Information delivery method and device

Abstract

The invention discloses an information delivery method and device, and relates to the technical field of computers, the method comprises the following steps: obtaining at least one target delivery material and promotion configuration information of a target subject, the promotion configuration information comprising a plurality of promotion configuration items deployed by a promotion target subject and at least one configuration data corresponding to each promotion configuration item; combining at least one piece of configuration data of each target delivery material and each promotion configuration item to obtain at least one piece of delivery information; for each piece of putting information, putting a target putting material based on each piece of configuration data of the putting information to obtain respective putting effect data of each piece of putting information; determining a regulation and control strategy corresponding to the delivery effect data of each piece of delivery information; adjusting the delivery information based on the regulation and control strategy; according to the invention, the manpower cost of information release and the timeliness of release regulation and control can be obviously reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computers, in particular to an information putting method and device. BACKGROUND

[0002] With the development of the Internet industry, information putting and promotion on various Internet platforms (such as mobile Internet, etc.) has become the main form of information dissemination. For example, Internet advertising promotion for application programs or physical products is a typical representative of information putting, and has become an important way to expose and promote to target audiences.

[0003] Currently, the Internet advertising of a platform is usually defined by an advertising principal with various promotion configurations and follow-up advertising putting effects. In the advertising putting stage, the advertising with good effects is artificially amplified and the advertising with poor effects is timely processed. However, with the increasing number of products to be released and promoted, the advertising principal needs to create a large number of advertisements with different settings and maintain various promotion configurations before and during putting. The experience dependence degree and labor consumption cost are high, and the advertising principal is limited in manpower. Under the influence of multiple factors of advertising putting, a large number of advertising in putting is also difficult to be intervened and regulated in time according to the effects and cost budget. SUMMARY

[0004] The present application provides an information putting method, device, medium, equipment, server and program product, and the technical solutions are as follows:

[0005] In one aspect, the present application provides an information putting method, which comprises:

[0006] obtaining reference text data and a plurality of target text data of interface text resources to be detected in a target installation file, the text language of the reference text data and each target text data being different from each other;

[0007] detecting the text box occupation length of the reference text data and each target text data based on a preset text input control, the text input control being capable of adaptively adjusting the text box length based on the received input text length;

[0008] determining the target text data with the text box occupation length exceeding the text box occupation length of the reference text data as super-frame text data.

[0009] In another aspect, the present application provides an information putting method applied to a second end, wherein the second end runs a second application program with a second built-in plug-in, and the method comprises:

[0010] Based on the second built-in plugin, a target connection request is received from the backend server. The target connection request is generated by the first built-in plugin of the first end in response to the connection event of the first application to the second application. The target connection request carries a specified protocol domain name, and the specified protocol domain name points to the backend server corresponding to the first built-in plugin and the second built-in plugin.

[0011] Based on the second built-in plugin, the connection feedback information corresponding to the second application is sent to the backend server, so that the backend server forwards the connection feedback information to the first end, and the first end establishes a first long connection between the first built-in plugin and the backend server when the connection feedback information indicates that the connection is agreed.

[0012] On the other hand, this application provides an information delivery device, the device comprising:

[0013] First acquisition module: used to acquire the baseline text data and multiple target text data of the interface text resources to be detected in the target installation file, wherein the text languages ​​of the baseline text data and each of the target text data are different;

[0014] Length detection module: used to detect the length of the text box occupied by the baseline text data and each of the target text data based on a preset text input control. The text input control can adaptively adjust the length of the text box based on the length of the received input text.

[0015] The over-frame text determination module is used to determine target text data whose text box occupies a length exceeding that of the baseline text data as over-frame text data.

[0016] On the other hand, this application provides a computer-readable storage medium storing at least one instruction or at least one program, which is loaded and executed by a processor to implement the information delivery method as described above.

[0017] On the other hand, this application provides a computer device including a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the information delivery method as described above.

[0018] On the other hand, this application provides a computer program product, which includes computer instructions that, when executed by a processor, implement the information delivery method as described above.

[0019] On the other hand, this application provides a server that stores at least one instruction or at least one program, which is loaded and executed by a processor to implement the information delivery method described above.

[0020] The information delivery method, apparatus, medium, equipment, server, and program products provided in this application have the following technical effects:

[0021] The technical solution of this application obtains the target advertising materials and promotion configuration information of the target subject, and combines the configuration data of the target advertising materials and promotion configuration items to realize the automatic creation and automatic delivery of advertising information based on the needs of the advertiser. Based on the delivery effect data of each advertising information, the corresponding control strategy is determined to realize intelligent delivery and targeted delivery control of advertising information. This significantly reduces labor costs while improving the timeliness and effectiveness of advertising information effect control, thereby increasing the revenue of advertising information.

[0022] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0023] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of an application environment provided in an embodiment of this application;

[0025] Figure 2 This is a flowchart illustrating an information delivery method provided in an embodiment of this application;

[0026] Figure 3 This is a schematic diagram of the interface of a delivery management platform provided in an embodiment of this application;

[0027] Figure 4 This is another schematic diagram of the interface of a delivery management platform provided in an embodiment of this application;

[0028] Figure 5 This is another schematic diagram of the interface of a delivery management platform provided in an embodiment of this application;

[0029] Figure 6 This is a schematic diagram of a process for obtaining promotional configuration information provided in an embodiment of this application;

[0030] Figure 7 This is a schematic diagram illustrating the differences between the information delivery method provided in this application embodiment and the ordinary delivery method;

[0031] Figure 8 This is a schematic diagram illustrating the principle of bid adjustment provided in an embodiment of this application;

[0032] Figure 9 This is a schematic diagram illustrating the principle framework of a game advertising delivery method provided in an embodiment of this application;

[0033] Figure 10 This is a schematic diagram of the structural framework of an information delivery device provided in an embodiment of this application;

[0034] Figure 11 This is a schematic diagram of the hardware structure of a device for implementing an information delivery method, provided in an embodiment of this application. Detailed Implementation

[0035] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout.

[0036] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0037] Before providing a further detailed description of the embodiments of this application, the nouns and terms involved in the embodiments of this application will be explained, and the nouns and terms involved in the embodiments of this application shall be interpreted as follows.

[0038] Artificial intelligence (AI) is the theory, methods, technology, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. In other words, AI is a comprehensive technology within computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can react in a way similar to human intelligence. AI studies the design principles and implementation methods of various intelligent machines, enabling them to possess the functions of perception, reasoning, and decision-making.

[0039] Artificial intelligence (AI) is a comprehensive discipline encompassing a wide range of fields, including both hardware and software technologies. Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies primarily include computer vision, speech processing, natural language processing, and machine learning / deep learning.

[0040] In recent years, with the research and progress of artificial intelligence technology, artificial intelligence technology has been widely used in many fields. The solutions provided in the embodiments of this application involve artificial intelligence technologies such as machine learning / deep learning and natural language processing, which are specifically illustrated through the following embodiments.

[0041] Please see Figure 1 , Figure 1 This is a schematic diagram of an application environment provided in an embodiment of this application, such as... Figure 1 As shown, the application environment may include terminal 01 and server 02. In practical applications, terminal 01 and server 02 can be directly or indirectly connected via wired or wireless communication, and this application does not impose any restrictions on this.

[0042] Specifically, terminal 01 may include physical devices such as smartphones, desktop computers, tablets, laptops, digital assistants, augmented reality (AR) / virtual reality (VR) devices, smart voice interaction devices, smart home appliances, smart wearable devices, and in-vehicle terminal devices, and may also include software running on the physical devices, such as applications.

[0043] Specifically, Server 02 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Cloud technology refers to a hosting technology that unifies hardware, software, and network resources within a wide area network (WAN) or local area network (LAN) to achieve data computation, storage, processing, and sharing. Cloud technology can be applied to various fields, such as medical cloud, cloud IoT, cloud security, cloud education, cloud conferencing, artificial intelligence cloud services, cloud applications, cloud calling, and cloud social networking. Based on the cloud computing business model, cloud technology distributes computing tasks across a resource pool composed of a large number of computers, enabling various application systems to obtain computing power, storage space, and information services as needed. The network providing these resources is called the "cloud." From the user's perspective, the resources in the "cloud" are infinitely scalable, readily available, on-demand, expandable, and pay-as-you-go. As a provider of fundamental cloud computing capabilities, a cloud resource pool (referred to as a cloud platform, generally called IaaS (Infrastructure as a Service)) platform is established. Various types of virtual resources are deployed in the resource pool for external customers to choose from. The cloud resource pool mainly includes: computing devices (virtualized machines containing operating systems), storage devices, and network devices.

[0044] Specifically, the servers mentioned above may include physical devices, such as network communication submodules, processors, and memory, as well as software running on the physical devices, such as applications.

[0045] In this embodiment, terminal 01 can receive at least one target advertising material and promotion configuration information of a target subject submitted through an interface and send it to server 02. Server 02 then combines at least one configuration data item for each target advertising material and each promotion configuration item to obtain at least one advertising message. It then advertises the aforementioned advertising messages and obtains advertising effect data, and adjusts the advertising message based on the adjustment strategy corresponding to the advertising effect data. Alternatively, after receiving at least one target advertising material and promotion configuration information of a target subject, terminal 01 can directly perform the operations of information combination, advertising, effect acquisition, and adjustment on its own end.

[0046] Furthermore, it is understandable that Figure 1The example shown is merely an application environment for one information delivery method. This application environment may include more or fewer nodes, and this application does not impose any restrictions here.

[0047] It is understood that in the specific implementation of this application, data related to promotion configuration information and campaign performance data are involved. When the embodiments of this application are applied to specific products or technologies, permission or consent from users or relevant parties is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0048] Internet advertising can target both physical products and virtual products, such as games and applications. Advertisers run ads on advertising platforms to promote their applications and attract more new users. The typical advertising process for advertisers includes: 1) Before launching an ad campaign, advertisers create numerous ad placements, including setting ad placements, target bids, targeting (e.g., specific audience groups), and creative materials; 2) During the campaign, advertisers manually monitor the campaigns, adjusting creative materials and ad volume to avoid significant cost overruns; 3) After the campaign, advertisers review the performance of each creative material and promptly add new ads using high-quality materials. This process requires advertisers to create numerous ad placements daily for testing. The effectiveness of ad placements varies depending on factors such as the campaign scenario, target bid, and the quality of creative materials. Advertisers need to adjust their ad placements based on performance, such as adjusting promotional settings or ad placements, to avoid impacting their revenue. These all rely on the pitcher's manual monitoring and prior knowledge, which requires a lot of human resources from the advertiser and may result in problems such as untimely operation and poor reliability.

[0049] The following describes an information delivery method provided in this application, in conjunction with the aforementioned application environment. Figure 2 This is a flowchart illustrating an information delivery method provided in an embodiment of this application. This application provides method operation steps as shown in the embodiments or flowcharts, but based on conventional or non-inventive methods, more or fewer operation steps may be included. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only possible execution order. In actual system or server product execution, the method can be executed sequentially according to the embodiments or accompanying drawings, or in parallel (e.g., in a parallel processor or multi-threaded processing environment). Please refer to... Figure 2 The information delivery method provided in this application embodiment may include the following steps S201-S209:

[0050] S201: Obtain at least one target advertising material and promotion configuration information for the target entity.

[0051] Specifically, the target subject refers to the promotional project of the main product that the advertiser (such as the advertiser) needs to promote and publicize. This can be a promotional project for physical products, such as agricultural products, electronic products, or clothing and cosmetics, or a promotional project for virtual products, such as applications or paid knowledge products. In one example, the target subject is a game application. The advertiser, in turn, refers to the party that initiates the placement on an information delivery platform (such as an advertising platform). The target creative refers to the creative material currently determined for generating the delivery information (such as an advertisement). The creative material can take the form of one or more of the following, including but not limited to images, videos, audio, and text.

[0052] Specifically, the promotion configuration information includes multiple promotion configuration items deployed by the target entity and at least one configuration data corresponding to each promotion configuration item. The multiple promotion configuration items and corresponding configuration data in the promotion configuration information can be entirely submitted by the advertiser, or they can include data submitted by the advertiser and some data automatically generated by the system. For example, the multiple promotion configuration items may include, but are not limited to, targeting configuration items, bidding configuration items, placement configuration items, campaign time configuration items, and revenue configuration items. Correspondingly, the configuration data for each item may include the target audience corresponding to the targeting configuration item, the target bid corresponding to the bidding configuration item, the placement corresponding to the placement configuration item, the campaign time period corresponding to the campaign time configuration item, and the target rate of return corresponding to the revenue configuration item. It can be understood that each target entity can have more than one configuration data set for a single promotion configuration item to improve the flexibility and combination diversity of campaign information creation. For example, each target entity can set multiple target bids, multiple placements, or multiple campaign time periods.

[0053] Understandably, the configuration data can be submitted by the advertiser through the interface of the advertising management platform. The advertising management platform can set up an existing manual version of advertising, allowing advertisers to create, deliver, and control advertising information. It also sets up an automatic version, where advertisers only need to set at least some configuration data to achieve intelligent creation and delivery of advertising information through the platform. In this way, the data entry method for the manual and automatic versions is almost identical, reducing the additional learning and adaptation costs for advertisers.

[0054] In one example, refer to Figures 3-5 , Figure 3 The image shows an overview interface of the automated delivery version of the delivery management platform provided in one embodiment, which is used to display the basic information of each advertiser, including but not limited to the balance of the delivery account, the daily bidding expenditure, the daily bidding budget, advertising statistics, and the advertisements created today; Figure 4The image shows an automatic delivery version of the delivery management platform provided in one embodiment, which displays the basic information of each target entity, including but not limited to project name, smart delivery review status, delivery status, operation, delivery strategy, number of APP activations and number of payments, etc. Figure 5 This document illustrates an interface for filling in promotional configuration information during project creation on a campaign management platform provided in one embodiment. The interface may include settings windows for targeting options, campaign duration, and bid settings. Targeting configuration data may include specific targeting categories such as device type, region, or group type. The target bid can be set as a bid range, and multiple bid ranges can be set. The expected ROI (return on investment) can be specifically represented as the amount of money received from users acquired through the campaign information divided by the total cost of the campaign. During project creation, the campaign owner selects and fills in the campaign objectives through this interface, such as the aforementioned targeting configuration data, campaign duration, target bid, or expected return on investment.

[0055] In some embodiments, the currently determined target creative can be selected from the candidate creatives submitted by the advertiser. Accordingly, the acquisition method of at least one target creative includes S301-S305:

[0056] S301: Obtain at least two alternative ad creatives for the target subject and the historical ad performance data of the alternative ad creatives;

[0057] S303: For candidate creatives whose historical performance data is not empty, select the candidate creatives whose historical performance data meets the launch conditions as the creatives to be launched.

[0058] S305: Select target creatives from candidate creatives whose historical performance data is empty.

[0059] In a specific embodiment, when creating a promotional project corresponding to a target entity, the advertiser can submit various candidate advertising materials through the corresponding interface. Multiple candidate advertising materials for the same target entity can be uploaded in batches through the interface, such as uploading multiple promotional videos for the same project in batches and submitting corresponding copy. For example, in a game application project, candidate advertising materials may include endorsement promotions or selected clips of game operations, etc. When creating advertising information, the platform can automatically filter materials according to the backend strategy to create the advertising materials. The platform can provide cross-product combinations of multiple image materials, copy, and landing pages (advertising pages). More than one promotional project can be created for the same product.

[0060] Understandably, candidate creatives can be submitted to the platform for the first time or be creatives that have been used previously. The latter will store corresponding historical performance data. This historical performance data can correspond to a single candidate creative, such as a video clip, or it can correspond to a combination of candidate creatives, such as a combination of video clips and text. Historical performance data can include, but is not limited to, total campaign cost, impressions, clicks, click-through rate, conversions (such as app activations), and creative cost (such as conversion cost, for example, app activation cost). Creative cost refers to the resources consumed by the advertiser for a single new conversion target during the campaign of the candidate creative, such as the average creative cost obtained by dividing the total campaign cost of the candidate creative by the number of conversions.

[0061] Furthermore, for candidate creatives with historical performance data, based on the requirements of the campaign conditions (which can be determined based on the conversion goals selected by the advertiser, such as exposure exceeding the preset exposure, creative cost being lower than the preset cost, or activation count exceeding the preset conversion count), the corresponding performance data is selected for filtering. High-quality candidate creatives whose historical performance meets the campaign conditions are identified as the creatives to be launched, thereby determining a certain number of target creatives. For candidate creatives without historical performance data, target creatives can be determined by random selection.

[0062] If all candidate creatives for the target entity have historical performance data, a certain number of target creatives are directly selected from all the creatives to be launched. If none of the candidate creatives for the target entity have historical performance data, a certain number of target creatives are randomly selected from all the candidate creatives to explore the performance of new creatives. If both candidate creatives and candidate creatives without historical performance data exist, the selection priority of candidate creatives is higher than that of candidate creatives with no historical performance data. That is, if the quantity is sufficient, the proportion of candidate creatives in the generated ad placements is higher than that of candidate creatives with no historical performance data. This is to increase the resource investment in proven high-quality candidate creatives and improve the initial ad placement effect. At the same time, the ad placements generated by new creatives are configured to explore new creatives and increase the diversity of ad placement promotion.

[0063] Understandably, during the delivery of various campaigns for the target audience, there may be situations such as some campaigns being shut down or project budgets increasing. In such cases, it is necessary to provide alternative campaign information. This can be achieved by re-evaluating the historical performance data of each alternative campaign material to identify alternative campaign information from the updated campaign materials. Alternatively, alternative campaign information can be randomly selected from the remaining alternative campaign materials with empty historical performance data to supplement the campaign. This process can be repeated to achieve conversion of high-quality campaign materials and explore the effects of new campaign materials.

[0064] Understandably, if the target audience has a limited budget and needs to control promotion costs, the corresponding methods also include: determining the target quantity based on the target audience's budget and average promotion expenditure.

[0065] Specifically, the campaign budget is the maximum spending limit that a target entity can allocate. In some cases, the campaign budget refers to the maximum spending limit that the target entity can allocate at the initial creation of the project, and it remains unchanged after the target number is determined. In other cases, the campaign budget is the maximum spending limit that the target entity can currently allocate, meaning the campaign budget is updated in real time. As the project progresses, the total spending increases, and correspondingly, the project budget balance decreases, i.e., the campaign budget amount also decreases. If the advertiser increases the project budget or account limit, the campaign budget increases accordingly, and the target number also increases. For example, campaign budget = min(project budget, account budget / number of online projects, account balance / number of online projects), where the project budget refers to the total budget of the target entity's promotional projects, the account budget refers to the total budget of the advertiser's account for the target entity, the number of online projects refers to the number of target entities currently being advertised in the advertiser's account, and the account balance refers to the balance of the advertiser's account. In this way, determining the minimum value of the various budget amounts for projects and accounts as the campaign budget is beneficial for the rationality of quantity calculation and enables effective control of campaign spending.

[0066] Specifically, the average campaign spending is calculated by averaging the total actual spending across multiple historical campaigns. These multiple historical campaigns refer to all historical campaigns in the campaign management platform, all historical campaigns within a recent period, all historical campaigns for the same product category of the target entity, or all historical campaigns for the same product category of the target entity within a recent period. The data collection scope can be set based on actual needs, and this application does not impose any restrictions. The average calculation can be a simple average or a weighted average of the total actual spending across multiple historical campaigns. For example, the average campaign spending = total actual spending / N, where N is the number of the aforementioned multiple historical campaigns.

[0067] Specifically, the budget and target quantity are positively correlated, while the average ad spend is negatively correlated. For example, target quantity = budget / average ad spend. The target quantity refers to the upper limit on the types of ad messages that can be simultaneously delivered to a target audience. In other words, ad messages with the same creative and ad configuration are considered to be of the same type, while two ad messages with different creative or configuration data are considered to be of different types. Determining the target quantity in this way limits the number of ad messages generated for the same target audience, creating a reasonable number of ad messages. This avoids the problems of insufficient ad messages leading to low scaling and excessive ad messages causing budget shortages and ad contention, thus facilitating the effective amplification of high-performing ad messages during the campaign.

[0068] In some embodiments, the promotion configuration items include placement configuration items and bidding configuration items. The configuration data for the placement configuration item of each target entity includes at least one target placement, and the configuration data for the bidding configuration item of each target entity includes at least one target bid. The target bid refers to the resources that the target entity expects to consume for a single conversion target, which can specifically refer to the upper limit of the price that the advertiser expects to consume for a new conversion target. In normal advertising (i.e., manual version), the advertiser needs to set at least one target placement and the target bid for each target placement. The suggested target bids for different target placements are different. In smart advertising (i.e., automatic advertising version) scenario, if the advertiser chooses to advertise all placements or automatically advertise placements, the target placement and bid can be intelligently determined through the backend to optimize traffic delivery. Accordingly, in some embodiments, the method of obtaining the promotion configuration information in the reference figure includes S401-S405:

[0069] S401: Obtain multiple reference delivery information and reference performance data of the reference delivery information corresponding to the target subject;

[0070] S403: Based on the ranking of reference performance data, at least one valid reference delivery information is selected from multiple reference delivery information;

[0071] S405: Based on the historical placements and historical bids of each valid reference placement information, generate at least one target placement for the target subject's placement configuration items, at least one target bid for the bid configuration items, and the combination relationship between each target placement and each bid configuration item.

[0072] Specifically, the reference information includes at least one of the following: the target entity's historical campaign information, the target entity's product's historical campaign information, and the target entity's product category's historical campaign information. The selection priority of these three types of historical campaign information decreases progressively. The target entity's product's historical campaign information can refer to information previously campaigned by other entities (promotional projects) for the same product (e.g., a game application). The target entity's product category's historical campaign information refers to information previously campaigned by entities within the same category as the target entity's product. The sampling range for the reference campaign information can be a recent period, such as the past 7 days.

[0073] In one example, during the acquisition of reference placement information, historical placement information for the target entity can be searched based on the entity ID. If it exists, it is identified as multiple reference placement information. If it does not exist, the search continues for historical placement information with the same product ID, including historical placement information of other entities for the same product, such as other target entities placing placements on different operating systems (e.g., Android, iOS, or Windows). If it exists, it is identified as multiple reference placement information. If it does not exist, the search continues for historical placement information with the same product category ID, including historical placement information of other products in that product category, to identify multiple reference placement information. If it still does not exist, historical placement information of similar product categories or historical placement information from the overall platform can be selected as reference placement information to optimize placement selection. In this way, by identifying similar and more valuable placement information through the above method, the reliability of target placement determination is improved. Furthermore, if there is no data at the same entity level, it can be further rolled up to the product or category level, increasing the scope of reference data acquisition.

[0074] Specifically, the promotion configuration information for the reference placement information includes at least one historical placement position and at least one historical bid. The historical placement position refers to the target placement position set in the historical placement information, and the historical bid refers to the target bid set in the historical placement information.

[0075] Specifically, reference performance data is used to indicate the promotional effect generated by reference placement information. For example, the matching degree of historical placement cost and historical bid, conversion rate, placement cost, conversion volume, bid, and return on investment generated by the corresponding sampling historical period (such as the past seven days) of the reference placement information. The corresponding performance items can be sorted according to actual needs. For example, based on the matching degree mentioned above, the more matching, the higher the ranking, and vice versa; or based on placement cost, the lower the placement cost, the higher the ranking, and vice versa; or based on return on investment, the higher the return on investment, the higher the ranking, and vice versa. Then, the M reference placement information with the best performance in the ranking are determined as valid reference placement information.

[0076] Furthermore, the system analyzes historical placement and bid combinations for each valid reference placement, using these combinations as the target placement and bid for the current target audience, and retains the combinations between them. In this way, by learning from historical placement information and results (such as bid and cost achievement), the system identifies the optimal placement combinations and bid settings for cost-effectiveness or other performance, enabling the automatic generation of target placements and bids, thus improving intelligent advertising efficiency and conversion rates.

[0077] Alternatively, if multiple target bids have been set, the historical bids of the target placement can be matched with the current multiple target bids. The target bid that matches the historical bid is determined as the target bid for the current target placement. For example, if the historical bids of placements A / B / C are a / b / c respectively and gradually decrease, while the target bids currently configured for the target subject are a1 / b1 / c1 from high to low, then the target bids for placements A / B / C are determined as a1 / b1 / c1 in sequence.

[0078] In some embodiments, when multiple historical ad placements correspond to multiple target ad placements, the multiple target ad placements are classified based on the ranking of reference performance data to obtain ad placement categories for each target ad placement. Ad placement categories indicate the level of historical performance of the target ad placement. For example, based on the ranking of historical bids, multiple target ad placements are divided into optimal ad placements, exploration ad placements, and alliance ad placements, with historical bids gradually decreasing. Different ad placement categories correspond to different target bids; the higher the historical bid of an ad placement category, the higher its target bid, and vice versa. This approach of bidding by ad placement category aims to adapt to the goals of different ad placements.

[0079] Specifically, the better the historical performance of the placement category, the higher the allocation budget for the corresponding target placement during the campaign, and vice versa. For example, the proportion of the best placement, exploration placement, and affiliate placement in the generated campaign information gradually decreases in order to increase the promotion ratio of high-quality placements, ensure the promotion effect, and flexibly adjust the placements with lower performance so that when the performance is good, the allocation of their traffic can be increased, and when the performance is poor, the allocation can be tightened quickly, so as to help advertisers expand traffic and not affect the achievement of the desired results.

[0080] In one example, refer to Figure 6During the ad placement creation process, historical data is first acquired and filtered to remove data that does not meet the confidence threshold, thus obtaining valid historical data. Data that does not meet the confidence threshold may include historical ad placement information with too short a placement period or too low a conversion rate. Valid historical data for the same subject can be filtered first. If there is enough data, ad placement selection is performed directly. If not, the dimensions are rolled back up to the same product ID, other system platforms for the same product, the same product category (such as the game category), or the overall platform. For example, the identified target ad placements are A / B / C / D / E, sorted by ROI. The top 1 placements include A / B, the top 2 placements include A / C, and the top 3 placements include D / E. Ads (ad placement information) are generated based on the top 1 placements A and B and their corresponding target bids. These top 1 placements account for a relatively high percentage of the total number of ads created. In subsequent ad placements, the performance of these placements determines whether they need to be removed. For ads generated from the top 2 and top 3 placements, the percentage of ads generated from the top 2 and top 3 placements is lower than that of the top 2 and higher than that of the top 3. In subsequent ad placements, the performance of these top 2 and top 3 placements determines whether they need to be removed.

[0081] Understandably, in the smart advertising scenario, apart from the ad placement and bid, other promotion configuration items such as targeting and ad time can be set by the advertiser or automatically matched by the platform, and there are no restrictions here.

[0082] S203: Combine at least one configuration data of each target delivery material and each promotion configuration item to obtain at least one delivery information.

[0083] Understandably, each target creative can be configured with a set of configuration data, including various promotion configuration items, which are then combined into a single delivery message. The same target creative can be configured with different sets of configuration data to generate different delivery messages. Accordingly, S203 can include S501-S503:

[0084] S501: Determine at least one set of configuration datasets corresponding to each target delivery material;

[0085] S503: For each target delivery material, combine the target delivery material with each configuration dataset corresponding to the target delivery material to obtain at least one delivery information corresponding to the target delivery material.

[0086] Specifically, the configuration dataset includes configuration data corresponding to each promotion configuration item. For example, if there are six promotion configuration items, the configuration dataset contains six elements. In some cases, this configuration dataset can be generated through random combination or based on backend strategy combinations to generate diverse configurations for ad placement, expanding the diversity, flexibility, and exposure traffic dimensions of target audience promotion, thereby facilitating target selection and ad placement performance optimization.

[0087] In some embodiments, at least a portion of the configuration dataset includes target ad placements and target bids with the aforementioned combination relationship. As mentioned earlier, the pairing relationship between historical ad placements and historical bids in the valid reference ad placement information can be determined as the combination relationship between target ad placements and target bids. This combination relationship is retained when generating the configuration dataset to draw on configuration experience from excellent historical ad placement performance and improve the initial ad placement performance.

[0088] S205: For each delivery information, target delivery materials are delivered based on the configuration data of each delivery information to obtain the delivery performance data for each delivery information.

[0089] Specifically, the "deployment" here can refer to adding the target advertising material to the platform's ad recall library and storing its various configuration data (configuration dataset). This configuration dataset is used to set the display style, display position, or display period of the target advertising material during the deployment process, and is at least partially used as input data for recall, coarse ranking, and fine ranking to influence its recall ranking, coarse ranking, and fine ranking, thereby achieving the exposure of the advertising information.

[0090] Specifically, the system can periodically acquire campaign performance data after the current ad campaign has been displayed. For example, the data collection period can be 5 minutes, meaning the latest performance data is acquired in 5-minute granularity data streams. The campaign performance data can also be displayed through a user interface, allowing advertisers to view the performance of various creatives and campaign information on the platform and independently analyze high-performing creatives or information. For example, campaign performance data may include, but is not limited to, total campaign cost (e.g., total expenditure), impressions, clicks, click-through rate, conversions (e.g., app activations), conversion cost (e.g., app activation cost), conversion rate (e.g., activation rate), and return on investment. For instance, an ad might have a total expenditure of 3637.8, 30 app activations, and an app activation cost of 121.26.

[0091] S207: Determine the control strategy corresponding to the delivery effect data of each delivery information.

[0092] S209: Adjust the information released based on the control strategy.

[0093] Specifically, the campaign management platform sets multiple control strategies and corresponding campaign performance targets for each strategy. During the campaign, it can determine the appropriate campaign strategy based on performance data, thereby adjusting the campaign's configuration data, creative materials, or even stopping the campaign. Understandably, campaign performance data is continuously and periodically acquired during the campaign. Therefore, the control strategies corresponding to the performance data at different stages of the campaign are promptly adapted and flexibly adjusted to improve the relevance of the campaign to real-time performance, thereby optimizing campaign revenue.

[0094] In summary, the technical solution of this application obtains the target advertising materials and promotion configuration information of the target subject, and combines the configuration data of the target advertising materials and promotion configuration items to realize the automatic creation and automatic delivery of advertising information based on the needs of the advertiser. It also determines the corresponding control strategies based on the delivery effect data of each advertising information to achieve intelligent delivery and targeted delivery control of advertising information. This significantly reduces labor costs while improving the timeliness and effectiveness of advertising information effect control, thereby increasing the revenue of advertising information.

[0095] Understandably, in the manual version of ad creation and other normal campaign processes, reference is required. Figure 7 The traditional method requires advertisers to fill in configuration data to generate a plan, create ad configuration combinations based on the plan, and then generate ads for delivery based on creative materials. This method is only suitable for clients with sufficient experience. This application provides an additional intelligent delivery method. Advertisers (such as game advertisers) can switch to the automatic delivery version on the advertising management platform to activate the intelligent delivery scenario. The intelligent delivery product is changed from the original "account-plan-ad" hierarchy to the "account-project" hierarchy. Under the account, only the target entity needs to be created for the product, and its project-level promotion configuration information needs to be filled in. Only an intelligent delivery promotion project needs to be created; there is no need to create an ad for each creative combination. After creating an intelligent delivery promotion project, the advertiser does not need to perform any further operations; the backend automatically creates and delivers ads. The advertiser can also view the overall project's performance and independently start and pause the project. This method is suitable for advertisers with insufficient experience in ad delivery, or for scenarios where there is a shortage of manpower for large-scale promotion of new products such as new games.

[0096] It's important to note that the configuration data includes the target bid, and the performance data includes the current cost of campaigning. The current cost of campaigning refers to the average cost per conversion for a single user in the campaign. Specifically, during the campaign's execution, the current cost of campaigning can be determined based on the performance data. For example, the current cost of campaigning = total current cost of campaigning / number of conversions. By comparing the target bid with the current cost of campaigning, and then determining the corresponding adjustment strategy based on the comparison result, the target bid of the campaign can be adjusted to adapt to the performance and thus optimize the results.

[0097] In some embodiments, S207 may include S601: If the current delivery cost and target bid of the delivery information exceed the cost, and the degree to which the current delivery cost exceeds the target bid is greater than or equal to the cost overrun threshold, determine that the control strategy for the delivery information is to stop delivery. Accordingly, S209 may include S701: shut down the delivery of the information.

[0098] Specifically, over-cost refers to the resources actually consumed by the advertiser for a new conversion target exceeding the target bid currently configured for the ad. In other words, the current ad cost is greater than the target bid, indicating that the ad is wasting resources and performing poorly. Simultaneously, the degree of over-cost exceeding the target bid is calculated. This degree of over-cost can be set based on actual needs, such as as a percentage, multiple, or numerical value. The calculation methods are (current ad cost - target bid) / target bid, previous ad cost / target bid, and current ad cost - target bid, respectively. Correspondingly, the over-cost threshold refers to the upper limit of the over-cost level, corresponding to the form of the over-cost level. For example, the over-cost percentage, multiple, or numerical value can correspond to preset percentages, preset multiples, or preset over-cost values, respectively. When the over-cost level exceeds the over-cost threshold, it is determined that the ad is currently experiencing severe wastage. By promptly shutting down poorly performing promotional investments, reducing non-conversion costs during the ad exploration process, it is beneficial to supplement with high-performing ad content, improving ad performance and revenue.

[0099] In some embodiments, different over-cost thresholds are set for delivery information of different delivery duration categories. Accordingly, the method further includes: if the historical delivery duration of the delivery information meets the initial delivery category, the over-cost threshold corresponding to the delivery information is determined as a first threshold; if the historical delivery duration of the delivery information does not meet the initial delivery category, the over-cost threshold corresponding to the delivery information is determined as a second threshold. Here, historical delivery duration refers to the duration for which the delivery information has been delivered in the past. If the delivery information is being delivered for the first time and the cumulative duration of this delivery is less than or equal to a preset duration, it is determined to meet the initial delivery category, i.e., it is a new delivery information, and its over-cost threshold is the first threshold. If the over-cost threshold is in the form of an excess multiple, the first threshold can be, for example, 2.5 times. If the cumulative duration exceeds the preset duration, the over-cost threshold is determined as the second threshold, where the first threshold is higher than the second threshold. The second threshold can be, for example, 1.5 times. It is understandable that the over-cost threshold can be flexibly adjusted based on the main delivery needs or other factors. Thus, by setting a higher over-cost threshold for new delivery information, it can be given more opportunities for exploration, reducing the false shutdown rate.

[0100] In some embodiments, after the delivery information is turned off in S701, the method may further include:

[0101] S801: Filter the delivery information whose delivery performance meets the execution objectives based on the delivery performance data of each delivery information;

[0102] S803: Generate alternative delivery information based on the target delivery materials that meet the delivery information of the execution objectives;

[0103] S805: Deployment information for candidates.

[0104] Understandably, shutting down some ad placements will result in a reduction in exposure. To ensure traffic, alternative ad placements can be selected based on the current ad placement data to supplement the ad placements.

[0105] Specifically, the execution objective can be determined based on the advertiser's needs or the aforementioned advertising conditions, or it can be determined based on other factors related to optimizing advertising performance and revenue. For example, the execution objective can be defined as achieving cost targets and achieving a conversion rate higher than a preset conversion rate. This allows for the selection of target advertising creatives that meet the execution objective. These selected target advertising creatives are then combined with a corresponding generated configuration dataset to generate candidate advertising information. The corresponding generated configuration dataset can be randomly selected, extracted and combined from configuration data of currently valid advertising information (advertising information that has not been shut down), or generated based on other optimization strategies. In this way, after shutting down low-quality advertising information, high-quality creatives are selected based on advertising performance and prioritized for advertising creation as supplementary advertising, further expanding the exposure of proven high-quality creatives and improving revenue.

[0106] Understandably, after the release of the alternative release information, the aforementioned steps S205-S209 are repeated to continuously adjust and adapt.

[0107] In some embodiments, after S701 stops distributing information, the method further includes:

[0108] S807: Obtain updated campaign performance data for shut-down campaigns, including updated campaign costs;

[0109] S809: If the updated campaign cost and target bid indicate that the campaign cost has been reached or exceeded, the status of the suspended campaign will be updated to resume.

[0110] Specifically, the updated campaign performance data is obtained after the campaign has been shut down. It represents the campaign performance after a certain period of time. If the updated campaign cost achieves or exceeds the target cost, it indicates that the performance meets expectations, and the campaign can be updated to resume. This allows for the re-exploration of the campaign and resolves misjudgments caused by the lag between conversion time and exposure time. If the updated campaign cost and target bid indicator still exceed the target cost, the campaign will remain shut down.

[0111] Cost achievement refers to the matching of the resources actually consumed by the advertiser for a new conversion target with the advertiser's bid. Matching here means that the advertiser's cost or average cost over a period of time is equal to the advertiser's bid, or the advertiser's cost or average cost fluctuates within a preset range relative to the advertiser's bid.

[0112] In some embodiments, reference is made to Figure 8S207 may include S603: If the current delivery cost and target bid of the delivery information exceed the cost, and the degree of excess of the current delivery cost relative to the target bid is less than the excess cost threshold, the adjustment strategy for the delivery information is determined to be to lower the delivery bid of the delivery information based on a preset adjustment step size. Understandably, during the delivery process, the actual delivery bid is positively correlated with recall rate, fine-grained ranking, or coarse-grained ranking; that is, the higher the target bid, the higher the exposure probability, and vice versa. When initially delivering to the target subject, the delivery bid is set to the target bid. The adjustment strategy based on subsequent delivery performance data can lower or raise the actual delivery bid. For delivery information that exceeds the cost but is not severely underutilized, its delivery volume is controlled by lowering its delivery bid, so that delivery information that has not reached its cost target minimizes cost consumption during the exploration phase. It should also be noted that the exposure probability of ad placement information is affected by multiple factors, such as the bid price or the suitability between the target audience set in the promotion configuration and the current target subject. This suitability can be determined by the intelligent model in the ad recall database. The higher the suitability, the higher the exposure probability, and vice versa. Therefore, by appropriately reducing the bid price, the influence of suitability can be increased in reverse, thereby increasing the exposure of ad placement information that has not achieved the cost target in the target audience with a higher predicted conversion rate by the model, thus helping to improve its effectiveness.

[0113] Accordingly, S209 may include:

[0114] S703: Determine the premium of the current campaign cost relative to the target bid;

[0115] S705: The reduction is calculated based on the preset control step size and the overflow price to obtain the reduction value;

[0116] S707: Adjust the bid for ad placement based on the reduction value. The bid is positively correlated with the exposure probability of ad placement.

[0117] Specifically, the overflow price refers to the excess of the current campaign cost over the target bid. The reduction value calculated based on the preset adjustment step size is less than the overflow price to control the bid reduction range and avoid excessive adjustment that could lead to deviations in the exploration results. In some embodiments, the preset adjustment step size is a positive number less than 1, used as the adjustment coefficient for the overflow price. The updated campaign bid = original campaign bid - (current campaign cost - target bid) * preset adjustment step size, where current campaign cost - target bid refers to the overflow price.

[0118] In some embodiments, reference is made to Figure 8S207 can include S605: If the current campaign cost and target bid indication cost of the campaign information exceed the target, the adjustment strategy for the campaign information is determined to be to increase the campaign bid based on a preset adjustment step size. Cost exceeding the target means that the actual campaign cost consumed for a single new conversion target is lower than the target bid. This can be because the campaign cost or the average campaign cost within the statistical period is lower than the target bid, or the difference between the campaign cost or the average campaign cost within the statistical period and the target cost is greater than a preset value, such as less than 0.9 times the target bid. In other words, if the current campaign cost is lower than the target bid but the cost target is not met, it is determined to be a cost exceeding the target. Increasing the bid appropriately can increase its competitiveness, help further increase traffic, and amplify the performance of campaign information with good results.

[0119] Accordingly, S209 may include:

[0120] S709: Determine the shortfall in current campaign costs relative to the target bid;

[0121] S711: Calculate the increase value based on the preset control step size and the unmet quota;

[0122] S713: Adjust the bid for the placement information based on the increase value.

[0123] Specifically, the "missing bid" refers to the difference between the current campaign cost and the target bid. The increase calculated based on the preset adjustment step size is less than this difference to control the bid increase and avoid excessive adjustments that could lead to deviations in the exploration results and negative impacts on the overall performance. In some embodiments, the preset adjustment step size is a positive number less than 1, used as an adjustment coefficient for the missing bid. The updated campaign bid = original campaign bid - (current campaign cost - target bid) * preset adjustment step size, where the target bid - current campaign cost represents the missing bid.

[0124] In some embodiments, reference is made to Figure 8 S207 may include S607: If the current campaign cost and the target bid indication cost of the ad placement are achieved, determine that the adjustment strategy for the ad placement is to maintain the ad placement bid. Cost achievement means that the actual campaign cost consumed for a single new conversion target matches the target bid. Correspondingly, S209 may include S715: Maintain the ad placement bid of the ad placement. In this way, the ad placement bid of the ad placement that has achieved cost achievement is not adjusted, so as to maintain its traffic while effectively controlling the campaign cost.

[0125] Furthermore, in some embodiments, adjusting the delivery information based on the control strategy also includes: increasing the delivery volume of delivery information achieved at a higher cost, where the delivery volume is positively correlated with the exposure probability. The delivery volume refers to the number of the same delivery information in the delivery recall database. By replicating delivery information achieved at a higher cost, its exposure probability can be further increased, thereby further improving the traffic of high-quality information.

[0126] Understandably, after a statistical period of campaign performance data, the campaign information is adjusted once. In the next statistical period, this adjustment process is repeated, and so on, to control the configuration, shutdown, and restart of the campaign information in real time. This adapts the campaign to cost control and performance requirements, avoiding manual deployment while optimizing performance. In one example, based on actual campaign data from a game application, the method described in this application reduces the cost of creating one smart campaign targeting a specific subject by 8.84 units compared to a typical campaign. Furthermore, the activation cost (campaign cost) and first-day paid ROI of the game smart campaign are both superior to those of typical campaigns.

[0127] In some embodiments, during the process of adjusting the delivery information based on the control strategy, the upper and lower limits of the bid ceiling and bid floor corresponding to the target bid of the delivery information limit the increase and decrease of the target bid. The upper bid ceiling is higher than the target bid, and the lower bid floor is lower than the target bid. Both are obtained by adjusting the target bid, and the adjustment range can be set and flexibly adjusted based on actual needs. That is, the lower bid floor ≤ the updated delivery bid ≤ the upper bid ceiling. For example, the upper bid ceiling can be 1.1 times the target bid, and the lower bid floor can be 0.9 times the target bid, that is, target bid * 90% ≤ updated delivery bid ≤ target bid * 110%. In this way, upper and lower bound protection is set for the price adjustment strategy, which can prevent the bid adjustment range from being too large, causing excessive fluctuations in the effect of the delivery information, and avoiding problems such as the inability to adjust in a timely manner.

[0128] It should be noted that the target bid in the above adjustment process can be replaced with the target ROI (the ROI set by the advertiser), and the current campaign cost can be replaced with the current actual ROI. The difference between the current actual ROI and the target ROI can then be used to adjust the campaign bid or to shut down or restart the campaign. Other performance data can also be used for optimization, but these will not be listed here.

[0129] The following combination Figure 9This paper uses a promotional project targeting a game application and advertising information as an example to introduce the information delivery method of this application. First, the advertiser operates on the delivery platform: creating one or more projects, specifically including filling in the configuration data of the promotion configuration items to generate a plan, including budget configuration data, target bid, targeting configuration data, and creatives (alternative delivery materials). Further, a smart controller is set on the smart delivery platform. For the first project creation: multiple ads are created based on the aforementioned method, each ad has a corresponding ad bid (target bid), and the project's ad budget can also be set. During ad creation, more budget can be allocated to ads combining high-quality creatives (target delivery materials) and ad placements, such as creating higher target bids, while a small amount of exploratory budget is allocated to new creatives and ad placements with unknown effects. Further, the created ads are placed in the ad playback recall database, and traffic is driven and exposed through recall, coarse ranking, and fine ranking, generating performance logs to record delivery performance data in real time. Furthermore, during the campaign, subsequent adjustments are made based on campaign performance data: performance logs are statistically analyzed to determine the cost achievement and wasted resources of each ad. Then, models predicting high-quality ads and high-quality audiences are used to output the categories of each ad campaign, including high-quality ads (ads that achieved cost targets), potential ads (ads that exceeded or failed to meet cost targets, the latter being ads with slight cost overruns), and low-quality ads (ads whose cost exceeded the over-cost threshold, i.e., wasted resources or severe cost overruns). The system can also output the high-quality audience corresponding to the current project. Subsequently, low-quality ads are shut down, the number of high-quality ads is replicated and budget allocation is increased, and price adjustments are made for potential ads. Finally, strategy tools are used to execute campaigns, such as configuring one-click scaling and scaling boosters for high-quality ads.

[0130] Based on the above solution, game advertisers create smart advertising projects on the advertising platform, setting the placement, targeting, bid, and creative materials to be used. The smart advertising controller obtains the latest project information through transaction data and builds a periodic log data stream acquisition module to obtain the latest performance data. Based on the advertiser's needs and actual advertising results, a series of strategy adjustments are made. Through the intelligent advertising strategy of game ads, an automated advertising solution is provided for advertisers, and ads are automatically adjusted according to the advertising results. This frees up human resources for advertisers, explores the optimal advertising combination, and improves advertising results through timely strategy optimization while reducing the advertiser's manpower.

[0131] This application embodiment also provides an information delivery device 900, such as... Figure 10 As shown, Figure 10 The diagram shows a structural schematic of an information delivery device according to an embodiment of this application. The device may include the following modules:

[0132] First acquisition module 10: used to acquire at least one target delivery material and promotion configuration information of the target entity. The promotion configuration information includes multiple promotion configuration items deployed by the target entity and at least one configuration data corresponding to each promotion configuration item.

[0133] Combination Module 20: Used to combine at least one configuration data of each target delivery material and each promotion configuration item to obtain at least one delivery information;

[0134] Delivery module 30: is used to deliver target delivery materials for each delivery message based on the configuration data of the delivery message, and obtain the delivery effect data of each delivery message.

[0135] Strategy determination module 40: Used to determine the control strategy corresponding to the delivery effect data of each delivery information;

[0136] Control module 50: Used to adjust the delivery information based on the control strategy.

[0137] In some embodiments, the first acquisition module 10 includes:

[0138] The first acquisition submodule is used to acquire at least two alternative advertising materials for the target subject and the historical performance data of the alternative advertising materials.

[0139] The first determination submodule is used to determine the candidate creatives whose historical performance data is not empty and which meet the advertising conditions as the creatives to be deployed.

[0140] The first filtering submodule is used to filter target creatives from candidate creatives that are to be launched and whose historical performance data is empty. The filtering priority of the creatives to be launched is higher than that of candidate creatives whose historical performance data is empty.

[0141] In some embodiments, the apparatus further includes:

[0142] Quantity Determination Module: The target quantity is determined based on the target entity's advertising budget and average promotion spending. The advertising budget is the upper limit of spending that the target entity can allocate. The average promotion spending is calculated by averaging the total actual spending of multiple historical advertising messages. The target quantity refers to the upper limit of the types of advertising messages that can be simultaneously delivered to the target entity.

[0143] In some embodiments, the promotion configuration items include placement configuration items and bidding configuration items. The configuration data of the placement configuration item for each target entity includes at least one target placement, and the configuration data of the bidding configuration item for each target entity includes at least one target bid. The target bid refers to the resources that the target entity expects to consume for a single conversion. The first acquisition module 10 may include:

[0144] Reference Acquisition Submodule: Used to acquire multiple reference placement information and reference performance data of the reference placement information corresponding to the target entity. The multiple reference placement information includes at least one of the historical placement information of the target entity, the historical placement information of the product to which the target entity belongs, and the historical placement information of the product category to which the target entity belongs. The promotion configuration information of the reference placement information includes at least one historical placement position and at least one historical bid.

[0145] The second filtering submodule is used to filter out at least one valid reference delivery information from multiple reference delivery information based on the sorting of reference performance data.

[0146] Configuration generation submodule: Based on the historical placements and historical bids of each valid reference placement information, it generates at least one target placement for the target subject, at least one target bid for the bid configuration item, and the combination relationship between each target placement and each bid configuration item.

[0147] In some embodiments, the combination module 20 includes:

[0148] Configuration set submodule: used to determine at least one configuration dataset corresponding to each target delivery creative. The configuration dataset includes configuration data corresponding to each promotion configuration item. At least part of the configuration dataset includes target delivery positions and target bids that have a combination relationship.

[0149] Combination submodule: Used to combine the target delivery material with each configuration dataset corresponding to the target delivery material for each target delivery material, so as to obtain at least one delivery information corresponding to the target delivery material.

[0150] In some embodiments, the configuration data includes the target bid, and the campaign performance data includes the current campaign cost. The strategy determination module 40 is used to: if the current campaign cost and the target bid of the campaign information indicate that the cost exceeds the target bid, and the degree to which the current campaign cost exceeds the target bid is greater than or equal to the cost exceeding threshold, determine that the control strategy for the campaign information is to stop the campaign; the current campaign cost refers to the average campaign cost of a single conversion target corresponding to the campaign information.

[0151] The control module 50 is used for: shutting down delivery information.

[0152] In some embodiments, the strategy determination module 40 is specifically used for:

[0153] If the historical delivery duration of the delivery information meets the initial delivery category, the over-cost threshold corresponding to the delivery information is determined as the first threshold.

[0154] If the historical delivery duration of the delivery information does not meet the initial delivery category, the excess cost threshold corresponding to the delivery information is determined as the second threshold, and the first threshold is higher than the second threshold.

[0155] In some embodiments, the delivery module 30 is further configured to: after shutting down delivery information, filter delivery information whose delivery effect meets the execution target based on the delivery effect data of each delivery information; generate candidate delivery information based on the target delivery material of the delivery information that meets the execution target; and deliver the candidate delivery information.

[0156] In some embodiments, the delivery module 30 is further configured to: after shutting down the delivery information, obtain updated delivery performance data of the shut-down delivery information, the updated delivery performance data including updated delivery cost; if the updated delivery cost and the target bid indicate that the delivery information cost has been achieved or exceeded, update the status of the shut-down delivery information to resume delivery.

[0157] In some embodiments, the configuration data includes the target bid, and the strategy determination module 40 is further configured to: if the current delivery cost and the target bid of the delivery information indicate an over-cost, and the degree of over-cost of the current delivery cost relative to the target bid is less than the over-cost threshold, determine that the adjustment strategy of the delivery information is to lower the delivery bid of the delivery information based on a preset adjustment step size;

[0158] The adjustment module 50 is used to: determine the overflow price of the current placement cost relative to the target bid; calculate the reduction based on the preset adjustment step size and overflow price to obtain the reduction value; and lower the placement bid of the placement information based on the reduction value, wherein the placement bid is positively correlated with the exposure probability of the placement information.

[0159] In some embodiments, the configuration data includes the target bid, the campaign performance data includes the current campaign cost, and the strategy determination module 40 is further configured to: if the current campaign cost and the target bid indication cost of the campaign information exceed the target bid, determine that the adjustment strategy of the campaign information is to increase the campaign bid of the campaign information based on a preset adjustment step size;

[0160] The control module 50 is used to: determine the amount that the current delivery cost has fallen short of the target bid; calculate the increase based on the preset control step size and the amount that has fallen short, and obtain the increase value; and increase the delivery bid of the delivery information based on the increase value.

[0161] In some embodiments, the configuration data includes the target bid, the campaign performance data includes the current campaign cost, and the strategy determination module 40 is further configured to: if the current campaign cost of the campaign information and the target bid indication cost are reached, determine that the adjustment strategy of the campaign information is to maintain the campaign bid of the campaign information;

[0162] The control module 50 is used to maintain the bid price for the delivery of information.

[0163] In some embodiments, the control module 50 is also used to: increase the amount of information delivered at the cost achieved, wherein the amount of information delivered is positively correlated with the exposure probability.

[0164] In some embodiments, during the process of adjusting the delivery information based on the control strategy, the upper and lower limits of the target bid corresponding to the target bid information limit the increase and decrease of the target bid.

[0165] It should be noted that the apparatus provided in the above embodiments is only illustrated by the division of the above functional modules when implementing its functions. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0166] This application provides a computer device including a processor and a memory. The memory stores at least one instruction or at least one program, which is loaded and executed by the processor to implement an information delivery method as provided in the above method embodiments.

[0167] Figure 11 A schematic diagram of the hardware structure of a device for implementing an information delivery method provided in an embodiment of this application is shown. The device may constitute or include the apparatus or system provided in the embodiment of this application. Figure 11 As shown, device 10 may include one or more processors 1002 (shown as 1002a, 1002b, ..., 1002n in the figure) 1002 (processor 1002 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 1004 for storing data, and a transmission device 1006 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 11 The structure shown is for illustrative purposes only and does not limit the structure of the electronic device described above. For example, device 10 may also include a... Figure 11 The more or fewer components shown, or having the same Figure 11 The different configurations shown.

[0168] It should be noted that the aforementioned one or more processors 1002 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be wholly or partially integrated into any other element within device 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0169] The memory 1004 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the method in this embodiment. The processor 1002 executes various functional applications and data processing by running the software programs and modules stored in the memory 1004, thereby realizing the above-described information delivery method. The memory 1004 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 1004 may further include memory remotely located relative to the processor 1002, and these remote memories can be connected to the device 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0170] The transmission device 1006 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of device 10. In one example, the transmission device 1006 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 1006 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0171] The display may be, for example, a touchscreen liquid crystal display (LCD) that allows a user to interact with the user interface of device 10 (or a mobile device).

[0172] This application embodiment also provides a computer-readable storage medium, which can be disposed in a server to store at least one instruction or at least one program related to implementing an information delivery method in the method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the information delivery method provided in the above method embodiment.

[0173] Optionally, in this embodiment, the storage medium may be located at at least one of the multiple network servers in a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0174] This invention also provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform an information delivery method provided in the various optional embodiments described above.

[0175] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are also possible or may be advantageous.

[0176] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device, equipment, and storage medium embodiments are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0177] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0178] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. An information delivery method, characterized in that, The method includes: Obtain at least one target advertising material and promotion configuration information for the target entity, wherein the promotion configuration information includes multiple promotion configuration items deployed for the target entity and at least one configuration data corresponding to each of the promotion configuration items; Combine at least one configuration data of each of the target delivery materials and each of the promotion configuration items to obtain at least one delivery information; For each delivery information, the target delivery material is delivered based on the configuration data of the delivery information, thereby obtaining the delivery effect data for each delivery information. Determine the control strategy corresponding to the delivery effect data of each of the aforementioned delivery information; The delivery information is adjusted based on the aforementioned control strategy.

2. The method according to claim 1, characterized in that, The methods for obtaining the at least one target delivery material include: Obtain at least two alternative ad creatives for the target entity and historical ad performance data for the alternative ad creatives; For candidate creatives whose historical performance data is not empty, the candidate creatives whose historical performance data meets the delivery conditions are determined as creatives to be delivered. The target creative is selected from the creative to be launched and the candidate creatives whose historical performance data is empty. The creative to be launched has a higher selection priority than the candidate creatives whose historical performance data is empty.

3. The method according to claim 1, characterized in that, The method further includes: The target quantity is determined based on the target entity's advertising budget and average promotional spending. The advertising budget is the upper limit of the spending amount that the target entity can allocate. The average promotional spending is calculated by averaging the total actual spending of multiple historical advertising information. The target quantity refers to the upper limit of the types of advertising information that can be simultaneously advertised to the target entity.

4. The method according to claim 1, characterized in that, The promotion configuration items include placement configuration items and bidding configuration items. The configuration data for the placement configuration item of each target entity includes at least one target placement. The configuration data for the bidding configuration item of each target entity includes at least one target bid. The target bid refers to the resources that the target entity expects to consume for a single conversion. The promotion configuration information is obtained through the following methods: Obtain multiple reference placement information corresponding to the target entity and reference performance data of the reference placement information. The multiple reference placement information includes at least one of the historical placement information of the target entity, the historical placement information of the product to which the target entity belongs, and the historical placement information of the product category to which the target entity belongs. The promotion configuration information of the reference placement information includes at least one historical placement position and at least one historical bid. Based on the ranking of the reference performance data, at least one valid reference delivery information is selected from the plurality of reference delivery information; Based on the historical placements and historical bids of each of the valid reference placement information, at least one target placement for the placement configuration item of the target subject, at least one target bid for the bid configuration item, and the combination relationship between each of the target placements and each of the bid configuration items are generated.

5. The method according to claim 4, characterized in that, The step of combining at least one configuration data of each of the target delivery materials and each of the promotion configuration items to obtain at least one delivery information includes: Determine at least one set of configuration datasets corresponding to each of the target delivery materials, wherein the configuration datasets include configuration data corresponding to each of the promotion configuration items, and at least a portion of the configuration datasets include target delivery positions and target bids with the aforementioned combination relationship; For each target delivery material, the target delivery material is combined with each of the configuration datasets corresponding to the target delivery material to obtain at least one delivery information corresponding to the target delivery material.

6. The method according to any one of claims 1-5, characterized in that, The configuration data includes the target bid, the campaign performance data includes the current campaign cost, and the control strategy for determining the campaign performance data corresponding to each campaign information includes: If the current campaign cost and target bid of the campaign information indicate that the cost is exceeded, and the degree to which the current campaign cost exceeds the target bid is greater than or equal to the cost exceedance threshold, the adjustment strategy for the campaign information is determined to be to stop campaigning; the current campaign cost refers to the average campaign cost of a single conversion target corresponding to the campaign information. The adjustment of the delivery information based on the control strategy includes: shutting down the delivery information.

7. The method according to claim 6, characterized in that, The method further includes: If the historical delivery duration of the delivery information meets the initial delivery category, the over-cost threshold corresponding to the delivery information is determined as the first threshold. If the historical delivery duration of the delivery information does not meet the initial delivery category, the over-cost threshold corresponding to the delivery information is determined to be the second threshold, and the first threshold is higher than the second threshold.

8. The method according to claim 6, characterized in that, After shutting down the delivery information, the method further includes: Based on the delivery performance data of each of the aforementioned delivery information, delivery information whose performance meets the execution objectives is selected; Based on the target delivery materials that meet the execution objectives, candidate delivery information is generated; The candidate deployment information is then deployed.

9. The method according to claim 6, characterized in that, After shutting down the delivery information, the method further includes: Obtain updated campaign performance data for the suspended campaign information, wherein the updated campaign performance data includes updated campaign costs; If the updated delivery cost and the target bid indicate that the delivery cost has been met or exceeded, the status of the suspended delivery information will be updated to resume delivery.

10. The method according to any one of claims 1-5, characterized in that, The configuration data includes the target bid, the campaign performance data includes the current campaign cost, and the control strategy for determining the campaign performance data corresponding to each campaign information includes: If the current delivery cost and target bid of the delivery information indicate that the cost exceeds the target bid, and the degree to which the current delivery cost exceeds the target bid is less than the cost exceeding threshold, the adjustment strategy for the delivery information is determined to be to lower the delivery bid of the delivery information based on a preset adjustment step size. The adjustment of the delivery information based on the control strategy includes: Determine the premium of the current deployment cost relative to the target bid; The reduction value is obtained by calculating the reduction based on the preset adjustment step size and the overflow price; The bid for the ad placement is lowered based on the reduction value, and the bid is positively correlated with the exposure probability of the ad placement.

11. The method according to any one of claims 1-5, characterized in that, The configuration data includes the target bid, the campaign performance data includes the current campaign cost, and the control strategy for determining the campaign performance data corresponding to each campaign information includes: If the current campaign cost and the target bid indication cost of the campaign information exceed the target bid, the adjustment strategy for the campaign information is determined to be to increase the campaign bid based on a preset adjustment step size. The cost exceeding the target bid means that the actual campaign cost consumed for a single new conversion target is lower than the target bid. The adjustment of the delivery information based on the control strategy includes: Determine the amount by which the current campaign cost falls short of the target bid; The increase value is obtained by calculating the increase based on the preset adjustment step size and the unmet limit; The bid price for the delivery information is increased based on the increase value.

12. The method according to any one of claims 1-5, characterized in that, The configuration data includes the target bid, the campaign performance data includes the current campaign cost, and the control strategy for determining the campaign performance data corresponding to each campaign information includes: If the current campaign cost and the target bid indication cost of the campaign information are reached, the adjustment strategy of the campaign information is determined to be to maintain the campaign bid of the campaign information. The cost reaching means that the actual campaign cost consumed for a single new conversion target matches the target bid. The adjustment of the delivery information based on the control strategy includes: Maintain the bidding price for the aforementioned ad placement information.

13. The method according to claim 12, characterized in that, The adjustment of the delivery information based on the control strategy also includes: The increased cost achieves the desired amount of information delivered, and the amount delivered is positively correlated with the exposure probability.

14. The method according to any one of claims 1-5, characterized in that, In the process of adjusting the delivery information based on the control strategy, the upper and lower limits of the target bid corresponding to the target bid information limit the increase and decrease of the target bid.

15. An information delivery device, characterized in that, The device includes: First acquisition module: used to acquire at least one target delivery material and promotion configuration information of the target entity, wherein the promotion configuration information includes multiple promotion configuration items deployed for the target entity and at least one configuration data corresponding to each of the promotion configuration items; Combination module: used to combine at least one configuration data of each of the target delivery materials and each of the promotion configuration items to obtain at least one delivery information; The delivery module is used to deliver the target delivery material based on the configuration data of each delivery information for each delivery information, and to obtain the delivery effect data of each delivery information. Strategy determination module: used to determine the control strategy corresponding to the delivery effect data of each delivery information; Control module: Used to adjust the delivery information based on the control strategy.

Images