implemented as an e-commerce platform, the candidate information is product information, and the first attribute information includes but is not limited to: the name, price, category, inventory, sales, rating, comment, specification and material of the product information. For another example, the target platform is implemented as a social platform, the candidate information is social information, and the first attribute information includes but is not limited to: user information (nickname, introduction, avatar, label, etc.), content information (text, type, title and topic, etc.), interactive information (number of likes, number of comments, number of reposts, number of shares and number of collections, etc.), relationship information (friends, followers, fans, etc.). The target platform is implemented as a search platform, the candidate information is search information, and the first attribute information is but is not limited to: search information keywords, categories or labels, relevance, release location information and time information, content type, comments and ratings, and data update time.

[0057] In addition, the first attribute information also includes historical bidding information, which indicates the bidding information provided by the provider of the candidate information for displaying the candidate information in the past period of time, and the bidding information can be the bidding information that the information provider can provide for each information display request. For example, the historical bidding information of a candidate information can be one or more, for example, the bid in the first month is 5 yuan, the bid in the second month is 4 yuan, and the bid in the third month is 8 yuan, so the historical bidding information of the candidate information can include 5 yuan, 4 yuan, and 8 yuan.

[0058] Among them, in the information system, the second attribute information of the candidate information may include but is not limited to: the click-through rate and user experience information corresponding to the candidate information in the information system. Among them, in a possible implementation method, the click-through rate can be realized as the post-exposure click-through rate (Post-Impression Click-Through Rate, Post-Impression CTR), which refers to the probability that the user clicks on the candidate information within a period of time after the candidate information is displayed (exposed). This indicator is usually used to measure the delayed effect of candidate information, that is, the user may not click immediately after seeing the candidate information for the first time, but return and click at a certain point in time thereafter. Among them, the post-exposure click-through rate is used to evaluate the long-term effect and influence of the candidate information. In another implementation method, the click-through rate can be the click-through rate of the candidate information in a historical time period, which is not limited.

[0059] Among them, User Experience (UE) refers to the data generated during the interaction between users and the target platform, which reflects the user's feelings, satisfaction and usage of the target platform. User experience information is crucial for product design, optimization and improvement. For example, user experience information can be reflected by at least one of the following attribute items: the frequency of use of the target platform by users, the duration of use, the number of active users of the target platform, the user retention rate, the user satisfaction score, etc. For example, different weights can be assigned to different attribute items, so that the final user experience information can be determined based on the scores of different attribute items.

[0060] Different information systems may have different click-through rates after exposure and different user experience information for the same candidate information. For example, in information system C1, candidate information D0 corresponds to click-through rate E1 after exposure and user experience information F1, and in information system C2, candidate information D0 corresponds to click-through rate E2 after exposure and user experience information F2.

[0061] In addition, the second attribute information also includes the current bid information for the candidate information, wherein the current bid information refers to the amount that the information provider of the candidate information is willing to pay in order to display the candidate information, wherein the cost information of a single click of the candidate information for each access request may be lower than the current bid information. Furthermore, in the case where multiple information systems include an advertising system, the second attribute information of the candidate information in the advertising system also includes the current bid information. Furthermore, the bid information of non-advertising systems in multiple information systems may be 0.

[0062] It should be noted that, for bidding information, historical bidding information is irrelevant to the information system, and the historical bidding information is the same for different information systems. However, the current bidding information (or current bidding information) can be considered to be related to the information system. For example, the current bidding information of the candidate information is 6 yuan. If the target display form of the candidate information is an advertising display form, the current bidding information corresponding to the candidate information is 6 yuan. If the target display form of the candidate information is a natural display form, the current bidding information corresponding to the candidate information is 0 yuan.

[0063] (ii) Information display decision part: i.e. selecting target information from multiple candidate information; returning the target information to the requesting end of the information display request, so that the requesting end can display the target information in the target display form of the target information. The requesting end can be the terminal device involved in the above-mentioned embodiment.

[0064] Optionally, the display order of the multiple candidate information is determined according to the target display form and the second attribute information of the multiple candidate information, and the target information is selected from the multiple candidate information according to the display order of the multiple candidate information.

[0065] Among them, the display order of multiple candidate information can reflect the order of multiple candidate information in the display position. The earlier the display order, the higher the probability of the candidate information being clicked, and the later the display order, the lower the probability of the candidate information being clicked.

[0066] The implementation method of selecting target information from multiple candidate information according to the display order of multiple candidate information is not limited. For example, the number information of the display positions is obtained. If the number information is greater than or equal to the number of the multiple candidate information, the multiple candidate information can be used as the target information; if the number information is less than the number of the multiple candidate information, part of the candidate information corresponding to the number information can be selected in turn according to the display order of the multiple candidate information as the target information. The number information of the display positions is related to the layout and design of the terminal and the layout and design of the target application.

[0067] In the embodiment of the present application, the candidate information is not directly displayed in the display form corresponding to the information system to which it belongs, but the unique target display form of the candidate information is determined according to the attribute information of the candidate information, and the target information is selected from multiple candidate information and then displayed in the unique target display form. In the process of determining the target display form, it can be ensured that the candidate information belonging to multiple information systems at the same time can be displayed in the unique target display form, and will not be repeatedly displayed in multiple different display forms. It is not a simple deduplication process, and it can be ensured that the display form is not directly affected by the information system to which it belongs, for example, it is not affected by the bidding information of the advertising system itself, and the natural bidding independence is satisfied, and then the incentive compatibility between different information systems is satisfied, so as to achieve a balance between platform value and user experience.

[0068] In an optional embodiment, the implementation method of determining the target display form of multiple candidate information according to the first attribute information and the second attribute information of multiple candidate information is not limited. For example, multiple candidate information is divided into a first group and a second group, the target display form of the first group is the display form corresponding to the first information system, and the second attribute information of each candidate information in the first group is used to determine the target display form of each candidate information in the second group. In the process of dividing the first group and the second group, the current bid information of the multiple candidate information is not considered, indicating that the target display form of each candidate information in the first group is irrelevant to the bid information of each candidate information; in the process of determining the target display form of each candidate information in the second group, the current bid information of each candidate information in the second group is also not considered, ensuring that the target display form of each candidate information in the second group is irrelevant to the bid information of each candidate information itself, thereby ensuring that the target display form of each candidate information in the first group and the second group meets the aforementioned natural bid independence. In theory, multiple candidate information meets the natural bid independence, and as the bid information increases, the click rate of the candidate information meets the monotonically increasing property, and it can be considered that the fusion mechanism meets the incentive compatibility property.

[0069] A specific implementation method is provided below: multiple information systems include a first information system and a second information system, and multiple candidate information are divided into a first group and a second group according to first attribute information of multiple candidate information; the display form corresponding to the first information system is used as the target display form of the candidate information in the first group; for the candidate information in the first group, the second attribute information corresponding to the first information system is selected from its multiple second attribute information as the third attribute information, that is, the third attribute information is the second attribute information corresponding to the first information system; based on the third attribute information of the candidate information in the first group and the first attribute information of the candidate information in the second group, the target display form of the candidate information in the second group is determined.

[0070] In the process of grouping multiple candidate information, the source systems of the multiple candidate information may not be considered first, and the source systems of the multiple candidate information are assumed to be unknown. According to the first attribute information of the multiple candidate information, some candidate information whose display form is highly similar to the display form of the first information system is selected from the multiple candidate information and added to the first group, and the candidate information that does not appear in the first group among the multiple candidate information is added to the second group. It can be considered that the candidate information in the first group is most likely derived from the first information system, and the candidate information in the second group may come from the first information system or the second information system.

[0071] The first display form corresponding to the first information system may be used as the target display form of each candidate information in the first group, while the target display form of the candidate information in the second group is to be determined and needs to be further determined.

[0072] In order to facilitate distinction and description, the display form corresponding to the first information system is referred to as the first display form, and the display form corresponding to the second information system is referred to as the second display form.

[0073] The implementation method of selecting the second attribute information corresponding to the first information system from the plurality of second attribute information as the third attribute information is not limited. For example, the second attribute information corresponding to the plurality of candidate information in the first information system and the second information system can be calculated based on the first attribute information of the plurality of candidate information; and the second attribute information corresponding to the first information system of the candidate information in the first group is obtained as the third attribute information.

[0074] The implementation method of calculating the second attribute information corresponding to the plurality of candidate information in the first information system and the second information system respectively according to the first attribute information of the candidate information is not limited. For example, the first attribute information of the plurality of candidate information can be input into the first information system, and the first information system outputs the second attribute information corresponding to the plurality of candidate information respectively; the first attribute information of the plurality of candidate information can be input into the second information system, and the second information system outputs the second attribute information of the plurality of candidate information respectively. Any information system can calculate the click rate contained in the second attribute information through the click rate prediction model, and determine the user experience information through numerical calculation. The input of the click rate prediction model is the first attribute information of the candidate information, and the output is the estimated click rate of the candidate information. The first information system or the second information system maintains the bid information corresponding to the candidate information. When the identification information of the candidate information is included in the first attribute information, the bid information of the candidate information can be obtained through the identification information of the candidate information. For example, if the first information system is an advertising system, the bid information of the candidate information is the bid information of the advertiser for the candidate information. If the second information system is a recommendation system, the bid information of the candidate information in the recommendation system defaults to 0.

[0075] For example, the first attribute information of multiple candidate information is expressed as C{c[1],...,c[n]}, where n is the number of multiple candidate information, c[i] represents the first attribute information corresponding to any candidate information, and 1≤i≤n. Among them, multiple candidate information can be expressed as a set N={1,2,…,n}. Taking the second attribute information corresponding to multiple candidate information including: click-through rate CTR[i] after exposure, user experience information UE[i] and current bid information b[i] as an example, the second attribute information is exemplified.

[0076] Among them, the first attribute information C{c[1],...,c[n]} can be input into the first information system and the second information system respectively, and the first information system and the second system respectively output the corresponding second attribute information including: CTR[i,A], UE[i,A] and the current bid information b[i], wherein A indicates that multiple candidate information corresponds to the first display form, such as the advertising form; the second attribute information corresponding to the second information system includes: CTR[i,O], UE[i,O] and bid information b[i], wherein O indicates that multiple candidate information corresponds to the second display form, such as the natural form. If the number of candidate information is N, the value of i is 1 to n, and n is a positive integer. It should be noted that the bidding information in the first display form and the second display form are different. In the first display form, b[i] can be the actual bid, and in the second display form, b[i] can be 0.

[0077] The first group can be called an auxiliary decision subset, which means that the candidate information in the first group can assist in determining the display form of each candidate information in the second group; the second group can be called a pending decision subset, which means that the display form of each candidate information in the second group is pending. Therefore, according to the third attribute information of the candidate information in the first group and the first attribute information of the candidate information in the second group, the target display form of the candidate information in the second group is determined.

[0078] Optionally, a specific implementation method of determining the target display form of candidate information in the second group according to the third attribute information of the candidate information in the first group and the first attribute information of the candidate information in the second group includes: generating a first ranking score of the candidate information in the first group according to the third attribute information of each candidate information in the first group; for the convenience of distinction and description, the second attribute information corresponding to the second information system is referred to as the fourth attribute information; generating a second ranking score of the candidate information in the second group according to the fourth attribute information of the candidate information in the second group; generating a decision threshold corresponding to the candidate information in the second group according to the first ranking score of the candidate information in the first group and the first attribute information of the candidate information in the second group; if the second ranking score of the candidate information in the second group is less than the corresponding decision threshold, the first display form is used as the target display form; if the second ranking score of the candidate information in the second group is greater than or equal to the corresponding decision threshold, the second display form is used as the target display form. Wherein, each candidate information in the second group corresponds to a decision threshold, and when determining the target display form of the candidate information in the second group, it is determined by the decision threshold corresponding to the candidate information.

[0079] The calculation method of the first ranking score is not limited. For example, when the bid information b[i] of the second information system is 0, the first ranking score sa[i]=CTR[i;A]*(b[i]+UE[i;A]), the second ranking score so[j]=CTR[j;O]*UE[j;O], "*" represents a multiplication operation, the number in the second group is k, the number in the first group is Nk, and accordingly, 1≤i≤nk, 1≤j≤k, n>k, n is the number of candidate information, and i, j, k and n are all positive integers.

[0080] According to the first ranking score of the candidate information in the first group and the first attribute information of the candidate information in the second group, the decision thresholds corresponding to the candidate information in the second group are generated. The decision threshold is used to judge the display form of each candidate information in the second group. For example, the decision threshold is compared with the second ranking score of the candidate information to determine the display form of the candidate information. If the second group is represented by the set P = {p(1), p(2), ..., p(k)}, k≤m, m is the number of display positions. The first group is represented by the set Q=N\P={q(1),q(2),…,q(nk)}, and the decision threshold of the candidate information in the second group can be expressed as θ(p(j)). θ(p(j)) can satisfy the following two properties:

[0081] (1) For any candidate information q(i) in the first group, θ(p(j)) is monotonically non-decreasing with respect to sa(q(i)). For example, when any sa(q(i)) increases, all θ(p(j)) increase or remain unchanged.

[0082] (2)θ(p(j))≥sa(q(i)), where 1≤i≤m, and m is the number of display positions, that is, the output decision threshold is not lower than the first ranking score of the mth candidate information in the display order in the first group.

[0083] Among them, considering that the first ranking score of the candidate information in the first display form is related to the bid information, the higher the bid information, the higher the first ranking score, and the lower the bid information, the lower the ranking score. The second ranking score of the candidate information in the second display form is not related to the bid information (for example, the bid is 0), and the second ranking score is usually a fixed value.

[0084] For any candidate information in the second group, if the second ranking score of any candidate information is less than the decision threshold of the candidate information, the display order determined based on the second ranking score may be relatively late, resulting in the inability of the candidate information to be displayed. Therefore, the first display form can be used as the target display form of the candidate information, and the display order can be determined based on the first ranking score of the candidate information. If the bid is increased, the candidate information will have a chance to be displayed to increase the display probability. If the second ranking score of the candidate information is higher than or equal to its corresponding decision threshold, it means that the second ranking score of the candidate information is high and the probability of being displayed to the user is also high, and the second display form can be used as the target display form of the candidate information.

[0085] Further optionally, the display form decision part is implemented by a target display form determination network. The internal structure of the target display form determination network is not limited. Figure 2b As shown, the target display morphology determination network includes a division module F and a threshold module G.

[0086] The division module F is mainly used to divide the plurality of candidate information into the first group and the second group according to the first attribute information of the plurality of candidate information. Specifically, the first attribute information of the plurality of candidate information can be input into the division module of the target display form determination network, and the correlation between the plurality of candidate information is calculated according to the first attribute information of the plurality of candidate information, and the plurality of candidate information is divided into the first group and the second group according to the correlation between the plurality of candidate information.

[0087] The partitioning module F can be implemented by any neural network model, for example, the Transformer model. The Transformer model is a neural network model based on the self-attention mechanism. The partitioning module F can capture the relationship between the input information (different first attribute information) through the multi-head attention mechanism, and retain the position information of the elements (such as attribute items) in the input sequence through position encoding. The correlation between multiple candidate information is learned through the encoder-decoder structure. The encoder is stacked with multiple identical layers, each of which includes a multi-head self-attention sublayer and a feedforward neural network sublayer. The decoder is also composed of multiple identical layers, each of which includes a multi-head self-attention sublayer (for attention calculation inside the decoder), a multi-head attention sublayer (for attention calculation between the encoder and the decoder) and a feedforward neural network sublayer. Residual connection and layer normalization can also be used. Residual connection: Adding residual connection before each sublayer helps gradient propagation. Layer normalization applies layer normalization after each sublayer, which helps stabilize the training process.

[0088] Among them, the threshold module G is mainly used to generate a decision threshold corresponding to the candidate information in the second group according to the first ranking score of the candidate information in the first group and the first attribute information of the candidate information in the second group. For example, according to the first ranking score of the candidate information in the first group and the number of booths, at least part of the candidate information is selected from the first group; the first ranking score corresponding to at least part of the candidate information and the first attribute information of the candidate information in the second group are input into the threshold generation module of the target display form determination network. In the threshold generation module, the decision threshold corresponding to the candidate information in the second group is generated with the goal that the decision threshold is monotonically non-decreasing relative to the first ranking score corresponding to at least part of the candidate information, and the decision threshold is greater than or equal to the third ranking score. The first ranking score corresponding to at least part of the candidate information includes the third ranking score. For example, the third ranking score can be the minimum value of the first ranking scores corresponding to the at least part of the candidate information, or the third ranking score can also be the minimum value plus a set threshold. The set threshold can be 0.5 or 1, etc., and there is no limitation on this.

[0089] Furthermore, with the goal that the threshold module satisfies the two properties of θ(p(j)) introduced above, a decision threshold corresponding to each candidate information in the second group is generated.

[0090] The threshold module G can be implemented by any neural network model, for example, the Transformer model. The two properties satisfied by θ(p(j)) introduced above can be implemented by designing the internal structure of the threshold module G. When the threshold module G adopts the Transformer model, the internal structure of the Transformer model can refer to the introduction of the partition module F mentioned above.

[0091] It should be noted that the information display form decision part can be implemented by using both the partition module F and the threshold module G, or by using the partition module F alone, or by using the threshold module G alone, and the other functions can be implemented by numerical calculation.

[0092] exist Figure 2b In the figure, the division module F and the threshold module G are used at the same time. The following is a detailed description of the first information system being an advertising system and the second information system being a recommendation system.

[0093] (1) Input multiple first attribute information c[1], ..., c[n] of multiple candidate information into the division module F, and divide the multiple candidate information into a first group Q and a second group P, where P is the subset to be decided and Q is the auxiliary decision subset. Wherein, P = {p(1), p(2), ..., p(k)}, k≤m, m is the number of display positions. Q=N\P={q(1),q(2),…,q(nk)} represents, “N\P” represents the set of elements that belong to set N but not to set P.

[0094] (2) The target display form of the candidate information q[i] in the first group Q is set to the advertising display form, denoted as z[q[i]]=1. The candidate information in the second group Q is sorted from high to low according to the advertising ranking score, that is, sa[q[1]]≥…≥sa[q[nk]]. Let Qm={q[1],...,q[m]} represent the m candidate information with the highest advertising ranking scores in Q. Among them, the advertising ranking score is calculated in the same or similar manner as the aforementioned first ranking score, and the details can be found in the aforementioned introduction.

[0095] (3) Enumerate each candidate information p[i] in the second group P: i = 1, ..., k, and use the following method to determine the target display form z[p[i]] of the candidate information p[i] using the advertising ranking score of the candidate information in Qm. For example, the advertising ranking scores sa[q[1]], ..., sa[q[m]] of each candidate information in Qm and the first attribute information c[p[1]], ..., c[p[k]] of each candidate information in the second group P are input into the threshold module G, and the threshold module G outputs the judgment threshold θ[p[i]] corresponding to each candidate information in the second group P; the natural ranking score so[p[i]] of each candidate information p[i] in the second group P is calculated; it is judged whether so[p[i]] reaches the threshold θ[p[i]], if so[p[i]]≥θ[p[i]], the target display form of p[i] is set to the natural display form, that is, z[p[i]]=0; otherwise, if so[p[i]]<θ[p[i]], the target display form of p[i] is set to the advertising display form, that is, z[p[i]]=1.

[0096] In an optional embodiment, it also includes: a process of training the target display form determination network by using reinforcement learning. Specifically: obtaining multiple sample data, any sample data includes multiple sample candidate information obtained from multiple information systems, and the multiple sample candidate information includes: first attribute information irrelevant to the multiple information systems, and second attribute information corresponding to the multiple information systems, and different information systems correspond to different display forms; inputting the first attribute information and multiple second attribute information of the multiple sample candidate information into the initial display form determination network, and determining the target display form of the multiple sample candidate information through the initial display form determination network; determining the reward value corresponding to the initial display form determination network according to the target display form of the multiple sample candidate information and the attenuation coefficient of the display position; with the goal of maximizing the reward value, the initial display form determination network is model trained until the set conditions are met to obtain the target display form determination network.

[0097] The reward value can be d[i] is the total ranking score after the information form decision is made using the initial partitioning module F and the initial threshold module G, wherein β[i] is a monotonically decreasing click rate coefficient of the display position. For a detailed introduction to d[i], please refer to the above embodiment, which will not be repeated here.

[0098] Among them, the set conditions may include that the reward value no longer changes; or the number of training times reaches a set number threshold, such as the set number threshold may be 10,000 times, 50,000 times, or 100,000 times; or the training time reaches a set time threshold, for example, 1 day, 2 days or 5 days.

[0099] In an optional embodiment, the implementation method of determining the display order of multiple candidate information based on the target display forms and multiple second attribute information of multiple candidate information is not limited. A specific implementation method includes: for any candidate information, if the target display form of any candidate information is identified as the first display form, generating a target ranking score of any candidate information according to the third attribute information included in any candidate information; if the target display form of any candidate information is identified as the second display form, generating a target ranking score of any candidate information according to the fourth attribute information of any candidate information; determining the display order of multiple candidate information according to the respective target ranking scores of the multiple candidate information, wherein the target ranking score is positively correlated with the display order, that is, the higher the target ranking score, the frontier the display order, the higher the exposure rate of the display position, and the higher the click rate obtained by displaying the candidate information at the display position.

[0100] Optionally, a target ranking score for any candidate information is generated based on the third attribute information of any candidate information, including: generating the target ranking score for the candidate information based on the current bid information, user experience information and click-through rate information of the candidate information in the third attribute information of the candidate information; and generating the target ranking score for the candidate information based on the fourth attribute information of the candidate information, including: generating the target ranking score for the candidate information based on the user experience information and click-through rate information in the fourth attribute information of the candidate information.

[0101] For example, the target ranking score s[i]=z[i]*sa[i]+(1-z[i])*so[i]. Wherein, 1≤i≤n, n is the number of candidate information, and z[i] is the display form of the candidate information. For example, z[i]=1 indicates that the target display form of the candidate information is the first display form (such as an advertising display form), and z[i]=0 indicates that the target display form of the candidate information is the second display form (such as a natural display form). Wherein, sa[i] may be the first ranking score mentioned above, and so[i] may be the second ranking score mentioned above, wherein the generated first ranking score and the second ranking score may be saved, and when calculating the target ranking score, the saved first ranking score or the second ranking score may be obtained in combination with the target display form of the candidate information to calculate the target ranking score of the candidate information.

[0102] Among them, the target ranking scores can be sorted from high to low to obtain the order of target ranking scores s[1], ..., s[n], from which m (the number of display positions) candidate information with the highest target ranking scores are selected and added to the set D = (d[1], ..., d[m]), and the display positions from front to back are allocated in turn, and displayed according to the target display form of each candidate information.

[0103] In an optional embodiment, after displaying the target information, cost information may also be determined for candidate information whose target display form is the first display form. Specifically, the first target information is screened out from the target information, and the number of the first target information may be one or more, for example, 10, 15, or 18. The target display form of the first target information is the first display form; based on the first click-through rate corresponding to the display position of any first target information and the second click-through rate of any first target information itself, the third click-through rate of any first target information at the display position is estimated; based on the third click-through rate and the bid information for any first target information, the single cost information of any first target information being clicked under the information display request is determined.

[0104] The second click-through rate of the first target information itself indicates the probability of a user clicking on the product when the product is displayed to the user, which reflects the attractiveness of the product itself and can measure the attractiveness and popularity of the first target information. The click-through rate of the display position of the first target information indicates the probability of the first target information being clicked on a specific display position, which reflects the impact of different display positions on the click-through rate, and can evaluate the display effect of the display position and guide the information display strategy. The third click-through rate can be the product of the first click-through rate and the second click-through rate. Furthermore, different weights can be added to the first click-through rate and the second click-through rate and then multiplied to obtain the third click-through rate.

[0105] The implementation method of determining the single cost information of any first target information being clicked under the information display request based on the third click rate and the bid information for any first target information is not limited. For example, according to economic theory, there is a unique cost rule for the above allocation rules so that the fusion mechanism satisfies the incentive compatibility property. For any first target information i, it can be determined according to the standard formula 1≤i≤m, calculate the cost information of a single click on any first target information, where x i (z) represents the click rate of the first target information i displayed at the display position when the bid information of the other first target information is fixed and the bid is z for any first target information i.

[0106] In an optional embodiment, the implementation method of obtaining multiple candidate information from multiple information systems corresponding to the target platform in response to the information display request is not limited. The following provides a specific implementation method. In the case where the multiple information systems include a first information system and a second information system, in response to the information display request, a first information set is obtained from the first information system, and a second information set is obtained from the second information system; wherein, there may or may not be duplicate elements in the first information set and the second information set. Therefore, it can be determined whether there are duplicate elements in the first information set and the second information set; if there is duplicate information in the first information set and the second information set, the duplicate information in the first information set and the second information set is deduplicated to obtain multiple candidate information. For example, the deduplication process can be to take the union of the first information set and the second information set to obtain multiple non-duplicate candidate information.

[0107] It should be noted that when there are duplicate elements in the first information set and the second information set, they are retained as candidate information when deduplication is performed. The candidate information may have second attribute information related to the first information system and second attribute information related to the second information system. For example, the candidate information has two display forms, namely the first display form and the second display form, and it is not certain in which display form the candidate information is displayed. Therefore, the present application can be used to Figure 1a The method shown determines a target presentation modality for candidate information.

[0108] Of course, if there is no duplicate information in the first information set and the second information set, Figure 1a The method shown determines the target display form of multiple candidate information, determines the display order, and determines the target information that can be displayed based on the number of display positions.

[0109] Optionally, if there is no duplicate information between the first information set and the second information set, the information included in the first information set and the second information set can be directly used as multiple candidate information, and the display forms can be determined according to the source systems of the multiple candidate information, and the display order can be calculated, so as to determine the target information that can be displayed according to the number of display positions.

[0110] The method provided in the embodiment of the present application has the following advantages:

[0111] (1) The allocation rule of the fusion mechanism Y3 is divided into two parts: information form decision and information display order decision. The target display form of each candidate information is determined in advance through the information form decision method to ensure that no repeated display occurs.

[0112] (2) The information form decision method divides multiple candidate information into a first group and a second group, determines that the target display form of each candidate information in the first group is the first display form, and uses the first ranking score (such as the advertising ranking score) of each candidate information in the second group to make an adaptive decision on the target display form of each candidate information in the first group, thereby ensuring that the aforementioned natural bid independence is met, thereby ensuring the advertiser incentive compatibility.

[0113] (3) By combining reinforcement learning training, the decision-making strategy of information display format can be optimized in a data-driven manner, and the display format of key information can be flexibly adjusted, thereby effectively optimizing the multi-objective utility of the platform.

[0114] The exemplary embodiment of the present application also provides an information display method, such as Figure 1b As shown, the method includes:

[0115] 101b. In response to the information display request, multiple candidate information is obtained from multiple information systems of the target platform, where the candidate information includes first attribute information that is not related to the multiple information systems and second attribute information that is related to the multiple information systems, and different information systems correspond to different display forms;

[0116] 102b. Determine target display forms of the plurality of candidate information according to the first attribute information and the second attribute information of the plurality of candidate information, wherein the target display form of the candidate information is the same as or different from the display form corresponding to the information system to which the candidate information belongs;

[0117] 103b. Select target information from multiple candidate information, and display the target information in the target display form of the target information.

[0118] In this embodiment, the implementation method of obtaining multiple candidate information from multiple information systems of the target platform in response to the information display request is not limited. For example, a target application is running on the terminal device, and the target application provides a search page. The terminal device obtains the search term in response to the user's input operation on the information display page; wherein the input operation can be a voice input operation or a text input operation, etc. The terminal device obtains multiple candidate information from multiple information systems corresponding to the target platform in response to the information display request. For another example, the terminal device can obtain multiple candidate information from multiple information systems corresponding to the target platform in response to a startup operation for the target application, for the startup operation of the target application.

[0119] In either of the above situations, the information display request can be initiated by user operation, application event, or system event. User operation includes but is not limited to various interaction methods such as touch operation, gesture operation, voice operation, head movement operation, eye movement operation, etc. Touch operation includes but is not limited to single operation, double-click operation, long press operation, and sliding operation. Application events may include but are not limited to jump events or clock events from other applications to the target application, and system events may include but are not limited to power-on events, events to recover from sleep mode, and hardware connection events.

[0120] In this embodiment, the detailed description of step 102b and step 103b can be found in the above-mentioned embodiment, which will not be described again here.

[0121] The following provides a scenario implementation example, taking the target platform as an e-commerce platform, the candidate information as candidate product information, the first information system as an advertising system, the second information system as a recommendation system, the first attribute information as product attribute information, the second attribute information as marketing attribute information, the display form corresponding to the advertising system as an advertising form, and the form corresponding to the recommendation system as a natural form as an example, to exemplify the information display method.

[0122] Among them, the exemplary embodiment of the present application provides a flowchart of a method for displaying commodity information, combined with Figure 1c The method flow is described, and the method comprises:

[0123] 101c, displaying a first page, where the first page includes search entry information;

[0124] 102c. In response to a search operation initiated through the search entry information, a plurality of candidate product information matching the search term is obtained from the advertising system and the recommendation system; the candidate product information includes product attribute information and marketing attribute information corresponding to the advertising system and the recommendation system respectively;

[0125] 103c. Determine target display forms of the plurality of candidate product information according to product attribute information and marketing attribute information of the plurality of candidate product information, wherein the target display form is an advertising display form or a natural display form;

[0126] 104c. Select target product information from the plurality of candidate product information, and display the target product information on the second page in the target display form of the target product information.

[0127] In this embodiment, the first page can be any page in the target application that includes search entry information, for example, it can be the home page or an intermediate page, and there is no limitation on this. The search entry information can include but is not limited to: a search box, a navigation menu, a voice search control, and link information.

[0128] In this embodiment, different search entry information initiates search operations in different ways. For example, if the search entry information is a search box, and the search box includes a search term (default search term or user input), click the search control corresponding to the search box to initiate a search operation; if the search entry information is link information, click the link information to initiate a search operation; if the search entry information is a navigation menu, click the search term in the navigation menu to initiate a search operation; if the search entry information is a voice search control, enter the search term for the voice search control to initiate a search operation. Figure 1c The search entry information is illustrated as a search box as an example, and "mobile phone case" is used as an example as a search term, but it is not limited to this.

[0129] In this embodiment, in response to a search operation initiated through search entry information, multiple candidate product information that is compatible with the search term can be obtained from the advertising system and the recommendation system; the candidate product information includes product attribute information, and marketing attribute information corresponding to the advertising system and the recommendation system respectively; wherein, for an introduction to the product attribute information and the marketing attribute information, please refer to the aforementioned introduction to the first attribute information and the second attribute information.

[0130] In this embodiment, the target product information can be introduced by referring to the above-mentioned target information, which will not be described in detail here. The target product information can be displayed on the first page or on the second page, without limitation. The second page can be a product list page. Figure 1c In the example, target product information F1 to target product information F5 are taken as examples, and target product information F1 and target product information F4 are advertisement display forms, but the present invention is not limited thereto.

[0131] It should be noted that the above-mentioned product information display method can be implemented by combining the terminal and the server, such as Figure 1c As shown; the commodity information display method can also be implemented by the terminal alone, and there is no limitation on this.

[0132] The present application also provides a page display method, combining Figure 1d The method flow is described, and the method comprises:

[0133] 101d. In response to a request to start the target application, a plurality of candidate product information adapted to the user attribute information is obtained from the advertising system and the recommendation system; the candidate product information includes product attribute information and marketing attribute information corresponding to the advertising system and the recommendation system respectively;

[0134] 102d. Determine target display forms of the plurality of candidate product information according to product attribute information and marketing attribute information of the plurality of candidate product information, wherein the target display form is an advertising display form or a natural display form;

[0135] 103d. Select target product information from the plurality of candidate product information, and display the target product information on the homepage of the target application in the target display form of the target product information.

[0136] In this embodiment, the method is a page display method for starting the target application process. The manner of starting the target application is not limited. For example, the target application can be started by user operation, by application event, or by system event, and there is no limitation on this. User operations include but are not limited to various interaction methods such as touch operation, gesture operation, voice operation, head movement operation, eye movement operation, etc. Touch operations include but are not limited to stand-alone operation, double-click operation, long press operation, and sliding operation. Application events may include but are not limited to jump events or clock events from other applications to the target application, and system events may include but are not limited to power-on events, events to recover from sleep mode, and hardware connection events. In Figure 1d In the figure, the start request is initiated by a user operation as an example, but the present invention is not limited to this.

[0137] The user attribute information may include but is not limited to: the user's nickname, tags, historical browsing information, favorites, and purchase records. The implementation method of displaying the target product information on the home page can refer to the above-mentioned method for displaying the target information, and will not be described in detail. Figure 1c Target product information E1 to target product information E6 are taken as examples for illustration, wherein the display order from front to back is: target product information E1 to target product information E6, target product information E1 is displayed in the carousel area, the display area of ​​target product information E2 is larger than the areas of target product information E3 to target product information E6, wherein the borders of the display areas of target product information E1 and target product information E3 are dotted lines, indicating that the display forms of target product information E1 and target product information E3 are advertising display forms, and target product information E2 and target product information E4 to target product information E6 are natural display forms.

[0138] It should be noted that the above page display method can be implemented by combining the terminal and the server, or the page display method can be implemented by the terminal alone, such as Figure 1d As shown, this is not limited.

[0139] Regarding the embodiments of the present application Figure 1b-1dThe detailed implementation and beneficial effects of each step in the method have been described in detail in the aforementioned embodiments and will not be elaborated here.

[0140] It should be noted that the execution subject of each step of the method provided in the above embodiment can be the same device, or the method can be executed by different devices. For example, the execution subject of steps 101a to 103a can be device A; for another example, the execution subject of steps 101a and 102a can be device A, and the execution subject of step 103a can be device B; and so on.

[0141] In addition, in some of the processes described in the above embodiments and the accompanying drawings, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel, and the sequence numbers of the operations, such as 101a, 102a, etc., are only used to distinguish between different operations, and the sequence numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0142] Figure 3 A schematic diagram of the structure of an information display device provided by an exemplary embodiment of the present application, such as Figure 3 As shown, the device includes: an acquisition module 31, a determination module 32, a selection module 33 and a return module 34.

[0143] The acquisition module 31 is used to respond to the information display request and acquire multiple candidate information from multiple information systems of the target platform, wherein the candidate information includes first attribute information irrelevant to the multiple information systems and multiple second attribute information corresponding to the multiple information systems, and different information systems correspond to different display forms;

[0144] A determination module 32, configured to determine a target display form of the plurality of candidate information according to the first attribute information and the plurality of second attribute information of the plurality of candidate information, wherein the target display form of the candidate information is the same as or different from the display form corresponding to the information system to which the candidate information belongs;

[0145] A selection module 33, used to select target information from multiple candidate information;

[0146] The return module 34 is used to return the target information to the request end of the information display request, so that the request end can display the target information in the target display form of the target information.

[0147] In an optional embodiment, the multiple information systems include a first information system and a second information system, and the determination module is specifically used to: divide the multiple candidate information into a first group and a second group according to the first attribute information of the multiple candidate information; use the display form corresponding to the first information system as the target display form of the candidate information in the first group, and for the candidate information in the first group, select the second attribute information corresponding to the first information system from its multiple second attribute information as the third attribute information; determine the target display form of the candidate information in the second group according to the third attribute information of the candidate information in the first group and the first attribute information of the candidate information in the second group.

[0148] Optionally, the determination module is specifically used to: input the first attribute information of multiple candidate information into the division module of the target display form determination network, calculate the correlation between the multiple candidate information according to the first attribute information of the multiple candidate information, and divide the multiple candidate information into the first group and the second group according to the correlation between the multiple candidate information.

[0149] Optionally, the determination module is specifically used to: generate a first ranking score for the candidate information in the first group based on the third attribute information of each candidate information in the first group; generate a second ranking score for the candidate information in the second group based on the fourth attribute information of the candidate information in the second group, the fourth attribute information refers to the second attribute information corresponding to the second information system; generate a decision threshold corresponding to the candidate information in the second group based on the first ranking score of each candidate information in the second group and the first attribute information of each candidate information in the second group; if the second ranking score of the candidate information in the second group is less than the corresponding decision threshold, then use the display form corresponding to the first information system as the target display form; if the second ranking score of the candidate information in the second group is greater than or equal to the corresponding decision threshold, then use the display form corresponding to the second information system as the target display form.

[0150] Further optionally, the determination module is specifically used to: select at least part of the candidate information from the first group according to the first ranking score of the candidate information in the first group and the number of booths; input the first ranking score corresponding to at least part of the candidate information and the first attribute information of the candidate information in the second group into the threshold generation module of the target display form determination network; in the threshold generation module, generate the decision threshold corresponding to the candidate information in the second group with the goal that the decision threshold is monotonically non-decreasing with respect to the first ranking score corresponding to at least part of the candidate information and the decision threshold is greater than or equal to the third ranking score, and the first ranking score corresponding to at least part of the candidate information includes the third ranking score.

[0151] In an optional embodiment, the selection module is specifically used to: determine the display order of multiple candidate information according to the target display forms of the multiple candidate information and multiple second attribute information; and select target information from the multiple candidate information according to the display order of the multiple candidate information.

[0152] Optionally, the selection module is specifically used to: for any candidate information, if the target display form of the candidate information is identified as the display form corresponding to the first information system, generate a target ranking score of the candidate information according to the third attribute information of the candidate information; the third attribute information is the second attribute information corresponding to the first information system; if the target display form of the candidate information is identified as the display form corresponding to the second information system, generate a target ranking score of the candidate information according to the fourth attribute information of the candidate information; the fourth attribute information is the second attribute information corresponding to the second information system; determine the display order of multiple candidate information according to their respective target ranking scores, and the target ranking score is positively correlated with the display order.

[0153] Further optionally, the selection module is specifically used to: generate a target ranking score for the candidate information based on the current bid information, user experience information and click-through rate information of the candidate information in the third attribute information of the candidate information; generate a target ranking score for the candidate information based on the user experience information and click-through rate information in the fourth attribute information of the candidate information.

[0154] In an optional embodiment, the device also includes: a screening module and an estimation module; after displaying the target information, the screening module is used to filter out the first target information from the target information, and the target display form of the first target information is the first display form; the estimation module is used to estimate the third click-through rate of the first target information at the display position based on the first click-through rate corresponding to the display position of the first target information and the second click-through rate of the first target information itself; the determination module is also used to: determine the single cost information of the first target information being clicked under the information display request based on the third click-through rate and the bid information for the first target information.

[0155] In an optional embodiment, the device also includes: a training module; the training module is used to obtain multiple sample data, the sample data includes multiple sample candidate information obtained from multiple information systems, the multiple sample candidate information includes: first attribute information independent of the multiple information systems, and multiple second attribute information corresponding to the multiple information systems, different information systems correspond to different display forms; the first attribute information and the multiple second attribute information of the multiple sample candidate information are input into the initial display form determination network, and the target display form of the multiple sample candidate information is determined by the initial display form determination network; the reward value corresponding to the initial display form determination network is determined according to the target display form of the multiple sample candidate information and the attenuation coefficient of the display position; with the goal of maximizing the reward value, the initial display form determination network is model trained until the set conditions are met to obtain the target display form determination network.

[0156] In an optional embodiment, the first information system is an advertising system, and the second information system is a recommendation system.

[0157] In an optional embodiment, the multiple information systems include a first information system and a second information system; the acquisition module is specifically used to: respond to an information display request, obtain a first information set from the first information system, and obtain a second information set from the second information system; if there is duplicate information in the first information set and the second information set, deduplicate the duplicate information in the first information set and the second information set to obtain multiple candidate information; wherein the information retained by the duplicate information is used as candidate information, and the candidate information has second attribute information related to the first information system and second attribute information related to the second information system.

[0158] An embodiment of the present application also provides another information display device, which includes: an acquisition module, a determination module, a selection module and a display module.

[0159] An acquisition module, used to respond to an information display request and acquire multiple candidate information from multiple information systems of a target platform, wherein the candidate information includes first attribute information irrelevant to the multiple information systems and second attribute information corresponding to the multiple information systems, and different information systems correspond to different display forms;

[0160] A determination module, configured to determine target display forms of the plurality of candidate information according to the first attribute information and the plurality of second attribute information of the plurality of candidate information, wherein the target display forms of the candidate information are the same as or different from the display forms corresponding to the information system to which the candidate information belongs;

[0161] Selection module, used to select target information from multiple candidate information

[0162] The display module is used to display the target information in the target display form of the target information.

[0163] The embodiment of the present application also provides a commodity information display device, which includes: a display module, an acquisition module, a determination module and a selection module.

[0164] A display module, used to display a first page, the first page including search entry information;

[0165] An acquisition module, configured to acquire, in response to a search operation initiated through search entry information, a plurality of candidate product information adapted to the search term from the advertising system and the recommendation system; the candidate product information includes product attribute information and marketing attribute information corresponding to the advertising system and the recommendation system respectively;

[0166] A determination module, used to determine a target display form of the plurality of candidate product information according to product attribute information and marketing attribute information of the plurality of candidate product information, wherein the target display form is an advertising display form or a natural display form;

[0167] The selection module is used to select target product information from multiple candidate product information and display the target product information on the second page in a target display form of the target product information.

[0168] The embodiment of the present application also provides a page display device, which includes: an acquisition module, a determination module and a selection module;

[0169] An acquisition module, used to respond to an access request to a target application and acquire multiple candidate product information adapted to user attribute information from an advertising system and a recommendation system; the candidate product information includes product attribute information and marketing attribute information corresponding to the advertising system and the recommendation system respectively;

[0170] A determination module, used to determine a target display form of the plurality of candidate product information according to product attribute information and marketing attribute information of the plurality of candidate product information, wherein the target display form is an advertising display form or a natural display form;

[0171] The selection module is used to select target product information from multiple candidate product information and display the target product information on the home page of the target application in the target display form of the target product information.

[0172] Regarding the embodiments of the present application Figure 3 The detailed implementation and beneficial effects of each step in the illustrated device have been described in detail in the aforementioned embodiments and will not be elaborated on here.

[0173] Figure 4 A schematic diagram of the structure of an electronic device provided by an exemplary embodiment of the present application is shown in FIG. Figure 4 As shown, the device includes: a memory 44 and a processor 45.

[0174] The memory 44 is used to store computer programs and can be configured to store various other data to support operations on the electronic device. Examples of such data include instructions for any application or method used to operate on the electronic device.

[0175] The processor 45 is coupled to the memory 44 and is used to execute the computer program in the memory 44, so as to: in response to an information display request, obtain multiple candidate information from multiple information systems of a target platform, the candidate information includes first attribute information that is unrelated to the multiple information systems, and second attribute information that corresponds to the multiple information systems, and different information systems correspond to different display forms; determine the target display form of the multiple candidate information according to the first attribute information and the multiple second attribute information of the multiple candidate information, the target display form of the candidate information is the same as or different from the display form corresponding to the information system to which the candidate information belongs; select the target information from the multiple candidate information; return the target information to the request end of the information display request, so that the request end can display the target information in the target display form of the target information.

[0176] In an optional embodiment, the multiple information systems include a first information system and a second information system. When the processor 45 determines the target display form of the multiple candidate information based on the first attribute information and the multiple second attribute information of the multiple candidate information, it is specifically used to: divide the multiple candidate information into a first group and a second group based on the first attribute information of the multiple candidate information; use the display form corresponding to the first information system as the target display form of the candidate information in the first group; for the candidate information in the first group, select the second attribute information corresponding to the first information system from its multiple second attribute information as the third attribute information; determine the target display form of the candidate information in the second group based on the third attribute information of the candidate information in the first group and the first attribute information of the candidate information in the second group.

[0177] Optionally, when the processor 45 divides the multiple candidate information into the first group and the second group according to the first attribute information of the multiple candidate information, it is specifically used to: input the first attribute information of the multiple candidate information into a division module of the target display form determination network, calculate the correlation between the multiple candidate information according to the first attribute information of the multiple candidate information, and divide the multiple candidate information into the first group and the second group according to the correlation between the multiple candidate information.

[0178] Optionally, when the processor 45 determines the target display form of the candidate information in the second group based on the third attribute information of the candidate information in the first group and the first attribute information of the candidate information in the second group, it is specifically used to: generate a first ranking score for the candidate information in the first group based on the third attribute information of the candidate information in the first group; generate a second ranking score for the candidate information in the second group based on the fourth attribute information of the candidate information in the second group, the fourth attribute information referring to the second attribute information corresponding to the second information system; generate a decision threshold corresponding to the candidate information in the second group based on the first ranking score of the candidate information in the first group and the first attribute information of the candidate information in the second group; if the second ranking score of the candidate information in the second group is less than the corresponding decision threshold, use the display form corresponding to the first information system as the target display form; if the second ranking score of the candidate information in the second group is greater than or equal to the corresponding decision threshold, use the display form corresponding to the second information system as the target display form.

[0179] Further optionally, when the processor 45 generates a decision threshold corresponding to the candidate information in the second group based on the first ranking score of the candidate information in the first group and the first attribute information of the candidate information in the second group, it is specifically used to: select at least part of the candidate information from the first group based on the first ranking score of the candidate information in the first group and the number of booths; input the first ranking score corresponding to at least part of the candidate information and the first attribute information of the candidate information in the second group into a threshold generation module of the target display form determination network; in the threshold generation module, generate a decision threshold corresponding to the candidate information in the second group with the goal that the decision threshold is monotonically non-decreasing with respect to the first ranking score corresponding to at least part of the candidate information and the decision threshold is greater than or equal to the third ranking score, and the first ranking score corresponding to at least part of the candidate information includes the third ranking score.

[0180] In an optional embodiment, when the processor 45 selects target information from multiple candidate information, it is specifically used to: determine the display order of multiple candidate information according to the target display forms of the multiple candidate information and multiple second attribute information; select the target information from the multiple candidate information according to the display order of the multiple candidate information.

[0181] Optionally, the multiple information systems include a first information system and a second information system. When the processor 45 determines the display order of multiple candidate information based on the target display forms of the multiple candidate information and the multiple second attribute information, it is specifically used to: for any candidate information, if the target display form of the candidate information is identified as the display form corresponding to the first information system, generate a target ranking score of the candidate information according to the third attribute information of the candidate information; the third attribute information is the second attribute information corresponding to the first information system; if the target display form of the candidate information is identified as the display form corresponding to the second information system, generate a target ranking score of the candidate information according to the fourth attribute information of the candidate information; the fourth attribute information is the second attribute information corresponding to the second information system; determine the display order of the multiple candidate information according to their respective target ranking scores, and the target ranking score is positively correlated with the display order.

[0182] Optionally, when the processor 45 generates a target ranking score for the candidate information based on the third attribute information of the candidate information, the processor 45 is specifically used to: generate a target ranking score for the candidate information based on the current bid information, user experience information, and click-through rate information of the candidate information in the third attribute information of the candidate information; when the processor 45 generates a target ranking score for the candidate information based on the fourth attribute information of the candidate information, the processor 45 is specifically used to: generate a target ranking score for the candidate information based on the user experience information and click-through rate information in the fourth attribute information of the candidate information.

[0183] In an optional embodiment, after displaying the target information, the processor 45 is further used to: filter out the first target information from the target information, the target display form of the first target information is the display form corresponding to the first information system; estimate the third click rate of the first target information at the display position based on the first click rate corresponding to the display position of the first target information and the second click rate of any first target information itself; determine the single cost information of the first target information being clicked under the information display request based on the third click rate and the bid information for the first target information.

[0184] In an optional embodiment, the processor 45 is also used to: obtain multiple sample data, the sample data includes multiple sample candidate information obtained from multiple information systems, the multiple sample candidate information includes: first attribute information independent of the multiple information systems, and second attribute information corresponding to the multiple information systems, different information systems correspond to different display forms; input the first attribute information and multiple second attribute information of the multiple sample candidate information into the initial display form determination network, and determine the target display form of the multiple sample candidate information through the initial display form determination network; determine the reward value corresponding to the initial display form determination network according to the target display form of the multiple sample candidate information and the attenuation coefficient of the display position; with the goal of maximizing the reward value, perform model training on the initial display form determination network until the set conditions are met to obtain the target display form determination network.

[0185] In an optional embodiment, the first information system is an advertising system, and the second information system is a recommendation system.

[0186] In an optional embodiment, the multiple information systems include a first information system and a second information system; when the processor 45 responds to an information display request and obtains multiple candidate information from multiple information systems of the target platform, it is specifically used to: respond to the information display request, obtain a first information set from the first information system, and obtain a second information set from the second information system; if there is duplicate information in the first information set and the second information set, deduplicate the duplicate information in the first information set and the second information set to obtain multiple candidate information; wherein the information that is retained as duplicate information is used as candidate information, and the candidate information has second attribute information related to the first information system and second attribute information related to the second information system.

[0187] Regarding the embodiments of the present application Figure 4 The detailed implementation and beneficial effects of each step in the illustrated device have been described in detail in the aforementioned embodiments and will not be elaborated on here.

[0188] Further, if Figure 4 As shown, the electronic device also includes: a communication component 46, a display 47, a power component 48, an audio component 49 and other components. Figure 4 Only some components are shown schematically, which does not mean that the electronic device only includes Figure 4 In addition, Figure 4The components in the dashed box are optional components, not mandatory components, and the specific components depend on the product form of the electronic device. The electronic device of this embodiment can be implemented as a terminal device such as a desktop computer, a laptop computer, a smart phone, or an IOT device, or a server device such as a conventional server, a cloud server, or a server array. If the electronic device of this embodiment is implemented as a terminal device such as a desktop computer, a laptop computer, a smart phone, etc., it can include Figure 4 If the electronic device of this embodiment is implemented as a server device such as a conventional server, a cloud server or a server array, it may not include Figure 4 Components within the dashed box.

[0189] The embodiment of the present application also provides an electronic device, the implementation structure of the electronic device is Figure 4 The implementation structure of the electronic device shown is the same or similar, and can refer to Figure 4 The electronic device provided in this embodiment is implemented as follows: Figure 4 The difference between the electronic devices in the illustrated embodiments mainly lies in that the functions implemented by the processor executing the computer program stored in the memory are different. For the electronic device provided in this embodiment, its processor executes the computer program stored in the memory, which can be used to: respond to information display requests, obtain multiple candidate information from multiple information systems of the target platform, the candidate information includes first attribute information unrelated to the multiple information systems, and second attribute information corresponding to the multiple information systems, and different information systems correspond to different display forms; determine the target display form of the multiple candidate information based on the first attribute information and the multiple second attribute information of the multiple candidate information, the target display form of the candidate information is the same as or different from the display form corresponding to the information system to which the candidate information belongs; select target information from the multiple candidate information, and display the target information in the target display form of the target information.

[0190] The detailed implementation and beneficial effects of the electronic device provided in the embodiments of the present application have been described in detail in the aforementioned embodiments and will not be elaborated here.

[0191] The embodiment of the present application also provides an electronic device, the implementation structure of the electronic device is Figure 4 The implementation structure of the electronic device shown is the same or similar, and can refer to Figure 4 The electronic device provided in this embodiment is implemented as follows: Figure 4The difference between the electronic devices in the illustrated embodiments mainly lies in that the functions implemented by the processor executing the computer program stored in the memory are different. For the electronic device provided in this embodiment, its processor executes the computer program stored in the memory, which can be used to: display a first page, the first page includes search entry information; in response to a search operation initiated through the search entry information, obtain multiple candidate product information adapted to the search term from the advertising system and the recommendation system; the candidate product information includes product attribute information, and marketing attribute information corresponding to the advertising system and the recommendation system respectively; determine the target display form of the multiple candidate product information based on the product attribute information and the marketing attribute information of the multiple candidate product information, the target display form is an advertising display form or a natural display form; select the target product information from the multiple candidate product information, and display the target product information on the second page in the target display form of the target product information.

[0192] The embodiment of the present application also provides an electronic device, the implementation structure of the electronic device is Figure 4 The implementation structure of the electronic device shown is the same or similar, and can refer to Figure 4 The electronic device provided in this embodiment is implemented as follows: Figure 4 The difference between the electronic devices in the illustrated embodiments mainly lies in that the functions implemented by the processor executing the computer program stored in the memory are different. For the electronic device provided in this embodiment, its processor executes the computer program stored in the memory, which can be used to: respond to the start request of the target application, obtain multiple candidate product information adapted to the user attribute information from the advertising system and the recommendation system; the candidate product information includes product attribute information, and the marketing attribute information corresponding to the advertising system and the recommendation system respectively; determine the target display form of the multiple candidate product information based on the product attribute information and the marketing attribute information of the multiple candidate product information, the target display form is an advertising display form or a natural display form; select the target product information from the multiple candidate product information, and display the target product information on the homepage of the target application in the target display form of the target product information.

[0193] Accordingly, the embodiment of the present application further provides a computer-readable storage medium storing a computer program, which can achieve the above-mentioned Figure 1a and Figure 1b The steps in the information display method, product information search method and page display method embodiments shown can be executed by an electronic device.

[0194] Accordingly, the embodiment of the present application also provides a computer program product, including a computer program / instruction, which, when executed by a processor, causes the processor to implement the above Figure 1a and Figure 1bThe steps in the information display method, product information search method and page display method embodiments shown can be executed by an electronic device.

[0195] The above-mentioned memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable programmable read only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0196] The above-mentioned communication component is configured to facilitate wired or wireless communication between the device where the communication component is located and other devices. The device where the communication component is located can access a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G / LTE, 5G and other mobile communication networks, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be based on Radio Frequency Identification (RFID) technology, Infrared Data Association (IrDA) technology, Ultra Wide Band (UWB) technology, Bluetooth (BT) technology and other technologies.

[0197] The above-mentioned display includes a screen, and the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0198] The power supply assembly provides power to various components of the device where the power supply assembly is located. The power supply assembly may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device where the power supply assembly is located.

[0199] The above-mentioned audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (Microphone, MIC), and when the device where the audio component is located is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in a memory or sent via a communication component. In some embodiments, the audio component also includes a speaker for outputting an audio signal.

[0200] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-readable storage media (including but not limited to disk storage, compact disc read-only memory (Compact Disc Read-Only Memory, CD-ROM), optical storage, etc.) containing computer-usable program code.

[0201] The present application is described with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, and the combination of the process and / or box in the flowchart and / or block diagram can be realized by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for realizing the function specified in one process or multiple processes in the flowchart and / or one box or multiple boxes in the block diagram.

[0202] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0203] These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0204] In a typical configuration, a computing device includes one or more processors (Central Processing Unit, CPU), input / output interface, network interface and memory.

[0205] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0206] Computer readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change random access memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0207] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0208] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. An information display method, characterized in that: include: In response to the information display request, a plurality of candidate information is obtained from a plurality of information systems of the target platform, wherein the candidate information includes first attribute information irrelevant to the plurality of information systems and a plurality of second attribute information corresponding to the plurality of information systems, and different information systems correspond to different display forms; Determine, according to the first attribute information and the second attribute information of the plurality of candidate information, a target display form of the plurality of candidate information, wherein the target display form of the candidate information is the same as or different from a display form corresponding to the information system to which the candidate information belongs; Select target information from the plurality of candidate information, and return the target information to the request end of the information display request, so that the request end can display the target information in the target display form of the target information.

2. The method according to claim 1, characterized in that The multiple information systems include a first information system and a second information system, and determining a target display form of the multiple candidate information according to the first attribute information and the multiple second attribute information of the multiple candidate information, including: Dividing the plurality of candidate information into a first group and a second group according to the first attribute information of the plurality of candidate information; Using the display form corresponding to the first information system as the target display form of the candidate information in the first group; For the candidate information in the first group, selecting the second attribute information corresponding to the first information system from the plurality of second attribute information as the third attribute information; A target display form of the candidate information in the second group is determined according to the third attribute information of the candidate information in the first group and the first attribute information of the candidate information in the second group.

3. The method according to claim 2, characterized in that According to the first attribute information of the plurality of candidate information, the plurality of candidate information is divided into a first group and a second group, comprising: The first attribute information of the multiple candidate information is input into the division module of the target display form determination network, the correlation between the multiple candidate information is calculated according to the first attribute information of the multiple candidate information, and the multiple candidate information is divided into a first group and a second group according to the correlation between the multiple candidate information.

4. The method according to claim 2, characterized in that: Determining a target display form of the candidate information in the second group according to the third attribute information of the candidate information in the first group and the first attribute information of the candidate information in the second group includes: generating a first ranking score of the candidate information in the first group according to the third attribute information of the candidate information in the first group; generating a second ranking score of the candidate information in the second group according to fourth attribute information of the candidate information in the second group, wherein the fourth attribute information refers to second attribute information corresponding to the second information system; generating a decision threshold corresponding to the candidate information in the second group according to the first ranking score of the candidate information in the first group and the first attribute information of the candidate information in the second group; If the second ranking score of the candidate information in the second group is less than the corresponding decision threshold, the display form corresponding to the first information system is used as the target display form; If the second ranking score of the candidate information in the second group is greater than or equal to the corresponding decision threshold, the display form corresponding to the second information system is used as the target display form.

5. The method according to claim 4, characterized in that Generating a decision threshold corresponding to the candidate information in the second group according to the first ranking score of the candidate information in the first group and the first attribute information of the candidate information in the second group includes: selecting at least part of the candidate information from the first group according to the first ranking score of the candidate information and the number of booths in the first group; Inputting the first ranking score corresponding to the at least part of the candidate information and the first attribute information of the candidate information in the second group into a threshold generation module of the target display form determination network; In the threshold generation module, a decision threshold corresponding to the candidate information in the second group is generated with the goal that the decision threshold is monotonically non-decreasing relative to the first ranking score corresponding to at least part of the candidate information, and the decision threshold is greater than or equal to the third ranking score, and the first ranking score corresponding to at least part of the candidate information includes the third ranking score.

6. The method according to any one of claims 1 to 5, characterized in that: Selecting target information from the plurality of candidate information includes: Determining a display order of the plurality of candidate information according to target display forms of the plurality of candidate information and the plurality of second attribute information; Select target information from the plurality of candidate information according to the presentation order of the plurality of candidate information.

7. The method according to claim 6, characterized in that The multiple information systems include a first information system and a second information system, and determine a display order of the multiple candidate information according to a target display form of the multiple candidate information and multiple second attribute information, including: For any candidate information, if it is identified that the target display form of the candidate information is the display form corresponding to the first information system, a target ranking score of the candidate information is generated according to the third attribute information of the candidate information; the third attribute information is the second attribute information corresponding to the first information system; If it is identified that the target display form of the candidate information is the display form corresponding to the second information system, generating a target ranking score of the candidate information according to the fourth attribute information of the candidate information; the fourth attribute information is the second attribute information corresponding to the second information system; The display order of the plurality of candidate information is determined according to the target ranking scores of each of the plurality of candidate information, and the target ranking scores are positively correlated with the display order.

8. The method according to claim 7, characterized in that Generating a target ranking score of the candidate information according to the third attribute information of the candidate information, including: generating a target ranking score of the candidate information according to the current bid information, the user experience information and the click rate information of the candidate information in the third attribute information of the candidate information; Generating a target ranking score of the candidate information according to the fourth attribute information of the candidate information includes: generating a target ranking score of the candidate information according to user experience information and click-through rate information in the fourth attribute information of the candidate information.

9. The method according to any one of claims 2-5 or 7-8, characterized in that: After displaying the target information, it also includes: Filtering out first target information from the target information, wherein the target display form of the first target information is a display form corresponding to the first information system; estimating a third click rate of the first target information at the display position according to the first click rate corresponding to the display position of the first target information and the second click rate of the first target information itself; According to the third click-through rate and the bid information for the first target information, the single cost information of the first target information being clicked in response to the information display request is determined.

10. The method according to claim 3 or 5, characterized in that: The method further comprises: Acquire a plurality of sample data, wherein the sample data includes a plurality of sample candidate information acquired from a plurality of information systems, wherein the plurality of sample candidate information includes: first attribute information irrelevant to the plurality of information systems, and a plurality of second attribute information corresponding to the plurality of information systems, wherein different information systems correspond to different display forms; Inputting the first attribute information and the second attribute information according to the plurality of sample candidate information into an initial display form determination network, and determining the target display form of the plurality of sample candidate information through the initial display form determination network; Determining a reward value corresponding to the initial display form determination network according to the target display forms and the attenuation coefficients of the display positions of the plurality of sample candidate information; With the goal of maximizing the reward value, the initial display form determination network is trained until the set conditions are met, thereby obtaining a target display form determination network.

11. The method according to any one of claims 2-5 or 7-8, characterized in that: The first information system is an advertisement system, and the second information system is a recommendation system.

12. The method according to any one of claims 1-5 or 7-8, characterized in that: The multiple information systems include a first information system and a second information system; in response to the information display request, multiple candidate information is obtained from the multiple information systems of the target platform, including: In response to the information display request, obtaining a first information set from the first information system and obtaining a second information set from the second information system; If there is duplicate information in the first information set and the second information set, deduplication processing is performed on the duplicate information in the first information set and the second information set to obtain multiple candidate information; The information that is retained as the duplicate information is used as candidate information, and the candidate information has second attribute information related to the first information system and second attribute information related to the second information system.

13. An information display method, characterized in that: include: In response to the information display request, a plurality of candidate information is obtained from a plurality of information systems of the target platform, wherein the candidate information includes first attribute information irrelevant to the plurality of information systems and second attribute information corresponding to the plurality of information systems, and different information systems correspond to different display forms; Determine, according to the first attribute information and the second attribute information of the plurality of candidate information, a target display form of the plurality of candidate information, wherein the target display form of the candidate information is the same as or different from a display form corresponding to the information system to which the candidate information belongs; Target information is selected from the plurality of candidate information, and the target information is displayed in a target display form of the target information.

14. A commodity information search method, characterized in that: include: Displaying a first page, wherein the first page includes search entry information; In response to a search operation initiated through the search entry information, a plurality of candidate product information matching the search term is obtained from an advertising system and a recommendation system; the candidate product information includes product attribute information and marketing attribute information corresponding to the advertising system and the recommendation system respectively; Determining target display forms of the plurality of candidate product information according to product attribute information and marketing attribute information of the plurality of candidate product information, wherein the target display form is an advertising display form or a natural display form; Select target product information from the plurality of candidate product information, and display the target product information on a second page in a target display form of the target product information.

15. A page display method, characterized in that: include: In response to a request to start a target application, multiple candidate product information that matches the user attribute information is obtained from an advertising system and a recommendation system; The candidate product information includes product attribute information, and marketing attribute information corresponding to the advertising system and the recommendation system respectively; Determining target display forms of the plurality of candidate product information according to product attribute information and marketing attribute information of the plurality of candidate product information, wherein the target display form is an advertising display form or a natural display form; Select target product information from the plurality of candidate product information, and display the target product information on the homepage of the target application in a target display form of the target product information.

16. An electronic device, characterized in that: include: Memory and processor; The memory is used to store a computer program; the processor is coupled to the memory and is used to execute the computer program to implement the steps in the method of any one of claims 1-12 and claims 13-15.

17. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor is caused to implement the steps in the method according to any one of claims 1 to 12 and claims 13 to 15.

18. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the processor is caused to implement the steps in the method of any one of claims 1-12 and claims 13-15.

Images