Promotion information processing method and device, equipment and storage medium

Abstract

The invention discloses a promotion information processing method and device, equipment and a storage medium, which are used for maximizing the resource quantity obtained by a media platform while ensuring the success rate of displaying promotion information. The method comprises the steps that a first request strategy for transaction platforms is adjusted, a second request strategy is obtained, and the first request strategy comprises the request sequence of requesting L transaction platforms to put promotion information to a media platform and the required resource quantity needed by the media platform for displaying the promotion information for each transaction platform; predicting a first total resource amount obtained from the L transaction platforms based on a historical resource amount and a first request strategy provided by the L transaction platforms to the media platform, and predicting a second total resource amount obtained from the L transaction platforms based on the historical resource amount and a second request strategy; determining a third request strategy based on the first resource total amount and the second resource total amount; and requesting L transaction platforms to put promotion information to the media platform based on the third request strategy.

Description

Technical Field

[0001] This application relates to the field of information processing technologies, and in particular, to a method, apparatus, device, and storage medium for processing promotion information. Background Art

[0002] Promoting information delivery through a media platform is an important technical means to achieve business promotion and has been widely applied. The media platform obtains promotion information from a trading platform and displays the promotion information on the pages accessed by users to obtain a certain amount of resources from the trading platform. Since the display opportunity each time a user accesses a page can only be allocated to one trading platform, and different trading platforms provide different amounts of resources for the promotion information, how the media platform requests promotion information from the trading platform determines the success rate of the media platform in displaying the promotion information and the amount of resources that can be obtained from the media platform. Summary of the Invention

[0003] The purpose of the embodiments of this application is to provide a method, apparatus, device, and storage medium for processing promotion information, which is used to maximize the amount of resources that the media platform can obtain while ensuring the success rate of displaying the promotion information.

[0004] To achieve the above purpose, the embodiments of this application adopt the following technical solutions:

[0005] In a first aspect, the embodiments of this application provide a method for processing promotion information, including:

[0006] Adjust a first request strategy for a trading platform to obtain a second request strategy, where the first request strategy includes: the request order for L trading platforms to deliver promotion information to the media platform, and the required resource amount for the media platform to display promotion information for each trading platform;

[0007] Based on the historical resource amounts provided by the L trading platforms to the media platform and the first request strategy, predict the total first resource amount obtained from the L trading platforms, and based on the historical resource amounts and the second request strategy, predict the total second resource amount obtained from the L trading platforms;

[0008] Based on the total first resource amount and the total second resource amount, determine a third request strategy;

[0009] Based on the third request strategy, request the L trading platforms to deliver promotion information to the media platform.

[0010] In a second aspect, the embodiments of this application provide a device for processing promotion information, including:

[0011] An adjustment unit for adjusting a first request policy for a trading platform to obtain a second request policy, where the first request policy includes: the request order for L trading platforms to place promotion information on the media platform, and the amount of demand resources required for the media platform to display promotion information for each trading platform;

[0012] A prediction unit for predicting a first total resource obtained from the L trading platforms based on the historical resource amounts provided by the L trading platforms to the media platform and the first request policy, and predicting a second total resource obtained from the L trading platforms based on the historical resource amounts and the second request policy;

[0013] A determination unit for determining a third request policy based on the first total resource and the second total resource;

[0014] A request unit for requesting the L trading platforms to place promotion information on the media platform based on the third request policy.

[0015] In a third aspect, an embodiment of the present application provides an electronic device, including: a processor; a memory for storing executable instructions of the processor; wherein, the processor is configured to execute the instructions to implement the promotion information processing method as described in the first aspect.

[0016] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, when the instructions in the storage medium are executed by a processor of an electronic device, enabling the electronic device to execute the promotion information processing method as described in the first aspect.

[0017] The above at least one technical solution adopted in the embodiments of the present application can achieve the following beneficial effects:

[0018] The request strategy in the waterfall flow mode is used to request multiple trading platforms to deliver promotional information to the media platform. In the request strategy, the request order for multiple trading platforms to deliver promotional information to the media platform and the demand resource quantity required by the media platform to display promotional information for each trading platform are configured, so as to improve the success rate of the media platform in displaying promotional information, thereby improving the information filling rate of the media platform and increasing the total amount of resources obtained by the media platform. On this basis, by adjusting the current first request strategy for the trading platform, a second request strategy is obtained, and based on the historical resource quantities provided by multiple trading platforms to the media platform, the total amount of resources that the media platform can obtain is predicted when requesting multiple trading platforms to deliver promotional information with the two request strategies respectively, which helps to accurately analyze the impact of the request order and the demand resource quantity of the media platform for each trading platform on the total amount of resources. Further, based on the total amount of resources predicted under the two request strategies, a third request strategy is determined, and based on the third request strategy, multiple trading platforms are requested to deliver promotional information to the media platform, which can maximize the amount of resources that the media platform can obtain while ensuring the success rate of displaying promotional information. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present application and form 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 of the present application. In the drawings:

[0020] Figure 1 It is a schematic diagram of a transaction process between a media platform and a trading platform provided by an embodiment of the present application;

[0021] Figure 2 It is a schematic diagram of a request strategy in the waterfall flow mode provided by an embodiment of the present application;

[0022] Figure 3 It is a schematic flowchart of a method for processing promotional information provided by an embodiment of the present application;

[0023] Figure 4 It is a schematic diagram of the reference resource quantity provided by a trading platform to historical users provided by an embodiment of the present application;

[0024] Figure 5 It is a schematic flowchart of a method for processing promotional information provided by another embodiment of the present application

[0025] Figure 6 It is a schematic flowchart of a method for requesting advertisements provided by an embodiment of the present application;

[0026] Figure 7 It is a structural block diagram of a device for processing promotional information provided by an embodiment of the present application;

[0027] Figure 8 A schematic structural diagram of an electronic device provided for an embodiment of the present application. Specific embodiments

[0028] To make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with specific embodiments of the present application and the corresponding drawings. Apparently, the described embodiments are only a part rather than all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the scope of protection of the present application.

[0029] The terms "first", "second", etc. in this specification and the claims are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein. In addition, the "and / or" in this specification and the claims means at least one of the connected objects, and the character " / " generally indicates an "or" relationship between the associated objects before and after.

[0030] Explanation of some concepts:

[0031] Promotion information monetization: It refers to the act of a media platform obtaining resources by displaying promotion information. In the context of advertising placement, promotion information monetization is also known as advertising monetization, which refers to the act of a media platform obtaining advertising revenue by displaying advertisements.

[0032] Media platform: It refers to the entity of promotion information monetization, that is, a platform with the need for promotion information monetization and specific information display functions, such as Internet websites, mobile application programs (Application, APP), etc. In the context of advertising placement, the media platform is also known as an advertising media or an advertising publisher, etc., such as local community websites, small game APPs, etc.

[0033] Information publisher: An enterprise or individual that needs to place promotion information. In the context of advertising placement, the information publisher is also known as an advertiser, that is, an enterprise or individual that needs to place Internet advertisements.

[0034] Trading platform: An intermediary between the information publisher and the media platform. The information publisher can place promotion information on the trading platform, and the trading platform will display this promotion information on the media platform, thereby obtaining resources from the information publisher and also providing resources to the media platform. In the context of advertising placement, the trading platform is also known as an advertising platform. The advertiser can place advertisements on the trading platform, and the trading platform will display these advertisements on the website or mobile APP of the media platform, thereby charging possible fees from the advertiser and paying fees to the media platform.

[0035] Information display position: It refers to the position on the web page or APP page where the media platform places promotional information for display, such as the splash screen information display position, the in-feed information display position, the pop-up window information display position, the banner information display position, the short video information display position, etc. In the context of advertising placement, the information display position is also referred to as an ad slot, which refers to the position on the web page or APP page where the media platform places advertisements, such as the splash screen ad slot, the in-feed ad slot, the pop-up window ad slot, the banner ad slot, the short video ad slot, etc.

[0036] Transaction platform access: It means that the media platform configures information display positions and access request trigger codes on the transaction platform, such as Android SDK, IOS SDK, JavaScript code, etc. The content configured on the transaction platform includes the specifications of the information display positions (such as the format, width, height, etc. of videos and pictures), the amount of resources that can be provided for promotional information, etc. In the context of advertising placement, transaction platform access is also referred to as ad access, which means that the media platform configures ad slots and access request trigger codes on the transaction platform.

[0037] Promotional information transaction: It refers to the transaction between the transaction platform and the media platform. That is, when a user accesses the web page or APP page provided by the media platform with information display positions configured, the access request trigger code will trigger the media platform to request the transaction platform to place promotional information; the transaction platform responds to the request and returns the promotional information that meets the configuration of the information display position to the media platform. For example, the amount of resources that the transaction platform can provide for placing promotional information is not less than the required demand resources for the media platform to display this promotional information, so as to display the promotional information on this information display position and obtain 1 resource for one display. This process can be referred to Figure 1 .. In the context of advertising placement, the promotional information transaction is also referred to as an ad transaction, which refers to the transaction between the transaction platform and the media platform. That is, when a user opens the web page or APP page provided by the media platform with ad slots configured, the access request trigger code will trigger the media platform to request the transaction platform to place an advertisement; the transaction platform responds to the request and returns the advertisement that meets the configuration of the ad slot to the media platform to display the advertisement on this ad slot and obtain the ad revenue for one display.

[0038] Cost Per Mille (CPM): In the context of advertising placement, after each advertisement display, the transaction platform needs to accumulate the advertising fees for this display to the media platform, that is, the single-display advertising revenue obtained by the media platform. Since the single-display advertising revenue is relatively low and may be different each time, we usually determine the CPM in the following way, that is Among them, COST is the total advertising revenue, and Impression is the corresponding number of displays.

[0039] Effective cost per mille (eCPM): Similar to CPM described above, but in this document, CPM focuses on the revenue that has already occurred (for example, if the revenue yesterday was 100 yuan and the number of impressions was 2000, then CPM = 50), while eCPM focuses on measuring the revenue level of the trading platform. (For example, if the media platform has obtained a total revenue of 1 million from this trading platform, corresponding to 10 million impressions, then eCPM = 100). It should be noted that eCPM has different definitions and calculation methods in various scenarios, and the above definition is only applicable in this document.

[0040] Ad fill rate: In the context of ad placement, it refers to the success rate of the media platform in displaying ads. When the media platform initiates an ad placement request to the trading platform, it may be due to various reasons that the trading platform does not return ads that may be displayed. For example, the floor price (i.e., the required resource quantity) set by the media platform for this ad slot is too high, resulting in the trading platform not having suitable ads to return, or communication failures caused by network latency, etc., and the media platform fails to obtain the ads returned by the trading platform in a timely manner.

[0041] This application studies the interaction process between existing media platforms and trading platforms and finds that since the display opportunity each time a user visits a page can only be allocated to one trading platform, if the Waterfall mode is adopted to enable the media platform to connect to multiple trading platforms, set one or more required resource quantities for each trading platform, and request the trading platform to place promotional information in a polling manner according to a certain order, the trading success rate (i.e., the success rate of the media platform in displaying promotional information) can be increased, which helps to increase the total amount of resources obtained by the media platform.

[0042] This application also studies the request strategies of different Waterfall modes and finds that since the resource quantities provided by different trading platforms for promotional information are different, and the resource quantities required by the media platform to display promotional information for different trading platforms are also different, and usually, the trading between the media platform and the trading platform can be successful only when the required resource quantity of the media platform is less than the resource quantity provided by the trading platform. Therefore, in the Waterfall mode, the total amount of resources obtained by the media platform will be affected by the request order of the media platform for multiple trading platforms and the required resource quantity of the media platform for each trading platform.

[0043] With Figure 2Taking the request strategies of the two waterfall flow modes shown as an example, when requesting multiple trading platforms to place promotional information according to the request order and required resource quantity indicated by request strategy 1, the total amount of resources obtained by the media platform is 101; when requesting multiple trading platforms to place promotional information according to the request order and resource requirement quantity indicated by request strategy 2, the total amount of resources obtained by each platform is 272, which is significantly greater than the total amount of resources obtained through request strategy 1. Secondly, when requesting trading platform 1 to place promotional information with a required resource quantity of 10, the number of successful requests among 10,000 promotional information placement requests is 5,000, while when requesting trading platform 1 to place promotional information with a required resource quantity of 20, the number of successful requests among 10,000 promotional information placement requests is only 2,000, that is, although a higher required resource quantity may bring higher resource returns, its transaction success rate is relatively lower; if the transaction fails, it is necessary to continue to request other trading platforms to place promotional information.

[0044] Based on this, the embodiment of the present application proposes a method for processing promotional information, which uses the request strategy of the waterfall flow mode to request multiple trading platforms to place promotional information on the media platform, and configures the request order for multiple trading platforms to place promotional information on the media platform and the required resource quantity for the media platform to display promotional information for each trading platform in the request strategy, so as to improve the success rate of the media platform in displaying promotional information, thereby improving the information filling rate of the media platform and increasing the total amount of resources obtained by the media platform; on this basis, by adjusting the current first request strategy for the trading platform, a second request strategy is obtained, and based on the historical resource quantity provided by multiple trading platforms to the media platform, it is predicted that the total amount of resources that the media platform can obtain when requesting multiple trading platforms to place promotional information according to the two request strategies respectively, which helps to accurately analyze the impact of the request order and the required resource quantity of the media platform for each trading platform on the total amount of resources; further, based on the predicted total amount of resources under the two request strategies, a third request strategy is determined, and based on the third request strategy, multiple trading platforms are requested to place promotional information on the media platform, which can maximize the amount of resources that the media platform can obtain while ensuring the success rate of displaying promotional information.

[0045] It should be understood that the method for processing promotional information provided by the embodiment of the present application can be executed by the media platform, specifically by the software deployed in the media platform.

[0046] The following will detail the technical solutions provided by each embodiment of the present application in conjunction with the accompanying drawings.

[0047] Please refer to Figure 3 , which is a schematic flowchart of a method for processing promotional information provided by an embodiment of the present application. The method includes the following steps:

[0048] S302. Adjust the first request policy for the trading platform to obtain a second request policy.

[0049] The first request policy refers to the request policy of the current waterfall flow mode adopted by the media platform. The first request policy includes: the request order for L trading platforms to deliver promotional information to the media platform, and the amount of demand resources required by the media platform to display promotional information for each trading platform, where L is an integer greater than 1. The first request policy can have various appropriate forms, and the embodiments of this application do not limit this. For the convenience of accurately analyzing the impact of the request order and the amount of demand resources of the media platform for each trading platform on the total amount of resources that the media platform can obtain, as an example, the first request policy can include L request parameters, and the L request parameters correspond one by one to the L trading platforms. The arrangement order of the L trading platforms is the same as the request order. Each request parameter includes the platform information of the corresponding trading platform and the amount of demand resources required for the corresponding trading platform to display promotional information. Among them, the platform information of the trading platform can, for example, include but is not limited to the name, identifier, address, etc. of the trading platform. For example, taking Figure 2 the request policy 1 shown as an example, it can include the following 4 request parameters arranged in sequence: (Trading Platform 1, 10), (Trading Platform 2, 9), (Trading Platform 3, 30), (Trading Platform 4, 4).

[0050] In practical applications, each request parameter can also be referred to as a waterfall step.

[0051] Secondly, before the above S302, it is necessary to connect the media platform to L trading platforms, and this connection operation can be implemented through the background management website of the media platform. For example, add the names, request addresses, request accounts and passwords, request timeout times, etc. of each trading platform in the background management website, and these configuration information will be saved in the database of the media platform for subsequent calls.

[0052] In addition, since after a transaction fails between the media platform and one of the trading platforms, it is necessary to request promotional information from the next trading platform, and each time a request is sent to the trading platform, it will take a certain amount of time. If the depth of the waterfall flow is too long, users need to wait for a long time to see the promotional information, which affects the user experience. Therefore, limit the depth of the waterfall flow, that is, limit the number of request parameters included in the first request policy.

[0053] To accurately analyze the impact of the request order and the amount of required resources of each trading platform by the media platform on the total amount of resources that the media platform can obtain, and to maximize the amount of resources that the media platform can obtain while ensuring the success rate of displaying promotional information, in the above S302, L request parameters are adjusted to obtain multiple second request strategies, and each second request strategy is obtained by adjusting one of the L request parameters.

[0054] Specifically, for each request parameter, at least one adjustment method can be used for adjustment. Taking the i-th request parameter as an example below, adjusting the i-th request parameter among the L request parameters includes at least one of the following methods:

[0055] Method 1: Exchange the i-th request parameter with the i + 1 request parameter to obtain a second request strategy.

[0056] For example, taking Figure 2 request strategy 1 as an example, exchange the 1st request parameter with the 2nd request parameter to obtain a second request strategy: (Trading Platform 2, 9), (Trading Platform 1, 10), (Trading Platform 3, 30), (Trading Platform 4, 4).

[0057] Method 2: Adjust the amount of required resources in the i-th request parameter, and use the adjusted amount of required resources to replace the original amount of required resources in the i-th request parameter to obtain a second request strategy.

[0058] Specifically in implementation, taking (A i , P i ) to represent the i-th request parameter, in Method 2, the new request parameter (A i , P i - ε) can be used to replace (A i , P i ) to obtain a second request strategy, and use the new request parameter (A i , P i + ε) to replace (A i , P i ) to obtain another second request strategy. Among them, A i represents the i-th trading platform, P i represents the amount of required resources for the media platform to display promotional information for the i-th trading platform, and ε represents a preset resource gradient, which can be adaptively adjusted according to the actual range of required resources.

[0059] For example, taking Figure 2Taking the request policy 1 shown as an example, assuming ε is 0.002, adjusting the required resource quantity in the first request parameter (trading platform 1, 10), two new request parameters (trading platform 1, 9.998) and (trading platform 1, 10.002) can be obtained; then, respectively replacing the first request parameter with the two new request parameters, the following two second request policies corresponding to this request parameter can be obtained:

[0060] Second request policy 1: (trading platform 1, 9.998), (trading platform 2, 9), (trading platform 3, 30), (trading platform 4, 4)

[0061] Second request policy 2: (trading platform 1, 10.002), (trading platform 2, 9), (trading platform 3, 30), (trading platform 4, 4)

[0062] Method 3: Adjust the required resource quantity in the i-th request parameter, generate a new request parameter based on the adjusted required resource quantity and the platform information in the i-th request parameter, and insert the new request parameter before or after the i-th request parameter to obtain the second request policy.

[0063] Specifically, when implementing, using (A i , P i ) to represent the i-th request parameter, in Method 3, the new request parameter (A i , P i - ε) can be inserted between the i-th request parameter (A i , P i ) and the (i - 1)-th request parameter (A i-1 , P i-1 ) to obtain a second request policy, and the new request parameter (A i , P i + ε) can be inserted between the i-th request parameter (A i , P i ) and the (i + 1)-th request parameter (A i+1 , P i+1 ) to obtain another second request policy corresponding to this request parameter. Among them, A i represents the i-th trading platform, P i represents the required resource quantity for the media platform to display push information for the i-th trading platform, and ε represents the preset resource quantity gradient, which can be adaptively adjusted according to the actual required resource quantity range.

[0064] For example, taking Figure 2Taking the request policy 1 shown as an example, assuming ε is 0.002, adjusting the required resource quantity in the first request parameter (trading platform 1, 10) can obtain two new request parameters (trading platform 1, 9.998) and (trading platform 1, 10.002); then, inserting the new request parameter (trading platform 1, 9.998) before the first request parameter and inserting the new request parameter (trading platform 1, 10.002) between the first request parameter and the second request parameter can obtain the following two second request policies corresponding to this request parameter:

[0065] Second request policy 1: (trading platform 1, 9.998), (trading platform 1, 10), (trading platform 2, 9), (trading platform 3, 30), (trading platform 4, 4)

[0066] Second request policy 2: (trading platform 1, 10), (trading platform 1, 10.002), (trading platform 2, 9), (trading platform 3, 30), (trading platform 4, 4)

[0067] Method 4: Delete the i-th request parameter from the first request policy to obtain the second request policy.

[0068] For example, taking Figure 2 the request policy 1 as an example, deleting the first request parameter can obtain a second request policy: (trading platform 2, 9), (trading platform 3, 30), (trading platform 4, 4).

[0069] In practical applications, partial request parameters among the L request parameters can be adjusted, such as only adjusting one request parameter. Or, all the request parameters among the L request parameters can also be adjusted, and only one request parameter is adjusted each time to obtain the corresponding second request policy. In the case of adjusting at least two request parameters, or in the case of adjusting one request parameter using at least two adjustment methods, T second request policies can be obtained, where T is an integer greater than 1.

[0070] In another embodiment of the present application, for the above method 3, considering that adding new request parameters to the first request policy will increase the depth of the waterfall flow, which may lead to the problem of waterfall flow inflation. For example, assuming that the first request policy contains 10 request parameters, then in the worst case, it may take 10 requests to display the promotion information for the user; if each request takes 100 milliseconds, then the user needs to wait for 1 second to see the promotion information, affecting the user experience. Therefore, in the case of the above method 3, the length of the second request policy is restricted by setting a quantity threshold.

[0071] Specifically, for the above-mentioned method 3, obtain the number of request parameters included in the first request strategy; if the number is less than the preset number, adjust the required resource amount in the i-th request parameter, and generate a new request parameter based on the adjusted required resource amount and the platform information in the i-th request parameter; if the number is greater than or equal to the preset number, do not adopt the above-mentioned method 3.

[0072] S304. Based on the historical resource amounts provided by the L trading platforms to the media platform and the first request strategy, predict the total amount of the first resources obtained from the L trading platforms.

[0073] The total amount of the first resources refers to the total amount of resources that the media platform can obtain when the media platform requests promotion information from the L trading platforms according to the request order and the required resource amounts indicated by the first request strategy.

[0074] In an embodiment, the above S304 may include the following steps: S341. Based on the request order indicated by the first request strategy, compare the historical resource amount provided by each trading platform with the required resource amount for the media platform to display promotion information for each trading platform, and obtain a first comparison result; S342. Based on the first comparison result, predict the total amount of the first resources obtained from the L trading platforms.

[0075] Since usually the trading between the media platform and the trading platform can succeed only when the required resource amount of the media platform is less than or equal to the resource amount provided by the trading platform, through this embodiment, the total amount of the first resources can be accurately predicted, providing reliable data support for subsequent intelligent decision-making of the optimal request strategy, so as to maximize the resource amount that the media platform can obtain while ensuring the success rate of displaying promotion information.

[0076] Considering that different visiting users of the media platform have different values for different trading platforms, when the same user accesses the media platform and triggers a request to the trading platform to place promotion information, the resource amounts provided by different trading platforms are different. For example, for a trading platform that prefers to promote through short video information booths, young users who often browse short videos on mobile phones are more valuable than other users, so the trading platform provides a higher resource amount for such users; for a trading platform that prefers to promote through banner ad spaces, middle-aged users who like to browse news are more valuable than other users, so the trading platform provides a higher resource amount for such users.

[0077] Based on this, in order to accurately predict the total amount of the first resource, as an example, in the above S341, the consideration of the preferences and resource quantity differences of the historical users of the media platform by each trading platform is introduced. Specifically, the historical resource quantity provided by each trading platform includes the reference resource quantity provided by each trading platform for N historical users, and the N historical users include the users who accessed the media platform within the specified historical period. Among them, the specified historical period can be selected according to actual needs, such as the last 2 days. The reference resource quantity provided by the trading platform for historical users refers to the resource quantity provided by the trading platform when the historical user accesses the media platform and triggers the media platform to request the trading platform to place promotional information. The reference resource quantity provided by the trading platform for historical users can reflect the value of historical users to the trading platform.

[0078] Correspondingly, the above S341 may include the following steps:

[0079] Step A1, for each historical user, traverse L trading platforms in the order of requests, compare the reference resource quantity provided by the current trading platform for the historical user with the required resource quantity for the media platform to display promotional information for the current trading platform, and obtain the first comparison result.

[0080] Step A2, if the first comparison result does not meet the preset stop condition, continue to perform the above traversal operation until the obtained first comparison result meets the preset stop condition.

[0081] Among them, the preset stop condition includes: the reference resource quantity provided by the current trading platform for the historical user is not less than the required resource quantity for the media platform to display promotional information for the current trading platform.

[0082] For example, taking the historical user u as an example, traverse L trading platforms in the order of requests indicated by the first request strategy. If the current traversal reaches the i-th trading platform, the reference resource quantity of the i-th trading platform for the historical user u is denoted as B(A i , u), and the required resource quantity for the media platform to display promotional information for the i-th trading platform is denoted as P i .

[0083] If B(A i , u) ≥ P i , it can be estimated that the resource quantity provided by the future i-th trading platform for the historical user u will be higher than the required resource quantity of the media platform for the i-th trading platform. Furthermore, it can be predicted that in terms of the information display opportunity when the historical user u accesses the media, the future media platform and the i-th trading platform will succeed in the transaction. At this time, stop traversing the next trading platform and continue to perform the above operation on the next historical user.

[0084] If B(A i , u) < Pi , it can be estimated that the amount of resources provided by the i-th trading platform to the historical user u in the future will be lower than the required resource amount of the media platform for the i-th trading platform. Furthermore, it can be predicted that, in terms of the information display opportunity when the historical user u accesses the media, a transaction failure will occur between the future media platform and the i-th trading platform. At this time, continue to traverse the next trading platform and repeat the above operations.

[0085] In this method, since the media platform can obtain resources from the trading platform only when the transaction is successful, by performing the above traversal operation for each historical user, it can accurately predict the trading platform that can successfully transact with the media platform when each historical user accesses the media platform, providing reliable data support for accurately predicting the total amount of the first resources subsequently.

[0086] Correspondingly, the above S342 may include the following steps:

[0087] Step B1, for each historical user, during the process of traversing L trading platforms, if the first comparison result corresponding to the current trading platform meets the preset stop condition, then determine the current trading platform as the target trading platform corresponding to the historical user.

[0088] Step B2, determine the reference resource amount provided by the target trading platform to the historical user as the first resource component brought by the historical user to the media platform.

[0089] Step B3, calculate the sum of the first resource components brought by N historical users to the media platform to obtain the total amount of the first resources.

[0090] For example, continue to use the above example. Taking the historical user u as an example, during the process of traversing L trading platforms, if the current traversed trading platform is the i-th trading platform, and B(A i , u) ≥ P i , since it is predicted that, in terms of the information display opportunity when the historical user u accesses the media, a transaction will be successful between the future media platform and the i-th trading platform, then determine the i-th trading platform as the target trading platform corresponding to the historical user u. At this time, the first resource component g u = B(A i , u) brought by the historical user u to the media platform. Further, determine the sum of the first resource components brought by N histories to the media platform as the total amount of the first resources.

[0091] When predicting the total amount of the first resource, this method takes into account the preferences and resource quantity differences of the historical users of each trading platform for the media platform, and exceeds the ordinary historical average evaluation method in terms of accuracy. At the same time, it does not rely on detailed feature data and does not require the media platform to have a large amount of user portrait data, so it has advantages over common machine learning and deep learning models in terms of practicability and generality. Secondly, this method also utilizes the law of large numbers, that is, when the user sample is large enough, the prediction result of the total amount of the first resource is close enough to the truth. Taking N historical users who accessed the media platform within a specified historical period as samples, and using the reference resource quantity provided by each trading platform for the N historical users, comparing it with the required resource quantity for the media platform to display promotion information for each trading platform, to predict the resources brought by each historical user to the media platform, and then the obtained total amount of the first resource is close enough to the actual situation.

[0092] In the embodiments of the present application, for each historical user, the reference resource quantity provided by each trading platform for this historical user can be obtained through various methods, and specific selection can be made according to actual needs. The embodiments of the present application do not limit this.

[0093] In an implementation manner, in order to ensure the accuracy of the obtained reference resource quantity and provide reliable data support for subsequent finding of the optimal request strategy, a trading experiment can be conducted on the N historical users for several days, collecting the resource quantity provided by L trading platforms for the N historical users, and using the collection results to evaluate the resource quantity provided by each trading platform for each historical user.

[0094] The reference resource quantity provided by each trading platform for each historical user is obtained through the following method:

[0095] Step C1, for each historical user, listen to the access request of this historical user to the media platform within the specified target period.

[0096] The duration of the specified target period is equal to the duration of the specified historical period. For example, if the specified period is D days before the current time, then the specified target period is D days after the current time.

[0097] Step C2, if the access request of this historical user to the media platform is listened to, request L trading platforms to put promotion information on the media platform, and receive the response information of the L trading platforms for the historical user. The response information returned by each trading platform includes the resource quantity indicated to be provided by the trading platform.

[0098] Step C3, for each trading platform, based on the number of response information of the trading platform for the historical user and the resource quantity indicated in each response information, determine the reference resource quantity of the trading platform for this historical user.

[0099] For example, taking the historical user u as an example, within the specified target time period, each time a request from the historical user u to access the media platform is monitored, without limiting the required resources from each trading platform, randomly initiate transactions with L trading platforms, and record the response information of each trading platform to the historical user u, and extract the amount of resources provided by each trading platform to the historical user u from it.

[0100] Taking the trading platform a as an example, the amount of resources provided by the trading platform a to the historical user u is denoted as B(a, u). If there are multiple response messages from the trading platform a to the historical user u, then calculate the ratio between the sum of the amount of resources provided by the trading platform a to the historical user u and the number of response messages as the reference amount of resources provided by the trading platform a to the historical user. Thus, the reference amount of resources provided by each trading platform to each historical user is obtained. Figure 4 An example of the amount of resources provided by L trading platforms to N historical users is shown.

[0101] In practical applications, historical users can be identified in various ways. For example, if the media platform is a mobile APP, the device identifier of the device used by the historical user to access the media platform is used to identify the historical user; if the media platform is a website, the Cookie used by the historical user to access the media platform is used to identify the historical user.

[0102] This embodiment of the present application shows an implementation manner of the above S304 here. Of course, it should be understood that the above S304 can also be implemented in other ways, such as through a pre-trained machine learning model for prediction, etc., and this embodiment of the present application does not limit this.

[0103] S306, based on the historical resource amounts provided by L trading platforms to the media platform and the second request strategy, predict the total amount of second resources obtained from the L trading platforms.

[0104] The total amount of second resources refers to the total amount of resources that the media platform can obtain under the request that the media platform requests promotion information from the L trading platforms according to the request order and required resource amounts indicated by the second request strategy.

[0105] The specific implementation manner of the above S306 is similar to the specific implementation manner of the above S304 and will not be elaborated here. It is worth noting that in the case where the number of second request strategies is multiple, the above S306 can be executed for each second request strategy to obtain the total amount of second resources corresponding to this second request strategy.

[0106] S308, based on the total amount of first resources and the total amount of second resources, determine the third request strategy.

[0107] The third request strategy refers to the strategy finally used to request the L trading platforms to place promotion information.

[0108] In one embodiment, in order to quickly find the most suitable third request policy to maximize the amount of resources that the media platform can obtain while ensuring the success rate of displaying promotional information, the hill climbing algorithm can be used for optimization. As Figure 5 shown, the specific steps are as follows:

[0109] Compare the first total amount of resources with the second total amount of resources;

[0110] If the first total amount of resources is not less than the second total amount of resources, then use the first request policy as the third request policy;

[0111] If the first total amount of resources is less than the second total amount of resources, then use the second request policy as the new first request policy, and repeat the above steps from S302 to using the second request policy as the new first request policy until the obtained first total amount of resources is not less than the second total amount of resources or the number of repetitions reaches the preset number of times and stop, and use the latest first request policy as the third request policy.

[0112] In practical applications, considering that the number of second request policies may be multiple, and each second request policy has a corresponding second total amount of resources. In this case, to improve the optimization efficiency, the above comparison of the first total amount of resources with the second total amount of resources includes: selecting the maximum second total amount of resources from the second total amounts of resources corresponding to T second request policies; comparing the first total amount of resources with the maximum second total amount of resources, where T represents the total number of second request policies, and T is an integer greater than 1. Correspondingly, if the first total amount of resources is less than the second total amount of resources, then using the second request policy as the new first request policy includes: if the first total amount of resources is less than the maximum second total amount of resources, then use the second request policy corresponding to the maximum second total amount of resources as the new first request policy.

[0113] As an example, the first request policy is denoted as π0 = (A, P), where A represents the set of trading platforms, which contains L trading platforms, and P represents the set of required resource amounts, which represents the required resource amounts for displaying promotional information on L trading platforms. Adjust the first request policy through the above S302 to obtain T second request policies π'; predict the first total amount of resources as G(π0) through the above S304; predict the second total amount of resources corresponding to each second request policy as G(π'), and select the maximum second total amount of resources G(π max ); if G(π0) ≥ G(π max ), then use the first request policy π0 as the third request policy If G(π0) < G(π max ), then use the second request policy π corresponding to the maximum second total amount of resources maxAs a new first request strategy, repeat the above process until the total amount of the first resources obtained is not less than the total amount of the second resources or the number of repetitions C reaches the preset number K, and use the latest first request strategy as the third request strategy.

[0114] In this embodiment, the hill climbing algorithm can automatically find the most suitable third request strategy, which does not depend on human experience, saving manpower and better improving the total amount of resources obtained by the media platform.

[0115] This application embodiment shows an implementation manner of the above S308 here. Of course, it should be understood that the above S308 can also be implemented in other ways, such as the Monte Carlo algorithm, etc. This application embodiment does not limit this.

[0116] S310, based on the third request strategy, request L trading platforms to put promotion information on the media platform.

[0117] Specifically, each time a user access request to the media platform is monitored, request promotion information from the L trading platforms one by one according to the request order indicated by the third request strategy. If the currently requested trading platform does not return a response message, continue to request promotion information from the next trading platform; if the currently requested trading platform returns a response message and the response message indicates that the provided resource amount is not less than the required resource amount for displaying promotion information for this trading platform, then display promotion information for this trading platform and continue to monitor the user's access request to the media platform.

[0118] The promotion information processing method provided by one or more embodiments of this application uses a request strategy in a waterfall flow mode to request multiple trading platforms to put promotion information on the media platform, configures the request order for requesting multiple trading platforms to put promotion information on the media platform and the required resource amount for the media platform to display promotion information for each trading platform in the request strategy, so as to improve the success rate of the media platform in displaying promotion information, and then improve the information filling rate of the media platform and increase the total amount of resources obtained by the media platform; on this basis, by adjusting the current first request strategy for the trading platform, a second request strategy is obtained, and based on the historical resource amounts provided by multiple trading platforms to the media platform, predict the total amount of resources that the media platform can obtain when requesting multiple trading platforms to put promotion information with the two request strategies respectively, which helps to accurately analyze the impact of the request order and the required resource amount of the media platform for each trading platform on the total amount of resources; further, based on the predicted total amount of resources under the two request strategies, determine the third request strategy, and based on the third request strategy, request multiple trading platforms to put promotion information on the media platform, which can maximize the amount of resources that the media platform can obtain while ensuring the success rate of displaying promotion information.

[0119] The promotion information processing method provided by the embodiments of this application can be applied to various promotion information delivery scenarios, and the embodiments of this application do not limit this. The following combines Figure 6 , taking advertising as an example of promotion information, to illustrate the promotion information processing method provided by the embodiments of this application.

[0120] In this scenario, the amount of demand resources required by the media platform to display promotion information for the trading platform is the floor price of the media platform for the trading platform, the amount of resources provided by the trading platform for the media platform is the bid price of the trading platform for the media platform, and the total amount of resources obtained by the media platform is the advertising monetization revenue of the media platform.

[0121] First, the business personnel of the media platform configure the platform information (such as name, request address, request account and password, request timeout time, etc.) of L trading platforms through the background management website of the media platform and store it in the platform database, and connect the media platform to L trading platforms.

[0122] Then, the media platform collects the historical users who visited in the recent D days to obtain the user set U. The user set U includes N historical users, and N is an integer greater than 1. The media platform conducts a D-day trading experiment on the user set U, which specifically includes: the media platform monitors the access requests of the historical users in the user set U within D days; for each historical user, when the access request of this historical user is monitored, in a way that does not limit the floor price, requests L trading platforms to deliver promotion information to the media platform, and receives the response information of L trading platforms for this historical user. The response information returned by each trading platform includes the bid price of this trading platform for this historical user; for each trading platform, based on the number of response information of this trading platform for this historical user and the bid price indicated in each response information, the media platform determines the reference bid price of this trading platform for this historical user and stores it in the price database.

[0123] Next, the media platform adjusts the currently adopted first request strategy to obtain a second request strategy; based on the reference bid prices provided by L trading platforms to N historical users and the first request strategy, predicts the first advertising monetization revenue obtained from L trading platforms, and based on the reference bid prices provided by L trading platforms to N historical users and the second request strategy, predicts the second advertising monetization revenue obtained from L trading platforms; based on the first advertising monetization revenue and the second advertising monetization revenue, determines a third request strategy and stores the third request strategy in the strategy database.

[0124] Finally, the media platform requests L trading platforms to place advertisements based on the third request strategy. Specifically, when the media platform monitors an access request from a user to a page with an ad slot, it requests each of the L trading platforms to place an advertisement according to the third request strategy. If the currently requested trading platform does not return a response message, it determines that the transaction fails and continues to request the next trading platform to place promotional information. If the currently requested trading platform returns a response message and the bid indicated by the response message is not less than the floor price of the media platform for that trading platform, it determines that the transaction is successful, displays the promotional information for that trading platform, and continues to monitor the user's access requests to pages with ad slots.

[0125] Through the promotional information processing method provided in the embodiments of the present application, the media platform uses a waterfall flow mode request strategy to request multiple trading platforms to place advertisements. By configuring the request order for requesting multiple trading platforms to place advertisements and the floor price of the media platform for each trading platform in the request strategy, the success rate of the media platform in displaying advertisements can be improved, thereby improving the ad fill rate of the media platform and increasing the ad monetization revenue obtained by the media platform. On this basis, by adjusting the current first request strategy of the media platform, a second request strategy is obtained, and based on the historical bids of multiple trading platforms, it is predicted that the media platform can obtain ad monetization revenue when requesting multiple trading platforms to place advertisements under the two request strategies, which helps to accurately analyze the impact of the request order and the floor price of the media platform for each transaction on the ad monetization revenue. Further, based on the predicted ad monetization revenue under the two request strategies, a third request strategy is determined, and based on the third request strategy, multiple trading platforms are requested to place advertisements on the media platform, which can maximize the ad monetization revenue of the media platform while maintaining the ad fill rate.

[0126] The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired results. Additionally, the processes depicted in the figures do not necessarily require the specific order or sequential order shown to achieve the desired result. In certain implementations, multitasking and parallel processing are also possible or may be advantageous.

[0127] Based on the same inventive concept, the embodiments of the present application also provide a promotional information processing device. Please refer to Figure 7 FIG. 700 is a structural block diagram of a promotional information processing device 700 provided in an embodiment of the present application. The device 700 includes: an adjustment unit 710, a prediction unit 720, a determination unit 730, and a request unit 740.

[0128] An adjustment unit 710, configured to adjust a first request policy for a trading platform to obtain a second request policy, where the first request policy includes: a request order for requesting L trading platforms to place promotion information on a media platform, and the amount of required resources for the media platform to display promotion information for each trading platform.

[0129] A prediction unit 720, configured to predict a first total amount of resources obtained from the L trading platforms based on the historical amount of resources provided by the L trading platforms to the media platform and the first request policy, and predict a second total amount of resources obtained from the L trading platforms based on the historical amount of resources and the second request policy.

[0130] A determination unit 730, configured to determine a third request policy based on the first total amount of resources and the second total amount of resources.

[0131] A request unit 740, configured to request the L trading platforms to place promotion information on the media platform based on the third request policy.

[0132] In an embodiment, the first request policy includes L request parameters, the L request parameters correspond to the L trading platforms one by one, the arrangement order of the L request parameters is the same as the request order, and each request parameter includes the platform information of the corresponding trading platform and the amount of required resources for the media platform to display promotion information for the corresponding trading platform;

[0133] The adjustment unit is specifically configured to:

[0134] Adjust the L request parameters to obtain multiple second request policies, and each second request policy is obtained by adjusting one of the L request parameters.

[0135] In an embodiment, adjusting the i-th request parameter among the L request parameters includes at least one of the following methods:

[0136] Exchange the i-th request parameter with the (i + 1)-th request parameter to obtain a second request policy;

[0137] Adjust the amount of required resources in the i-th request parameter, and use the adjusted amount of required resources to replace the original amount of required resources in the i-th request parameter to obtain a second request policy;

[0138] Adjust the amount of required resources in the i-th request parameter, generate a new request parameter based on the adjusted amount of required resources and the platform information in the i-th request parameter, and insert the new request parameter before or after the (i + 1)-th request parameter to obtain a second request policy;

[0139] Delete the \(i\)th request parameter from the first request policy to obtain a second request policy.

[0140] In one embodiment, adjusting the required resource amount in the \(i\)th request parameter and generating a new request parameter based on the adjusted required resource amount and the platform information in the \(i\)th request parameter includes:

[0141] Obtain the number of request parameters included in the first request policy;

[0142] If the number is less than a preset number, adjust the required resource amount in the \(i\)th request parameter and generate a new request parameter based on the adjusted required resource amount and the platform information in the \(i\)th request parameter.

[0143] In one embodiment, the prediction unit predicts the total amount of the first resources in the following manner:

[0144] Based on the request order indicated by the first request policy, compare the historical resource amounts provided by each trading platform with the required resource amounts required by the media platform to display promotion information for each trading platform to obtain a first comparison result;

[0145] Based on the first comparison result, predict the total amount of the first resources obtained from the \(L\) trading platforms.

[0146] In one embodiment, the historical resource amounts provided by each trading platform include the reference resource amounts provided by each trading platform to \(N\) historical users, and the \(N\) historical users include users who have accessed the media platform within a specified historical period;

[0147] The prediction unit obtains the first comparison result in the following manner:

[0148] For each historical user, traverse the \(L\) trading platforms in the request order, compare the reference resource amount provided by the current trading platform to the historical user with the required resource amount required by the media platform to display promotion information for the current trading platform to obtain a first comparison result corresponding to the current trading platform;

[0149] If the first comparison result corresponding to the current trading platform does not meet the preset stop condition, continue to perform the above traversal operation until the obtained first comparison result meets the preset stop condition;

[0150] Wherein, the preset stop condition includes: the reference resource amount provided by the current trading platform to the historical user is not less than the required resource amount required by the media platform to display promotion information for the current trading platform.

[0151] In one embodiment, when predicting the total amount of the first resources obtained from the L trading platforms based on the first comparison result, the prediction unit performs the following steps:

[0152] For each historical user, during the process of traversing the L trading platforms, if the first comparison result corresponding to the current trading platform meets the preset stop condition, the current trading platform is determined as the target trading platform corresponding to the historical user;

[0153] The reference resource amount provided by the target trading platform to the historical user is determined as the first resource component brought by the historical user to the media platform;

[0154] Calculate the sum of the first resource components brought by the N historical users to the media platform to obtain the total amount of the first resources.

[0155] In one embodiment, the reference resource amount provided by each trading platform for each historical user is obtained through the following method:

[0156] For each historical user, monitor the access requests of the historical user to the media platform within the specified target time period, and the duration of the specified target time period is equal to the duration of the specified historical time period;

[0157] If the access request is monitored, request the L trading platforms to deliver promotion information to the media platform, and receive the response information of the L trading platforms for the historical user. The response information returned by each trading platform includes the resource amount indicated by the trading platform to provide;

[0158] For each trading platform, based on the number of response information of the trading platform for the historical user and the resource amount indicated in each response information, determine the reference resource amount of the trading platform for the historical user.

[0159] In one embodiment, the determining unit is specifically configured to:

[0160] Compare the total amount of the first resources with the total amount of the second resources;

[0161] If the total amount of the first resources is not less than the total amount of the second resources, use the first request strategy as the third request strategy;

[0162] If the total amount of the first resources is less than the total amount of the second resources, then use the second request policy as the new first request policy, and repeatedly execute the step of adjusting the new first request policy until the second request policy is used as the new first request policy, until the obtained total amount of the first resources is not less than the total amount of the second resources or the number of repeated executions reaches the preset number of times and then stop, and use the latest first request policy as the third request policy.

[0163] In one embodiment, the number of the second request policies is T, where T is an integer greater than 1, and each second request policy has a corresponding total amount of the second resources;

[0164] When the determining unit compares the total amount of the first resources with the total amount of the second resources, the following steps are executed:

[0165] Select the maximum total amount of the second resources from the total amounts of the second resources corresponding to the T second request policies;

[0166] Compare the total amount of the first resources with the maximum total amount of the second resources;

[0167] When the determining unit uses the second request policy as the new first request policy, the following steps are executed:

[0168] If the total amount of the first resources is less than the maximum total amount of the second resources, then use the second request policy corresponding to the maximum total amount of the second resources as the new first request policy.

[0169] Obviously, the promotion information processing device provided by the embodiments of the present application can be used as the execution subject of the above Figure 1 shown promotion information processing method, and thus can implement the functions realized by the promotion information processing device in Figure 1 Since the principle is the same, it will not be elaborated here.

[0170] Figure 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application. Please refer to Figure 8 , at the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. Among them, the memory may include a memory, such as a high-speed random access memory (Random-Access Memory, RAM), and may also include a non-volatile memory, such as at least one disk memory, etc. Of course, the electronic device may also include other hardware required for other services.

[0171] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 only a bidirectional arrow is used in

[0172] Memory, used to store programs. Specifically, the program can include program code, and the program code includes computer operation instructions. The memory can include a memory and a non-volatile memory, and provide instructions and data to the processor.

[0173] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a promotion information processing device at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0174] Adjust the first request policy for the trading platform to obtain a second request policy. The first request policy includes: the request order for L trading platforms to place promotion information on the media platform, and the amount of required resources for the media platform to display promotion information for each trading platform;

[0175] Based on the historical resource amounts provided by the L trading platforms to the media platform and the first request policy, predict the total first resource amount obtained from the L trading platforms, and based on the historical resource amounts and the second request policy, predict the total second resource amount obtained from the L trading platforms;

[0176] Based on the total first resource amount and the total second resource amount, determine a third request policy;

[0177] Based on the third request policy, request the L trading platforms to place promotion information on the media platform.

[0178] The above as in this application Figure 1The method executed by the promotion information processing device disclosed in the illustrated embodiment can be applied to or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit in the hardware of the processor or the instructions in the form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by the combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method.

[0179] The electronic device can also execute Figure 1 the method and implement the functions of the promotion information processing device in Figures 1 to 6 the illustrated embodiment, which will not be elaborated in the embodiments of the present application.

[0180] Of course, in addition to the software implementation method, the electronic device of the present application does not exclude other implementation methods, such as the logical device or the combination of software and hardware, etc. That is to say, the execution subject of the following processing flow is not limited to each logical unit, and can also be hardware or a logical device.

[0181] The embodiments of the present application also propose a computer-readable storage medium. The computer-readable storage medium stores one or more programs. The one or more programs include instructions. When the instructions are executed by a portable electronic device including a plurality of application programs, the portable electronic device can be enabled to execute Figure 1 the method in the illustrated embodiment and specifically used to perform the following operations:

[0182] Adjust the first request policy for the trading platform to obtain a second request policy. The first request policy includes: the request order for L trading platforms to place promotion information on the media platform, and the amount of required resources for the media platform to display promotion information for each trading platform.

[0183] Based on the historical resource amounts provided by the L trading platforms to the media platform and the first request policy, predict the total first resource amount obtained from the L trading platforms, and based on the historical resource amounts and the second request policy, predict the total second resource amount obtained from the L trading platforms.

[0184] Based on the total first resource amount and the total second resource amount, determine a third request policy.

[0185] Based on the third request policy, request the L trading platforms to place promotion information on the media platform.

[0186] In summary, the above are only the preferred embodiments of the present application and are not used to limit the protection scope of the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0187] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0188] A computer-readable medium includes both permanent and non-permanent, removable and non-removable media that can implement information storage by any method or technology. The 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 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 technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information accessible by a computing device. As defined herein, a computer-readable medium does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0189] It should also be noted that the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0190] Each embodiment in this specification is described in a progressive manner, and the same or similar parts among the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiments.

Claims

1. A promotion information processing method, characterized in that Including: Adjusting a first request policy for a trading platform to obtain a second request policy, where the first request policy includes: the request order for requesting L trading platforms to place promotion information on a media platform, and the amount of required resources for the media platform to display promotion information for each trading platform; Predicting a first total resource obtained from the L trading platforms based on the historical resource amounts provided by the L trading platforms to the media platform and the first request policy, and predicting a second total resource obtained from the L trading platforms based on the historical resource amounts and the second request policy; Determining a third request policy based on the first total resource and the second total resource; Requesting the L trading platforms to place promotion information on the media platform based on the third request policy.

2. The method according to claim 1, wherein The first request policy includes L request parameters, which correspond one-to-one with the L trading platforms. The arrangement order of the L request parameters is the same as the request order. Each request parameter includes the platform information of the corresponding trading platform and the amount of required resources for the media platform to display promotion information for the corresponding trading platform; The adjusting the first request policy for the trading platform to obtain a second request policy includes: Adjusting the L request parameters to obtain multiple second request policies, and each second request policy is obtained by adjusting one of the L request parameters.

3. The method according to claim 2, wherein Adjusting the i-th request parameter among the L request parameters includes at least one of the following methods: Exchanging the i-th request parameter with the (i + 1)-th request parameter to obtain a second request policy; Adjusting the amount of required resources in the i-th request parameter, and replacing the original amount of required resources in the i-th request parameter with the adjusted amount of required resources to obtain a second request policy; Adjusting the amount of required resources in the i-th request parameter, generating a new request parameter based on the adjusted amount of required resources and the platform information in the i-th request parameter, and inserting the new request parameter before or after the (i + 1)-th request parameter to obtain a second request policy; Deleting the i-th request parameter from the first request policy to obtain a second request policy.

4. The method according to claim 3, wherein The adjusting the amount of required resources in the i-th request parameter and generating a new request parameter based on the adjusted amount of required resources and the platform information in the i-th request parameter includes: Obtaining the number of request parameters included in the first request policy; If the number is less than a preset number, adjusting the amount of required resources in the i-th request parameter and generating a new request parameter based on the adjusted amount of required resources and the platform information in the i-th request parameter.

5. The method according to claim 1, wherein The predicting a first total resource obtained from the L trading platforms based on the historical resource amounts provided by the L trading platforms to the media platform and the first request policy includes: Based on the request order indicated by the first request policy, compare the historical resource amounts provided by each trading platform with the required resource amounts for the media platform to display promotion information for each trading platform, and obtain a first comparison result; Based on the first comparison result, predict the total first resource amount obtained from the L trading platforms.

6. The method according to claim 5, wherein The historical resource amount provided by each trading platform includes the reference resource amounts provided by each trading platform to N historical users, and the N historical users include users who accessed the media platform during a specified historical period; The step of comparing the historical resource amounts provided by each trading platform with the required resource amounts for the media platform to display promotion information for each trading platform based on the request order indicated by the first request policy, and obtaining a first comparison result includes: For each historical user, traverse the L trading platforms in the request order, compare the reference resource amount provided by the current trading platform to the historical user with the required resource amount for the media platform to display promotion information for the current trading platform, and obtain the first comparison result corresponding to the current trading platform; If the first comparison result corresponding to the current trading platform does not meet the preset stop condition, continue to perform the above traversal operation until the obtained first comparison result meets the preset stop condition; Wherein, the preset stop condition includes: the reference resource amount provided by the current trading platform to the historical user is not less than the required resource amount for the media platform to display promotion information for the current trading platform.

7. The method according to claim 6, characterized in that, The step of predicting the total first resource amount obtained from the L trading platforms based on the first comparison result includes: For each historical user, during the process of traversing the L trading platforms, if the first comparison result corresponding to the current trading platform meets the preset stop condition, determine the current trading platform as the target trading platform corresponding to the historical user; Determine the reference resource amount provided by the target trading platform to the historical user as the first resource component brought by the historical user to the media platform; Calculate the sum of the first resource components brought by the N historical users to the media platform to obtain the total first resource amount.

8. The method according to claim 6, wherein The reference resource amount provided by each trading platform to each historical user is obtained through the following method: For each historical user, listen for the access request of the historical user to the media platform within a specified target period, and the duration of the specified target period is equal to the duration of the specified historical period; If the access request is monitored, request the L trading platforms to deliver promotion information to the media platform, and receive the response information of the L trading platforms for the historical user. The response information returned by each trading platform includes the resource amount indicated by the trading platform to provide; For each trading platform, based on the number of response information of the trading platform for the historical user and the resource amount indicated in each response information, determine the reference resource amount of the trading platform for the historical user.

9. The method according to claim 1, wherein Determining a third request policy based on the first total amount of resources and the second total amount of resources includes: Comparing the first total amount of resources with the second total amount of resources; If the first total amount of resources is not less than the second total amount of resources, using the first request policy as the third request policy; If the first total amount of resources is less than the second total amount of resources, using the second request policy as the new first request policy, and repeatedly executing the step of adjusting the new first request policy until the second request policy is used as the new first request policy, until the obtained first total amount of resources is not less than the second total amount of resources or the number of repeated executions reaches a preset number and then stops, and using the latest first request policy as the third request policy.

10. The method according to claim 9, wherein The number of the second request policies is T, where T is an integer greater than 1, and each second request policy has a corresponding second total amount of resources; The comparing the first total amount of resources with the second total amount of resources includes: Selecting the maximum second total amount of resources from the second total amounts of resources corresponding to the T second request policies; Comparing the first total amount of resources with the maximum second total amount of resources; The if the first total amount of resources is less than the second total amount of resources, using the second request policy as the new first request policy includes: If the first total amount of resources is less than the maximum second total amount of resources, using the second request policy corresponding to the maximum second total amount of resources as the new first request policy.

11. An electronic device, characterized in that, Includes: A processor; A memory for storing executable instructions of the processor; Wherein, the processor is configured to execute the instructions to implement the promotion information processing method according to any one of claims 1 to 10.

12. A computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device can execute the promotion information processing method according to any one of claims 1 to 10.

Images