Ad inventory processing method, system, apparatus, device, and medium

Abstract

Embodiments of the present disclosure provide an advertisement inventory processing method, system, device, equipment and medium. In the embodiments of the present disclosure, the client sends a request for obtaining a target pre-stored advertisement and a request for obtaining a real-time advertisement to the server, wherein the request for obtaining the target pre-stored advertisement carries the identifiers of a plurality of pre-stored advertisements stored locally by the client, so that the server selects a target pre-stored advertisement with a suitable state from the plurality of pre-stored advertisements according to the current state of the obtained pre-stored advertisements, such as the current remaining display demand and the current advertisement delivery state, and sends the target pre-stored advertisement to the client, so that the target pre-stored advertisement is displayed in the case that the real-time advertisement is not successfully sent to the client or the real-time advertisement is not successfully loaded by the client. This can avoid the waste of advertisement inventory caused by directly selecting a pre-stored advertisement from the local client for display in the related art, such as advertisement over-delivery, thereby improving the effective utilization rate of the advertisement inventory.

Description

Technical Field

[0001] The embodiments of this disclosure relate to the field of multimedia technology, and more specifically, the embodiments of this disclosure relate to advertising inventory processing methods, systems, apparatuses, devices, and media. Background Technology

[0002] This section is intended to provide background or context for the embodiments of this disclosure as set forth in the claims. The description herein is not intended to be a prior art simply because it is included in this section.

[0003] With the rapid development of the mobile internet, mobile applications have gradually become an important part of users' daily lives. Consequently, advertising revenue from mobile applications has become a major source of income for many application developers. For example, boot-up ads have been widely used as a form of advertising in music, video, and social applications.

[0004] In current related technologies, when a user launches an application, the client sends a request to the advertising server to retrieve real-time ads. If the client is unable to display real-time ads due to reasons such as the advertising server failing to send real-time ads to the client resulting in a timeout or the client failing to load real-time ads, then the client will select a pre-stored ad based on the selection probability of pre-stored ads in the local storage for ad display.

[0005] However, since the status of ads on the server, such as the remaining display demand and the ad delivery status indicating whether ads are allowed to be delivered, is dynamically changing, the above-mentioned method of selecting ads for display based on the static selection probability on the client can lead to situations such as over-delivery of ads, which wastes ad inventory and reduces the effective utilization rate of ad inventory. Summary of the Invention

[0006] In this context, embodiments of the present disclosure are intended to provide an advertising inventory processing method, system, apparatus, device, and medium to improve the effective utilization rate of advertising inventory.

[0007] In a first aspect of this disclosure, an advertising inventory processing method is provided, the method being applied to a server, the method comprising:

[0008] The client receives a request to retrieve a target pre-stored advertisement and a request to retrieve a real-time advertisement. The request to retrieve the target pre-stored advertisement carries the identifiers of several pre-stored advertisements stored locally on the client.

[0009] The target pre-stored advertisement is determined based on the current state of the pre-stored advertisement; the current state refers to the latest state of the advertisement obtained at present;

[0010] The identifier of the target pre-stored advertisement is sent to the client at least so that the target pre-stored advertisement is displayed if the real-time advertisement is not successfully sent to the client or the client fails to load the real-time advertisement.

[0011] In one embodiment of this disclosure, the pre-stored advertisement includes price-guaranteed and quantity-guaranteed advertisements, price-guaranteed but not quantity-guaranteed advertisements, and / or auction advertisements; the request to obtain the target pre-stored advertisement also carries information characterizing the advertisement type of the pre-stored advertisement;

[0012] Determining the target pre-stored advertisement based on the current state of the pre-stored advertisement includes:

[0013] Based on the advertised type, a pre-stored advertiser with the current priority is selected. A target pre-stored advertiser is determined from the pre-stored advertisers that meet the preset conditions in the current state. If the target pre-stored advertiser is not determined, it is determined whether the target pre-stored advertiser can be determined from the pre-stored advertisers with the next priority. Among them, the price-guaranteed and quantity-guaranteed advertisers have a higher priority than the price-guaranteed but quantity-not-guaranteed advertisers, and the price-guaranteed but quantity-not-guaranteed advertisers have a higher priority than the bidding advertisers.

[0014] In one embodiment of this disclosure, determining the target pre-stored advertisement from pre-stored advertisements that currently meet preset conditions includes:

[0015] If the current priority pre-stored ad is a price-guaranteed and quantity-guaranteed ad, then search for pre-stored ads that are currently within the ad delivery time period from the current priority pre-stored ads.

[0016] If found, the probability of each pre-stored ad being selected is determined based on the current remaining display demand and remaining ad inventory of each pre-stored ad found; if a pre-stored ad is selected based on the selection probability of each pre-stored ad found, the selected pre-stored ad is taken as the target pre-stored ad.

[0017] If no target ad is found, or if no target ad is selected based on the probability of selection for each target ad found, then it is determined that no target target ad has been identified from the target ads of the current priority.

[0018] In one embodiment of this disclosure, determining the target pre-stored advertisement from pre-stored advertisements that currently meet preset conditions includes:

[0019] If the current priority pre-stored ad is a price-guaranteed but quantity-guaranteed ad, then search for a pre-stored ad in the current priority pre-stored ad whose current ad placement status is allowed. If found, then the pre-stored ad with the smallest current ad playback progress among the found pre-stored ads is taken as the target pre-stored ad. If not found, then it is determined that no target pre-stored ad has been determined from the current priority pre-stored ads.

[0020] In one embodiment of this disclosure, the request to obtain the target pre-stored advertisement also carries client information characterizing the client;

[0021] The step of determining the target pre-stored advertisement from the pre-stored advertisements that meet the preset conditions in the current state includes:

[0022] If the current priority pre-stored ad is a bidding ad, then if there is a pre-stored ad in the current priority pre-stored ad whose current ad placement status is allowed, then from the pre-stored ads whose current ad placement status is allowed, search for pre-stored ads whose current ad targeting conditions match the client information, and pre-stored ads whose ad targeting conditions do not exist; if found, then if the number of pre-stored ads found is 1, the found pre-stored ad is taken as the target pre-stored ad; if the number of pre-stored ads found is greater than 1, the pre-stored ad with the highest current estimated ad revenue among all the found pre-stored ads is taken as the target pre-stored ad.

[0023] If no target pre-installed ad is found, or if there is no pre-installed ad in the current priority pre-installed ad list that is currently allowed to be served, it is determined that no target pre-installed ad has been identified from the current priority pre-installed ad list.

[0024] In one embodiment of this disclosure, the method further includes:

[0025] If it is determined that no target pre-stored advertisement is found from the plurality of pre-stored advertisements, an instruction indicating that no target pre-stored advertisement has been found will be sent to the client. This means that if a real-time advertisement is not successfully sent to the client or the client fails to load the real-time advertisement, no advertisement will be displayed in this instance if no target pre-stored advertisement is found. If a target pre-stored advertisement is not successfully sent to the client, a pre-stored advertisement will be selected from the plurality of pre-stored advertisements stored locally on the client for display.

[0026] In one embodiment of this disclosure, the method further includes:

[0027] The system receives a request from the client to retrieve pre-stored advertisements, the request carrying client information that identifies the client.

[0028] Search the ad library for ads whose current ad targeting conditions match the client information, as well as ads for which no ad targeting conditions exist;

[0029] If the found advertisements include at least one non-bid advertisement, then the selection probability of each non-bid advertisement is determined based on the current remaining display demand and remaining advertisement inventory of each non-bid advertisement; and at least one non-bid advertisement is selected as a pre-stored advertisement based on the selection probability of each non-bid advertisement.

[0030] If the found advertisements include at least one bidding advertisement, the pre-trained advertising revenue prediction model is used to obtain the estimated advertising revenue of each bidding advertisement based on the current advertising price information of each bidding advertisement; and at least one bidding advertisement is selected as a pre-stored advertisement based on the estimated advertising revenue of each bidding advertisement.

[0031] At least the identifiers, ad creatives, and selection probabilities of each selected pre-stored ad should be sent to the client.

[0032] In a second aspect of this disclosure, an advertising inventory processing system is provided, the system comprising a client and a server;

[0033] The client is used to receive an application launch command triggered by a user, and send a request to the server to obtain a target pre-stored advertisement and a request to obtain a real-time advertisement; the request to obtain the target pre-stored advertisement carries the identifiers of several pre-stored advertisements stored locally by the client.

[0034] The server is configured to receive requests from the client to retrieve a target pre-stored advertisement and a request to retrieve a real-time advertisement, determine the target pre-stored advertisement based on the current state of the pre-stored advertisement; the current state refers to the latest state of the currently obtained advertisement; and at least send the identifier of the target pre-stored advertisement to the client.

[0035] The client is also configured to receive the identifier of the target pre-stored advertisement, so as to display the target pre-stored advertisement if the server fails to send the real-time advertisement to the client or the client fails to load the real-time advertisement.

[0036] In a third aspect of this disclosure, an advertising inventory processing apparatus is provided, the apparatus being applied to a server, the apparatus comprising:

[0037] The receiving module is used to receive requests from the client to obtain target pre-stored advertisements and requests to obtain real-time advertisements. The request to obtain target pre-stored advertisements carries the identifiers of several pre-stored advertisements stored locally by the client.

[0038] The determining module is used to determine the target pre-stored advertisement based on the current state of the pre-stored advertisement; the current state refers to the latest state of the advertisement obtained at present;

[0039] The sending module is configured to send at least the identifier of the target pre-stored advertisement to the client, so as to display the target pre-stored advertisement if the real-time advertisement is not successfully sent to the client or the client fails to load the real-time advertisement.

[0040] In one embodiment of this disclosure, the pre-stored advertisement includes price-guaranteed and quantity-guaranteed advertisements, price-guaranteed but not quantity-guaranteed advertisements, and / or auction advertisements; the request to obtain the target pre-stored advertisement also carries information characterizing the advertisement type of the pre-stored advertisement;

[0041] The determining module, when determining the target pre-stored advertisement based on the current state of the pre-stored advertisement, is used to:

[0042] Based on the advertised type, a pre-stored advertiser with the current priority is selected. A target pre-stored advertiser is determined from the pre-stored advertisers that meet the preset conditions in the current state. If the target pre-stored advertiser is not determined, it is determined whether the target pre-stored advertiser can be determined from the pre-stored advertisers with the next priority. Among them, the price-guaranteed and quantity-guaranteed advertisers have a higher priority than the price-guaranteed but quantity-not-guaranteed advertisers, and the price-guaranteed but quantity-not-guaranteed advertisers have a higher priority than the bidding advertisers.

[0043] In one embodiment of this disclosure, the determining module, when determining a target pre-stored advertisement from pre-stored advertisements whose current state meets preset conditions, is configured to:

[0044] If the current priority pre-stored ad is a price-guaranteed and quantity-guaranteed ad, then search for pre-stored ads that are currently within the ad delivery time period from the current priority pre-stored ads.

[0045] If found, the probability of each pre-stored ad being selected is determined based on the current remaining display demand and remaining ad inventory of each pre-stored ad found; if a pre-stored ad is selected based on the selection probability of each pre-stored ad found, the selected pre-stored ad is taken as the target pre-stored ad.

[0046] If no target ad is found, or if no target ad is selected based on the probability of selection for each target ad found, then it is determined that no target target ad has been identified from the target ads of the current priority.

[0047] In one embodiment of this disclosure, the determining module, when determining a target pre-stored advertisement from pre-stored advertisements whose current state meets preset conditions, is configured to:

[0048] If the current priority pre-stored ad is a price-guaranteed but quantity-guaranteed ad, then search for a pre-stored ad in the current priority pre-stored ad whose current ad placement status is allowed. If found, then the pre-stored ad with the smallest current ad playback progress among the found pre-stored ads is taken as the target pre-stored ad. If not found, then it is determined that no target pre-stored ad has been determined from the current priority pre-stored ads.

[0049] In one embodiment of this disclosure, the request to obtain the target pre-stored advertisement also carries client information characterizing the client;

[0050] The determining module, when determining the target pre-stored advertisement from the pre-stored advertisements that meet the preset conditions in the current state, is used for:

[0051] If the current priority pre-stored ad is a bidding ad, then if there is a pre-stored ad in the current priority pre-stored ad whose current ad placement status is allowed, then from the pre-stored ads whose current ad placement status is allowed, search for pre-stored ads whose current ad targeting conditions match the client information, and pre-stored ads whose ad targeting conditions do not exist; if found, then if the number of pre-stored ads found is 1, the found pre-stored ad is taken as the target pre-stored ad; if the number of pre-stored ads found is greater than 1, the pre-stored ad with the highest current estimated ad revenue among all the found pre-stored ads is taken as the target pre-stored ad.

[0052] If no target pre-installed ad is found, or if there is no pre-installed ad in the current priority pre-installed ad list that is currently allowed to be served, it is determined that no target pre-installed ad has been identified from the current priority pre-installed ad list.

[0053] In one embodiment of this disclosure, the sending module is further configured to:

[0054] If it is determined that no target pre-stored advertisement is found from the plurality of pre-stored advertisements, an instruction indicating that no target pre-stored advertisement has been found will be sent to the client. This means that if a real-time advertisement is not successfully sent to the client or the client fails to load the real-time advertisement, no advertisement will be displayed in this instance if no target pre-stored advertisement is found. If a target pre-stored advertisement is not successfully sent to the client, a pre-stored advertisement will be selected from the plurality of pre-stored advertisements stored locally on the client for display.

[0055] In one embodiment of this disclosure, the apparatus further includes a lookup module;

[0056] The receiving module is further configured to: receive a request from the client to obtain pre-stored advertisements, wherein the request to obtain pre-stored advertisements carries client information that represents the client;

[0057] The search module is used to: search the ad library for ads whose current ad targeting conditions match the client information, as well as ads for which no ad targeting conditions exist;

[0058] If the found advertisements include at least one non-bid advertisement, then the selection probability of each non-bid advertisement is determined based on the current remaining display demand and remaining advertisement inventory of each non-bid advertisement; and at least one non-bid advertisement is selected as a pre-stored advertisement based on the selection probability of each non-bid advertisement.

[0059] If the found advertisements include at least one bidding advertisement, the pre-trained advertising revenue prediction model is used to obtain the estimated advertising revenue of each bidding advertisement based on the current advertising price information of each bidding advertisement; and at least one bidding advertisement is selected as a pre-stored advertisement based on the estimated advertising revenue of each bidding advertisement.

[0060] The sending module is also used to send at least the identifier, advertising material, and selection probability of each selected pre-stored advertisement to the client.

[0061] In a fourth aspect of this disclosure, an electronic device is provided, comprising: a processor; and a computer-readable storage medium storing computer program instructions that, when executed by the processor, cause the processor to perform operations as described in the first aspect and any embodiment thereof.

[0062] In a fifth aspect of this disclosure, a computer-readable storage medium is provided that stores a program that is executed by a processor as described in the first aspect and any embodiment of the first aspect, performing the operations performed by the advertising inventory processing method.

[0063] In a sixth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, performs the operations performed by the advertising inventory processing method described in the first aspect and any embodiment thereof.

[0064] According to the advertising inventory processing method provided in this disclosure, the client sends a request to obtain a target pre-stored advertisement and a request to obtain a real-time advertisement to the server. The request to obtain the target pre-stored advertisement carries the identifiers of several pre-stored advertisements stored locally on the client. The server then selects a target pre-stored advertisement with a suitable status from the several pre-stored advertisements based on the current status of the obtained pre-stored advertisements, such as the current remaining display demand and the current advertisement delivery status, and sends it to the client. This allows the target pre-stored advertisement to be displayed even if the real-time advertisement is not successfully sent to the client or the client fails to load the real-time advertisement. This avoids the waste of advertising inventory, such as over-delivery of advertisements, caused by directly selecting pre-stored advertisements from the client's local storage in related technologies, thereby improving the effective utilization rate of advertising inventory. Attached Figure Description

[0065] The above and other objects, features, and advantages of this disclosure will become readily apparent from the following detailed description of exemplary embodiments, taken in conjunction with the accompanying drawings. Several embodiments of this disclosure are illustrated in the drawings by way of example and not limitation, in which:

[0066] Figure 1 A schematic diagram of the structure of an advertising inventory processing system according to an embodiment of the present disclosure is shown.

[0067] Figure 2 A schematic flowchart of an advertising inventory processing method according to an embodiment of the present disclosure is shown.

[0068] Figure 3 A schematic flowchart of a method for determining a target pre-stored advertisement according to an embodiment of the present disclosure is shown.

[0069] Figure 4 A schematic flowchart of another target pre-stored advertisement determination method according to an embodiment of the present disclosure is shown;

[0070] Figure 5 A schematic flowchart of another target pre-stored advertisement determination method according to an embodiment of the present disclosure is shown;

[0071] Figure 6 A block diagram of an advertising inventory processing apparatus according to an embodiment of the present disclosure is shown schematically;

[0072] Figure 7 A schematic diagram of a computer-readable storage medium according to an embodiment of the present disclosure is shown.

[0073] Figure 8 A schematic diagram of an electronic device according to an embodiment of the present disclosure is shown.

[0074] In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts.

[0075] It should be understood that the number of any elements in the accompanying drawings is for illustrative purposes only and not for limitation, and any naming is for distinction only and has no limiting meaning. Detailed Implementation

[0076] The principles and spirit of this disclosure will now be described with reference to several exemplary embodiments. It should be understood that these embodiments are given merely to enable those skilled in the art to better understand and implement this disclosure, and are not intended to limit the scope of this disclosure in any way. Rather, these embodiments are provided to make this disclosure more thorough and complete, and to fully convey the scope of this disclosure to those skilled in the art.

[0077] Those skilled in the art will recognize that embodiments of this disclosure can be implemented as a system, apparatus, device, method, or computer program product. Therefore, this disclosure can be specifically implemented in the following forms: entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0078] According to embodiments of this disclosure, an advertising inventory processing method, system, apparatus, device, and medium are proposed. The principles and spirit of this disclosure are explained in detail below with reference to several representative embodiments. Invention Overview

[0080] The author has observed that with the rapid development of the mobile internet, mobile applications have gradually become an important part of users' daily lives. Consequently, advertising revenue within mobile applications has become a major source of income for many application developers. For example, boot-up ads have been widely used as a form of advertising in music, video, and social applications.

[0081] Currently, in related technologies, the client periodically retrieves contracted ads from the advertising server to store locally as pre-stored ads. When a user launches the application, the client sends a request to the advertising server to retrieve real-time ads. If the client cannot display real-time ads due to reasons such as the advertising server failing to successfully send real-time ads to the client causing a request timeout or the client failing to successfully load real-time ads, then the client will select a pre-stored ad for display based on its selection probability. The selection probability of a pre-stored ad is calculated by the advertising server based on the remaining display demand and remaining ad inventory after determining the pre-stored ad.

[0082] However, since the status of ads on the advertising server, such as the remaining display demand and the ad delivery status, are dynamically changing, while the selection probability of the ads pre-stored locally on the client is a static value calculated based on the historical status of the pre-stored ads, it is not necessarily accurate. Therefore, the above method of selecting ads for display based on the selection probability of the pre-stored ads locally on the client may result in wasted ad inventory, such as over-deployment, thereby reducing the effective utilization rate of ad inventory.

[0083] In view of this, this disclosure aims to propose an advertising inventory processing scheme in which the server selects pre-stored advertisements for display based on the current state of the advertisements when the user launches the application, so as to efficiently manage and utilize the advertising inventory and address the shortcomings of related technologies.

[0084] Application Scenarios Overview

[0085] First refer to Figure 1 , Figure 1 A schematic diagram of the structure of an advertising inventory processing system according to an embodiment of the present disclosure is shown, such as... Figure 1 As shown, the system 100 may include a client 101 and a server 102.

[0086] In some embodiments, client 101 may refer to a program installed on a user device that provides services such as music and video services to the user. For example, client 101 may include, but is not limited to, applications and web pages; where Web is an abbreviation for World Wide Web. User devices may include, but are not limited to, smartphones, tablets, and laptops.

[0087] Server 102 can refer to a program installed in a background device that provides advertising services to users. For example, the background device can be a standalone server or a server cluster consisting of multiple servers; this embodiment is not specifically limited to this.

[0088] In some embodiments, when a user launches client 101 installed on their user device (i.e., when the user launches the application), client 101 sends a request to server 102 to retrieve a target pre-stored advertisement and a request to retrieve a real-time advertisement. The request to retrieve the target pre-stored advertisement carries identifiers of several pre-stored advertisements locally stored by client 101. Upon receiving the request to retrieve the target pre-stored advertisement from client 101, server 102, based on the advertisement inventory processing method provided in this disclosure, selects the target pre-stored advertisement from the several pre-stored advertisements and sends it to client 101, so that the target pre-stored advertisement is displayed even if real-time advertisements are not successfully sent to client 101 or if client 101 fails to load real-time advertisements.

[0089] It should be noted that the above application scenarios are shown only to facilitate understanding of the spirit and principles of this disclosure. The implementation of this disclosure is not limited in any way; on the contrary, the implementation of this disclosure can be applied to any applicable scenario.

[0090] Exemplary methods

[0091] The following section, in conjunction with the above description of relevant application scenarios, will provide a detailed introduction to the advertising inventory processing method provided in this disclosure.

[0092] See Figure 2 , Figure 2 A schematic flowchart illustrating an advertising inventory processing method according to an embodiment of this disclosure is shown. Figure 2 As shown, this method is applied to the server side and includes the following steps:

[0093] Step 201: Receive requests from the client to obtain target pre-stored advertisements and requests to obtain real-time advertisements; wherein, the request to obtain target pre-stored advertisements carries the identifiers of several pre-stored advertisements stored locally on the client.

[0094] Step 202: Determine the target pre-stored advertisement based on the current state of the pre-stored advertisement; the current state refers to the latest state of the currently obtained advertisement.

[0095] In some possible implementations, after receiving a request from the client to retrieve a target pre-stored advertisement, the server can obtain the current status of the pre-stored advertisement, such as remaining display demand and ad delivery status, based on the identifier of the pre-stored advertisement carried in the request. Based on the obtained current status of the pre-stored advertisement, the server can then determine the target pre-stored advertisement from among the several pre-stored advertisements carried in the request. The specific method for determining the target pre-stored advertisement based on its current status will be described with examples below and will not be elaborated upon here.

[0096] In some possible implementations, after receiving a request from a client to retrieve real-time ads, the server can select an ad from its ad library based on the request and return it to the client as a real-time ad. The specific handling of such requests will be described with examples below and will not be elaborated upon here.

[0097] Optionally, the ad library may include several contract ads and / or several auction ads. Contract ads can refer to a form of online advertising where the advertiser and the advertising platform reach a cooperation agreement, pre-determining the ad's display time, display position, display demand, and display price. Auction ads can refer to a form of online advertising where advertisers independently place and manage their ads, adjusting ad prices for ranking, and paying based on ad performance (such as pay-per-click and pay-per-conversion).

[0098] Step 203: Send at least the identifier of the target pre-stored ad to the client so that the target pre-stored ad can be displayed if the real-time ad is not successfully sent to the client or the client fails to load the real-time ad.

[0099] In some possible implementations, after the server determines the target pre-stored advertisement based on the current state of the pre-stored advertisement, it can at least send the identifier of the target pre-stored advertisement to the client. This allows the client to obtain the advertising material (such as images, text, videos, etc.) of the target pre-stored advertisement from its local machine based on the identifier of the target pre-stored advertisement, even if the real-time advertisement is not successfully sent to the client or the client fails to load the real-time advertisement. The client can then display the target pre-stored advertisement based on the advertising material of the target pre-stored advertisement.

[0100] According to the advertising inventory processing method provided in this disclosure, the client sends a request to obtain a target pre-stored advertisement and a request to obtain a real-time advertisement to the server. The request to obtain the target pre-stored advertisement carries the identifiers of several pre-stored advertisements stored locally on the client. The server then selects a suitable target pre-stored advertisement from the several pre-stored advertisements based on the current status of the obtained pre-stored advertisements, such as the current remaining display demand and the current advertisement delivery status, and sends it to the client. This allows the target pre-stored advertisement to be displayed even if the real-time advertisement is not successfully sent to the client or the client fails to load the real-time advertisement. This avoids the waste of advertising inventory, such as over-delivery of advertisements, caused by directly selecting pre-stored advertisements from the client's local storage in related technologies, thereby improving the effective utilization rate of advertising inventory.

[0101] After introducing the basic implementation process of this disclosure, various non-limiting embodiments of this disclosure will be described in detail below.

[0102] The following describes how the target pre-stored advertisement is determined based on the current state of the pre-stored advertisement:

[0103] In some embodiments, an advertisement may include multiple advertisement types, such as, but not limited to, price-guaranteed and quantity-guaranteed advertisements, price-guaranteed but not quantity-guaranteed advertisements, and auction-based advertisements. Therefore, the pre-stored advertisements carried in the aforementioned request to obtain the target pre-stored advertisement may include price-guaranteed and quantity-guaranteed advertisements, price-guaranteed but not quantity-guaranteed advertisements, and / or auction-based advertisements.

[0104] In this embodiment, both price-guaranteed but not quantity-guaranteed ads and price-guaranteed but quantity-guaranteed ads are contract ads. Price-guaranteed but quantity-guaranteed ads refer to an agreement between the advertiser and the advertising platform to place ads at a pre-agreed price while guaranteeing a certain number of ad impressions (such as impressions or clicks) within a specified timeframe. Price-guaranteed but not quantity-guaranteed ads refer to an agreement between the advertiser and the advertising platform to place ads at a pre-agreed price, but without guaranteeing a certain number of ad impressions within a specified timeframe.

[0105] In some embodiments, to improve overall advertising revenue, more contract ads can be selected as target pre-stored ads, so that more opportunities for the selected ads can be allocated to auction ads when acquiring real-time ads. Based on this, this embodiment can pre-set the priority of ads for each ad type for determining target pre-stored ads, wherein different ad types have different priorities; for example, as an embodiment, price-guaranteed quantity ads have a higher priority than price-guaranteed but not quantity ads, and price-guaranteed but not quantity ads have a higher priority than auction ads.

[0106] Based on the above description, taking the example that the priority of price-guaranteed and quantity-guaranteed ads is higher than that of price-guaranteed but not quantity-guaranteed ads, and the priority of price-guaranteed but not quantity-guaranteed ads is higher than that of bidding ads, in some embodiments, the above-mentioned determination of the target pre-stored ad based on the current state of the pre-stored ads can be implemented in a specific way, for example: the above-mentioned request to obtain the target pre-stored ad also carries information representing the ad type of the pre-stored ad; based on this, the current priority pre-stored ad can be selected based on the ad type of the pre-stored ad, for example, the current priority pre-stored ad is a price-guaranteed and quantity-guaranteed ad; then, for the current priority pre-stored ad, the target pre-stored ad is determined from the pre-stored ads whose current state meets the preset conditions; if the target pre-stored ad is not determined, it is determined whether the target pre-stored ad can be determined from the pre-stored ads of the next priority, and so on, until the target pre-stored ad is determined or the current priority is the last priority.

[0107] In this embodiment, the specific implementation methods for determining the target pre-stored advertisement from the pre-stored advertisements that meet the preset conditions in the current state are different for different types of pre-stored advertisements.

[0108] In one possible implementation, if the current priority pre-stored advertisement is a price-guaranteed and quantity-guaranteed advertisement, as described above, the requirement of a price-guaranteed and quantity-guaranteed advertisement is to guarantee the completion of a certain amount of advertisement display demand within a certain period of time. Therefore, it is advisable to prioritize pre-stored advertisements with a larger remaining display demand and a slower advertisement playback progress as target pre-stored advertisements to ensure that the price-guaranteed and quantity-guaranteed advertisement can complete the agreed amount of advertisement display demand within the agreed time period.

[0109] Based on this, see as follows Figure 3 The flowchart shown illustrates that determining the target pre-stored advertisement may include the following steps in its implementation:

[0110] Step 301: If the current priority pre-stored advertisement is a price-guaranteed and quantity-guaranteed advertisement, then search for pre-stored advertisements that are currently within the advertising time period from the current priority pre-stored advertisements; if found, proceed to step 302; if not found, proceed to step 305.

[0111] In some embodiments, each pre-stored advertisement corresponds to an advertising time period; different pre-stored advertisements may correspond to the same or different advertising time periods.

[0112] Step 302: Based on the current remaining display demand and remaining ad inventory of each pre-stored ad found, determine the probability of each pre-stored ad being selected.

[0113] In this embodiment, the remaining display demand can refer to the remaining unfulfilled advertising display demand; for example, for an advertisement, the agreed advertising display demand is 1 million times, and the advertisement has been displayed 100,000 times, that is, the completed display demand is 100,000 times, then the current remaining display demand of the advertisement is 1 million times - 100,000 times = 900,000 times.

[0114] Remaining ad inventory can refer to the number of available ad impressions remaining within a specified time period. In some embodiments, the current remaining ad inventory of any pre-stored ad can be determined as follows: if the pre-stored ad includes ad targeting conditions, the remaining ad inventory can be obtained by inputting the time period from the current time to the end of the specified time period, along with the ad targeting conditions of the pre-stored ad, into a trained inventory prediction model; if the pre-stored ad does not include ad targeting conditions, the remaining ad inventory can be obtained by inputting the time period from the current time to the end of the specified time period into a trained inventory prediction model. Ad targeting conditions can refer to methods of accurately delivering ads to specific target groups based on specific user characteristics, behaviors, or environments; for example, ad targeting conditions may include female, age between 20 and 30, and residence in city A.

[0115] In some embodiments, determining the selection probability of each pre-stored advertisement found in this step can be implemented by taking the current remaining display demand and remaining advertisement inventory of each pre-stored advertisement found as input parameters and inputting them into a preset probability calculation function to obtain the selection probability of each pre-stored advertisement.

[0116] Optionally, the above probability calculation function can be flexibly set based on actual application needs. For example, the probability calculation function can be: P = (a / b) * c, where P represents the probability of being selected, a represents the remaining display demand, b represents the remaining advertising inventory, and c represents the preset probability factor.

[0117] Step 303: Select a pre-stored advertisement based on the probability of selection for each found pre-stored advertisement. If selected, proceed to step 304; otherwise, proceed to step 305.

[0118] For example, assuming the pre-stored ads found are Ad 1, Ad 2, and Ad 3, and the probability of Ad 1, Ad 2, and Ad 3 being selected is 10%, 20%, and 30%, respectively, then when selecting a pre-stored ad based on the probability of each pre-stored ad being selected, there is a 10% probability of selecting Ad 1, a 20% probability of selecting Ad 2, a 30% probability of selecting Ad 3, and a 50% probability of not selecting any ad.

[0119] Step 304: Select the pre-stored advertisement as the target pre-stored advertisement.

[0120] Step 305: Determine that no target pre-stored advertisement has been identified from the pre-stored advertisements of the current priority.

[0121] In another possible implementation, if the currently prioritized pre-stored ads are price-guaranteed but quantity-not-guaranteed ads, as described above, these ads do not require a guarantee of completing a certain number of ad impressions within a specific timeframe. In this case, balancing the ad playback progress can be considered to ensure smooth ad display, avoiding over-targeting due to excessively fast playback and under-displaying due to excessively slow playback. Furthermore, ad placement status can be considered to avoid selecting ads that are not permitted to be displayed, thus preventing waste of ad inventory. Therefore, prioritizing pre-stored ads with permitted placement status and slower playback progress can be considered as target pre-stored ads to avoid wasting ad inventory and improve ad inventory utilization.

[0122] Based on this, see as follows Figure 4 The flowchart shown illustrates that determining the target pre-stored advertisement may include the following steps in its implementation:

[0123] Step 401: If the current priority pre-stored advertisement is a price-guaranteed but quantity-guaranteed advertisement, then search for pre-stored advertisements whose current advertising status is allowed to be placed from the current priority pre-stored advertisements. If found, proceed to step 402; if not found, proceed to step 403.

[0124] In some embodiments, ad delivery status may include allowed delivery and disallowed delivery. For example, if the ad is online, it means the ad delivery status is allowed, and if the ad is offline, it means the ad delivery status is disallowed.

[0125] Step 402: Select the pre-stored advertisement with the smallest current playback progress among the found pre-stored advertisements as the target pre-stored advertisement.

[0126] In this embodiment, the ad playback progress can refer to the ratio between the completed display demand and the agreed display demand, such as by expressing it as a percentage. For example, for an ad, the agreed display demand is 1 million times, and the current completed display demand is 100,000 times, then the current ad playback progress is 100,000 times / 1 million times = 10%.

[0127] Step 403: Determine that no target pre-stored advertisement has been identified from the pre-stored advertisements of the current priority.

[0128] In another possible implementation, if the current priority pre-stored ad is a bidding ad, since the launch and delisting of bidding ads change frequently, the ad targeting conditions will also change occasionally. Therefore, in order to avoid wasting ad inventory, it is possible to determine the target pre-stored ad based on the ad delivery status and ad targeting conditions.

[0129] Based on this, see as follows Figure 5 The flowchart shown illustrates that determining the target pre-stored advertisement may include the following steps in its implementation:

[0130] Step 501: If the current priority pre-stored advertisement is a bidding advertisement, check if there is a pre-stored advertisement in the current priority that is currently allowed to be placed; if yes, proceed to step 502; otherwise, proceed to step 504.

[0131] Step 502: From the pre-stored ads whose current ad delivery status is allowed, search for pre-stored ads whose current ad targeting conditions match the client information, as well as pre-stored ads whose ad targeting conditions do not exist; if found, proceed to step 503; if not found, proceed to step 504.

[0132] In this embodiment, the aforementioned client information refers to client information representing the client carried in the request for obtaining the target pre-stored advertisement. Optionally, the client information may include, but is not limited to, the client's network status information, device information, and operating system version information.

[0133] In some embodiments, searching for pre-stored ads that match the current ad targeting conditions with the client information can be implemented as follows: First, obtain the user information of the user bound to the client based on the client information. The user information may include information such as the user's gender and age. Then, for each pre-stored ad whose current ad delivery status is allowed, check whether the ad targeting conditions of the pre-stored ad match the aforementioned client information and user information. If so, determine that the pre-stored ad is a pre-stored ad whose current ad targeting conditions match the client information.

[0134] For example, suppose the advertising targeting criteria of a pre-stored advertisement are: female, aged between 20 and 30, medium network signal strength of the client, and operating system version A of the client. The client information includes: medium network signal strength and operating system version A. The user information includes: female and 25 years old. Then it can be determined that the advertising targeting criteria of the pre-stored advertisement match the client information.

[0135] It should be noted that the privacy information involved in this embodiment, such as user information, is all authorized information authorized by the user.

[0136] Step 503: When the number of pre-stored ads found is 1, the found pre-stored ad is taken as the target pre-stored ad. When the number of pre-stored ads found is greater than 1, the pre-stored ad with the highest estimated advertising revenue among the found pre-stored ads is taken as the target pre-stored ad.

[0137] In this embodiment, the estimated advertising revenue can refer to the estimated revenue from ad impressions. For example, the estimated advertising revenue can be represented by the metric eCPM. This embodiment does not specifically limit this. Here, eCPM is an abbreviation for Effective Cost Per Mille.

[0138] In some embodiments, the estimated advertising revenue of any pre-stored advertisement can be obtained by inputting the advertisement price information of the pre-stored advertisement as input data into a trained advertising revenue prediction model. The advertisement price information may include, for example, pay-per-click (costing x yuan per click) or pay-per-impression (costing y yuan per thousand impressions).

[0139] In some embodiments, when the number of pre-stored ads found is greater than 1, if there are multiple pre-stored ads with the highest estimated advertising revenue among the found pre-stored ads, then any one of the pre-stored ads is selected as the target pre-stored ad.

[0140] Step 504: Determine that no target pre-stored advertisement has been identified from the pre-stored advertisements of the current priority.

[0141] This concludes the description of determining the target pre-stored advertisement based on the current state of the pre-stored advertisement.

[0142] The following describes the situation where the target pre-stored advertisement has not been determined:

[0143] In some embodiments, based on the above description, if the target pre-stored advertisement is not identified from the pre-stored advertisements of each priority, then it is determined that the target pre-stored advertisement has not been identified from the pre-stored advertisements.

[0144] Based on this, if it is determined that no target pre-stored advertisement has been identified from a number of pre-stored advertisements, information indicating that no target pre-stored advertisement has been identified can be sent to the client. This means that if no target pre-stored advertisement has been identified when the real-time advertisement has not been successfully sent to the client or the client has not successfully loaded the real-time advertisement, it indicates that there is no suitable pre-stored advertisement for display in this case, and therefore no advertisement will be displayed.

[0145] If the target pre-stored advertisement is not successfully sent to the client, it means that there is a suitable pre-stored advertisement for display, but the target pre-stored advertisement was not successfully sent to the client, that is, the client did not receive the target pre-stored advertisement within the specified request-response time. Therefore, a pre-stored advertisement can be selected from several pre-stored advertisements stored locally on the client for display. Specifically, as described above, a pre-stored advertisement can be selected for display based on the selection probability of each pre-stored advertisement locally on the client.

[0146] The following describes the situation where a request to retrieve pre-stored advertisements is received from a client:

[0147] Based on the above description, since the server can obtain the current status of the advertisement in a timely manner and determine the target pre-stored advertisement based on the current status of the advertisement, the determination of the target pre-stored advertisement will not be affected for bidding advertisements whose advertising status and advertising targeting conditions change frequently, and they can also be included in the pre-stored advertisements. This can effectively improve the utilization rate of bidding advertisements and advertisement inventory.

[0148] Based on this, in some embodiments, the client can periodically send a request to the server to retrieve pre-stored advertisements. For example, the client can send a request to the server to retrieve pre-stored advertisements every 30 minutes or 1 hour.

[0149] Based on this, the server receives a request from the client to retrieve pre-stored advertisements, wherein the request to retrieve pre-stored advertisements carries client information that identifies the client.

[0150] Then, the server searches the ad database for ads whose current targeting conditions match the client's information, as well as ads for which no targeting conditions exist.

[0151] If the found advertisements include at least one non-bid advertisement, which may refer to contract advertisements, then the selection probability of each non-bid advertisement is determined based on the current remaining display demand and remaining advertisement inventory of each non-bid advertisement; and at least one non-bid advertisement is selected as a pre-stored advertisement based on the selection probability of each non-bid advertisement.

[0152] If the searched ads include at least one bidding ad, the pre-trained ad revenue prediction model is used to obtain the estimated ad revenue of each bidding ad based on the current ad price information of each bidding ad; and at least one bidding ad is selected as a pre-stored ad based on the estimated ad revenue of each bidding ad.

[0153] Finally, at least the identifiers, ad creatives, and selection probabilities of each selected pre-stored ad should be sent to the client.

[0154] In some embodiments, the above-mentioned selection of at least one non-bid advertisement based on the selection probability of each non-bid advertisement as a pre-stored advertisement can be implemented as follows: firstly, sort the non-bid advertisements in descending order of their selection probability to obtain a sorting result, and then use the top N non-bid advertisements in the sorting result as pre-stored advertisements, where N is greater than or equal to 1.

[0155] In some embodiments, the above-mentioned selection of at least one bidding advertisement as a pre-stored advertisement based on the estimated advertising revenue of each bidding advertisement can be implemented as follows: firstly, the bidding advertisements are sorted in descending order of estimated advertising revenue to obtain a sorting result, and then the top M bidding advertisements in the sorting result are used as pre-stored advertisements, where M is greater than or equal to 1.

[0156] This completes the description of the situation where a request to retrieve pre-stored advertisements is received from a client.

[0157] The following describes how to handle requests from clients to retrieve real-time advertisements:

[0158] In this embodiment, the request to obtain real-time advertisements carries at least client information that represents the client.

[0159] Based on this, in one possible implementation, firstly, real-time ad selection is performed for price-guaranteed and quantity-guaranteed ads. Specifically, the ad database is first searched for price-guaranteed and quantity-guaranteed ads that match the current ad targeting conditions with the client information, as well as price-guaranteed and quantity-guaranteed ads without ad targeting conditions. Then, if a match is found, an ad is selected from the searched price-guaranteed and quantity-guaranteed ads based on their selection probability. If selected, the selected price-guaranteed and quantity-guaranteed ad is used as a real-time ad. If not selected, or if no match is found, the process for selecting real-time ads for price-guaranteed but not quantity-guaranteed ads begins. For details on how to determine the selection probability of each price-guaranteed and quantity-guaranteed ad and how to select an ad from the searched price-guaranteed and quantity-guaranteed ads based on their selection probability, please refer to the relevant descriptions above, which will not be repeated here.

[0160] For price-guaranteed but not volume-guaranteed ads, first search the ad library for price-guaranteed but not volume-guaranteed ads that match the current ad targeting conditions with the client information, as well as price-guaranteed but not volume-guaranteed ads without ad targeting conditions. Then, if a match is found, select the ad with the highest ad price and the ad placement status that is allowed to be placed from the searched price-guaranteed but not volume-guaranteed ads, and use it as the real-time ad. If no match is found, proceed to the real-time ad selection process for bidding ads.

[0161] For auction ads, first search the ad library for auction ads that match the current ad targeting conditions with the client information, as well as auction ads that do not have ad targeting conditions. Then, if a match is found, select the ad with the highest estimated ad revenue from the searched auction ads as the real-time ad. If no match is found, it is determined that no real-time ad has been selected.

[0162] Based on this, if a real-time ad is selected, at least the ad creative for that real-time ad will be returned to the client; if a real-time ad is not selected, a message indicating that a real-time ad has not been selected will be returned to the client.

[0163] This completes the description of how to handle requests from clients to retrieve real-time advertisements.

[0164] To facilitate understanding of the specific implementation process of the above-mentioned advertising inventory processing method, a detailed embodiment is described below.

[0165] In some embodiments, the user first launches a client on the user device.

[0166] When the client starts, it sends two requests to the server: one to retrieve a target pre-stored advertisement and the other to retrieve a real-time advertisement. The request to retrieve the target pre-stored advertisement may include client information identifying the client, information identifying the type of the pre-stored advertisement, and several pre-stored advertisements stored locally on the client. The request to retrieve the real-time advertisement may also include client information identifying the client.

[0167] Then, the server receives requests from the client to retrieve pre-stored target ads and requests to retrieve real-time ads.

[0168] In response to a request to retrieve a target pre-stored advertisement, the server will determine the target pre-stored advertisement according to a preset priority: ads with guaranteed price and quantity have higher priority than ads with guaranteed price but not quantity, and ads with guaranteed price but not quantity have higher priority than bidding ads. Specifically, the server will select the pre-stored advertisement of the current priority based on the advertisement type, such as pre-stored advertisements of the guaranteed price and quantity type. It will determine the target pre-stored advertisement from the pre-stored advertisements that meet the preset conditions in the current state. If the target pre-stored advertisement cannot be determined, it will determine whether the target pre-stored advertisement can be determined from the pre-stored advertisements of the next priority.

[0169] After identifying the target pre-stored advertisement from a pool of pre-stored advertisements, the server will at least return the identifier of the target pre-stored advertisement to the client. If the target pre-stored advertisement is not identified from the pool of pre-stored advertisements, the server will at least return information indicating that the target pre-stored advertisement was not identified to the client.

[0170] In response to a request to retrieve a real-time ad, the server will first select a real-time ad from the guaranteed price and guaranteed quantity ads in the ad library. If no real-time ad is selected, it will continue to select a real-time ad from the guaranteed price but not guaranteed quantity ads in the ad library. If no real-time ad is selected yet, it will continue to select a real-time ad from the auction ads in the ad library. If no real-time ad is selected yet, it is determined that no real-time ad has been selected from the ad library.

[0171] After selecting a real-time ad from the ad library, the server will at least return the ad creative for that real-time ad to the client. If no real-time ad is selected from the ad library, the server will at least return a message to the client indicating that no real-time ad was selected.

[0172] Subsequently, if the client receives the real-time advertisement returned by the server within the first specified response time (that is, the server successfully sent the real-time advertisement to the client), and the advertising creative of the real-time advertisement is successfully loaded, then the advertisement will be displayed based on the advertising creative of the real-time advertisement.

[0173] If the client receives a real-time advertisement from the server within the first specified response time, but the ad creative for that real-time advertisement fails to load successfully; or, if the client does not receive a real-time advertisement from the server within the first specified response time (i.e., the server failed to send the real-time advertisement to the client), then:

[0174] If the server successfully sends the target pre-stored advertisement to the client within the second specified response time (that is, the server successfully sends the target pre-stored advertisement to the client), the advertising material of the target pre-stored advertisement is obtained from the client's local storage based on the identifier of the target pre-stored advertisement, and the advertisement is displayed.

[0175] If the target pre-stored advertisement is not received from the server within the second specified response time (that is, the server has not successfully sent the target pre-stored advertisement to the client), no advertisement will be displayed this time;

[0176] If the server returns an instruction within the second specified response time but the target pre-stored advertisement information is not determined, a pre-stored advertisement is selected from several pre-stored advertisements stored locally on the client based on the advertisement's selection probability. If the selected advertisement is selected, it is displayed; otherwise, no advertisement is displayed this time.

[0177] If the client does not select the real-time advertisement information when it receives the instruction returned by the server within the first specified response time, the advertisement will not be displayed this time.

[0178] In some embodiments, since acquiring real-time ads requires processes such as traffic allocation, ad recall, and bidding, while acquiring target pre-stored ads is simpler than acquiring real-time ads because it involves selecting from several pre-stored ads based on the current state of the ads, the processing time for acquiring real-time ads is usually longer than that for acquiring target pre-stored ads. Therefore, the first specified response time can be longer than the second specified response time; for example, the first specified response time can be 200ms and the second specified response time can be 10ms. This embodiment does not specifically limit this.

[0179] This concludes the description of the method provided in this embodiment.

[0180] Exemplary device

[0181] After introducing the methods of exemplary embodiments of this disclosure, the following references are made. Figure 6 An apparatus for advertising inventory processing according to exemplary embodiments of the present disclosure is described.

[0182] refer to Figure 6 , Figure 6 A block diagram of an advertising inventory processing apparatus according to an embodiment of the present disclosure is shown schematically, such as... Figure 6As shown, this device is used on the server side, and the device includes:

[0183] The receiving module 601 is used to receive requests from the client to obtain target pre-stored advertisements and requests to obtain real-time advertisements. The request to obtain target pre-stored advertisements carries the identifiers of several pre-stored advertisements stored locally on the client.

[0184] The determination module 602 is used to determine the target pre-stored advertisement based on the current state of the pre-stored advertisement; the current state refers to the latest state of the advertisement currently obtained.

[0185] The sending module 603 is used to send at least the identifier of the target pre-stored advertisement to the client so that the target pre-stored advertisement can be displayed if the real-time advertisement is not successfully sent to the client or the client fails to load the real-time advertisement.

[0186] In one embodiment of this disclosure, the pre-stored advertisements include price-guaranteed and quantity-guaranteed advertisements, price-guaranteed but not quantity-guaranteed advertisements, and / or auction advertisements; the request to obtain the target pre-stored advertisement also carries information characterizing the advertisement type of the pre-stored advertisement;

[0187] The determining module 602, when determining the target pre-stored advertisement based on the current state of the pre-stored advertisement, is used to: select the pre-stored advertisement with the current priority based on the advertisement type; determine the target pre-stored advertisement from the pre-stored advertisements that meet the preset conditions in the current state; and, if the target pre-stored advertisement is not determined, determine whether the target pre-stored advertisement can be determined from the pre-stored advertisements with the next priority; wherein, the priority of the price-guaranteed and quantity-guaranteed advertisement is higher than that of the price-guaranteed but not quantity-guaranteed advertisement, and the priority of the price-guaranteed but not quantity-guaranteed advertisement is higher than that of the bidding advertisement.

[0188] In one embodiment of this disclosure, the determining module 602, when determining the target pre-stored advertisement from the pre-stored advertisements that meet the preset conditions in the current state, is used to: if the pre-stored advertisement with the current priority is a price-guaranteed and quantity-guaranteed advertisement, then search for the pre-stored advertisements in the current time period that are currently in the advertisement placement time period from the pre-stored advertisements with the current priority.

[0189] If found, the probability of each found pre-stored ad being selected is determined based on the current remaining display demand and remaining ad inventory. If a pre-stored ad is selected based on the selection probability of each found pre-stored ad, the selected pre-stored ad is taken as the target pre-stored ad.

[0190] If no target ad is found, or if no target ad is selected based on the probability of selection for each target ad found, then it is determined that no target target ad has been identified from the target ads of the current priority.

[0191] In one embodiment of this disclosure, the determining module 602, when determining the target pre-stored advertisement from the pre-stored advertisements whose current state meets the preset conditions, is configured to: if the pre-stored advertisement with the current priority is a price-guaranteed but quantity-guaranteed advertisement, then search for a pre-stored advertisement whose current advertising status is allowed to be placed from the pre-stored advertisements with the current priority; if found, then take the pre-stored advertisement with the smallest current advertising playback progress among the found pre-stored advertisements as the target pre-stored advertisement; if not found, then determine that no target pre-stored advertisement has been determined from the pre-stored advertisements with the current priority.

[0192] In one embodiment of this disclosure, the request to obtain the target pre-stored advertisement also carries client information that characterizes the client;

[0193] The determining module 602, when determining the target pre-stored advertisement from the pre-stored advertisements that meet the preset conditions in the current state, is configured to: if the pre-stored advertisement with the current priority is a bidding advertisement, and if there is a pre-stored advertisement with the current ad placement status being allowed to be placed among the pre-stored advertisements with the current ad placement status being allowed to be placed, search for pre-stored advertisements whose current ad targeting conditions match the client information and pre-stored advertisements without ad targeting conditions; if found, if the number of pre-stored advertisements found is 1, the found pre-stored advertisement is taken as the target pre-stored advertisement; if the number of pre-stored advertisements found is greater than 1, the pre-stored advertisement with the highest current estimated ad revenue among the found pre-stored advertisements is taken as the target pre-stored advertisement.

[0194] If no target pre-installed ad is found, or if there is no pre-installed ad in the current priority pre-installed ad list that is currently allowed to be served, it is determined that no target pre-installed ad has been identified from the current priority pre-installed ad list.

[0195] In one embodiment of this disclosure, the sending module 603 is further configured to: if it is determined that no target pre-stored advertisement has been identified from a plurality of pre-stored advertisements, send information indicating that no target pre-stored advertisement has been identified to the client, so that if the real-time advertisement is not successfully sent to the client or the client fails to load the real-time advertisement, no advertisement will be displayed this time if no target pre-stored advertisement has been identified; if the target pre-stored advertisement is not successfully sent to the client, select one pre-stored advertisement from a plurality of pre-stored advertisements stored locally on the client for display.

[0196] In one embodiment of this disclosure, the device 600 further includes a lookup module;

[0197] The receiving module 601 is also used to receive a request sent by the client to obtain pre-stored advertisements, wherein the request to obtain pre-stored advertisements carries client information that represents the client.

[0198] The search module is used to: find ads in the ad library that match the current ad targeting criteria with the client information, as well as ads that do not have ad targeting criteria;

[0199] If the found advertisements include at least one non-bid advertisement, then the selection probability of each non-bid advertisement is determined based on the current remaining display demand and remaining advertisement inventory of each non-bid advertisement; and at least one non-bid advertisement is selected as a pre-stored advertisement based on the selection probability of each non-bid advertisement.

[0200] If the found advertisements include at least one bidding advertisement, the pre-trained advertising revenue prediction model is used to obtain the estimated advertising revenue of each bidding advertisement based on the current advertising price information of each bidding advertisement; and at least one bidding advertisement is selected as a pre-stored advertisement based on the estimated advertising revenue of each bidding advertisement.

[0201] The sending module 603 is also used to send at least the identifier, advertising material, and selection probability of each selected pre-stored advertisement to the client.

[0202] It should be noted that although several modules of the advertising inventory processing apparatus have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules described above can be embodied in a single module. Conversely, the features and functions of a single module described above can be further divided and embodied by multiple modules.

[0203] Exemplary media

[0204] Having introduced the medium of exemplary embodiments of this disclosure, the following references are made to... Figure 7 A computer-readable storage medium for advertising inventory processing, according to exemplary embodiments of the present disclosure, is described.

[0205] refer to Figure 7 , Figure 7 A schematic diagram of a computer-readable storage medium according to an embodiment of the present disclosure is shown, such as... Figure 7 As shown, a computer program 700 is stored on a computer-readable storage medium. When executed by a processor, the computer program 700 can perform the advertising inventory processing method provided in any embodiment of this disclosure.

[0206] Exemplary device

[0207] Having described the methods, media, and apparatus of exemplary embodiments of this disclosure, the following references... Figure 8 An electronic device for advertising inventory processing, according to exemplary embodiments of the present disclosure, is described.

[0208] refer to Figure 8 , Figure 8 A schematic diagram of an electronic device according to an embodiment of the present disclosure is shown, such as... Figure 8 As shown, the electronic device 800 may include, but is not limited to: a processor 810, a memory 820, and a bus 830 connecting different system components (including the memory 820 and the processor 810).

[0209] The memory 820 stores computer instructions that can be executed by the processor 810, enabling the processor 810 to perform the advertising inventory processing method provided in any embodiment of this disclosure. The memory 820 may include a random access memory (RAM) 821, a cache memory 822, and / or a read-only memory (ROM) 823. The memory 820 may also include a program tool 825 having a set of program modules 824, including but not limited to: an operating system, one or more application programs, other program modules, and program data. One or more combinations of these program modules may include an implementation of a network environment.

[0210] Bus 830 may include, for example, a data bus, an address bus, and a control bus. Electronic device 800 can also communicate with external device 850 via input / output (I / O) interface 840, such as a keyboard or Bluetooth device. Electronic device 800 can also communicate with one or more networks via network adapter 860, such as a local area network (LAN), a wide area network (WAN), or a public network. Figure 8 As shown, the network adapter 860 can also communicate with other modules of the electronic device 800 via the bus 830.

[0211] Exemplary Products

[0212] This disclosure also provides a computer program product, which includes a computer program. When the program is executed by the processor 810 of the electronic device 800, it can implement the advertising inventory processing method provided in any embodiment of this disclosure.

[0213] Furthermore, although the operations of the methods disclosed herein are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all of the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0214] While the spirit and principles of this disclosure have been described with reference to several specific embodiments, it should be understood that this disclosure is not limited to the disclosed specific embodiments, and the division of aspects does not imply that features in these aspects cannot be combined for benefit; such division is merely for convenience of expression. This disclosure is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

Claims

1. A method for handling advertising inventory, characterized in that, The method is applied to the server side, and the method includes: The client receives a request to retrieve a target pre-stored advertisement and a request to retrieve a real-time advertisement. The request to retrieve the target pre-stored advertisement carries the identifiers of several pre-stored advertisements stored locally on the client. The target pre-stored advertisement is determined based on the current state of the pre-stored advertisement; the current state refers to the latest state of the advertisement obtained at present; The identifier of the target pre-stored advertisement is sent to the client at least so that the target pre-stored advertisement is displayed if the real-time advertisement is not successfully sent to the client or the client fails to load the real-time advertisement.

2. The method according to claim 1, characterized in that, The pre-stored advertisements include price-guaranteed and quantity-guaranteed advertisements, price-guaranteed but not quantity-guaranteed advertisements, and / or auction advertisements; the request to obtain the target pre-stored advertisement also carries information representing the advertisement type of the pre-stored advertisement; Determining the target pre-stored advertisement based on the current state of the pre-stored advertisement includes: Based on the advertised type, a pre-stored advertiser with the current priority is selected. A target pre-stored advertiser is determined from the pre-stored advertisers that meet the preset conditions in the current state. If the target pre-stored advertiser is not determined, it is determined whether the target pre-stored advertiser can be determined from the pre-stored advertisers with the next priority. Among them, the price-guaranteed and quantity-guaranteed advertisers have a higher priority than the price-guaranteed but quantity-not-guaranteed advertisers, and the price-guaranteed but quantity-not-guaranteed advertisers have a higher priority than the bidding advertisers.

3. The method according to claim 2, characterized in that, The step of determining the target pre-stored advertisement from the pre-stored advertisements that meet the preset conditions in the current state includes: If the current priority pre-stored ad is a price-guaranteed and quantity-guaranteed ad, then search for pre-stored ads that are currently within the ad delivery time period from the current priority pre-stored ads. If found, the probability of each pre-stored ad being selected is determined based on the current remaining display demand and remaining ad inventory of each pre-stored ad found; if a pre-stored ad is selected based on the selection probability of each pre-stored ad found, the selected pre-stored ad is taken as the target pre-stored ad. If no target ad is found, or if no target ad is selected based on the probability of selection for each target ad found, then it is determined that no target target ad has been identified from the target ads of the current priority.

4. The method according to claim 2, characterized in that, The step of determining the target pre-stored advertisement from the pre-stored advertisements that meet the preset conditions in the current state includes: If the current priority pre-stored ad is a price-guaranteed but quantity-guaranteed ad, then search for a pre-stored ad in the current priority pre-stored ad whose current ad placement status is allowed. If found, then the pre-stored ad with the smallest current ad playback progress among the found pre-stored ads is taken as the target pre-stored ad. If not found, then it is determined that no target pre-stored ad has been determined from the current priority pre-stored ads.

5. The method according to claim 2, characterized in that, The request to obtain the target pre-stored advertisement also carries client information that represents the client. The step of determining the target pre-stored advertisement from the pre-stored advertisements that meet the preset conditions in the current state includes: If the current priority pre-stored ad is a bidding ad, then if there is a pre-stored ad in the current priority pre-stored ad whose current ad placement status is allowed, then from the pre-stored ads whose current ad placement status is allowed, search for pre-stored ads whose current ad targeting conditions match the client information, and pre-stored ads whose ad targeting conditions do not exist; if found, then if the number of pre-stored ads found is 1, the found pre-stored ad is taken as the target pre-stored ad; if the number of pre-stored ads found is greater than 1, the pre-stored ad with the highest current estimated ad revenue among all the found pre-stored ads is taken as the target pre-stored ad. If no target pre-installed ad is found, or if there is no pre-installed ad in the current priority pre-installed ad list that is currently allowed to be served, it is determined that no target pre-installed ad has been identified from the current priority pre-installed ad list.

6. The method according to claim 1, characterized in that, The method further includes: The system receives a request from the client to retrieve pre-stored advertisements, the request carrying client information that identifies the client. Search the ad library for ads whose current ad targeting conditions match the client information, as well as ads for which no ad targeting conditions exist; If the found advertisements include at least one non-bid advertisement, then the selection probability of each non-bid advertisement is determined based on the current remaining display demand and remaining advertisement inventory of each non-bid advertisement; and at least one non-bid advertisement is selected as a pre-stored advertisement based on the selection probability of each non-bid advertisement. If the found advertisements include at least one bidding advertisement, the pre-trained advertising revenue prediction model is used to obtain the estimated advertising revenue of each bidding advertisement based on the current advertising price information of each bidding advertisement; and at least one bidding advertisement is selected as a pre-stored advertisement based on the estimated advertising revenue of each bidding advertisement. At least the identifiers, ad creatives, and selection probabilities of each selected pre-stored ad should be sent to the client.

7. An advertising inventory processing system, characterized in that, The system includes a client and a server; The client is used to receive the application launch command triggered by the user, and send a request to the server to obtain the target pre-stored advertisement and a request to obtain the real-time advertisement. The request to obtain the target pre-stored advertisement carries the identifiers of several pre-stored advertisements stored locally on the client. The server is used to receive requests from the client to obtain a target pre-stored advertisement and a request to obtain a real-time advertisement, and to determine the target pre-stored advertisement based on the current state of the pre-stored advertisement. The current status refers to the latest status of the advertisement obtained at the moment; At least the identifier of the target pre-stored advertisement should be sent to the client; The client is also configured to receive the identifier of the target pre-stored advertisement, so as to display the target pre-stored advertisement if the server fails to send the real-time advertisement to the client or the client fails to load the real-time advertisement.

8. An advertising inventory processing device, characterized in that, The device is used on a server side, and the device includes: The receiving module is used to receive requests from the client to obtain target pre-stored advertisements and requests to obtain real-time advertisements. The request to obtain target pre-stored advertisements carries the identifiers of several pre-stored advertisements stored locally by the client. The determining module is used to determine the target pre-stored advertisement based on the current state of the pre-stored advertisement; the current state refers to the latest state of the currently obtained advertisement. The sending module is configured to send at least the identifier of the target pre-stored advertisement to the client, so as to display the target pre-stored advertisement if the real-time advertisement is not successfully sent to the client or the client fails to load the real-time advertisement.

9. An electronic device, characterized in that, The electronic device includes: Processor; and A computer-readable storage medium storing computer program instructions that, when executed by the processor, cause the processor to perform the steps of the method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, cause the processor to perform the steps of the method as described in any one of claims 1 to 6.

Images