Advertisement putting method, electronic equipment and storage medium

Abstract

The invention provides an advertisement putting method, electronic equipment and a storage medium, and relates to the technical field of advertisement putting. The method comprises the steps that value features and demand features generated by a user on a business platform within historical duration are acquired, the value features are used for indicating consumption ability of the user, and the demand features are used for indicating business demands of the user; according to the value features, the demand features and a preset material template library, synthesizing advertisement materials corresponding to the user; sending the advertisement material to a media platform, receiving a material identifier sent by the media platform, and pairing and storing the material identifier and a device identifier of a user; and after a delivery request sent by the media platform is received, under the condition of determining that the user participates in competition, generating a competition participation price according to a preset competition participation label, obtaining a material identifier according to the equipment identifier, and sending the material identifier and the competition participation price to the media platform, so that the media platform exposes an advertisement material to the user according to the material identifier. Therefore, the advertisement putting effect is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of advertisement delivery, and in particular to an advertisement delivery method, an electronic device and a storage medium. BACKGROUND

[0002] With the rapid development of digital marketing, placing advertisements on media platforms has become a main means for advertisers to reach target audiences. Among the existing various advertisement delivery modes, direct advertisement is widely used because of its simple operation and full use of the advantages of media platforms.

[0003] Direct advertisement allows advertisers to create advertisements using user data and advertisement generation algorithms of media platforms through an application programming interface (API) or directly on the media platform, and deliver the advertisements to users on the media platform.

[0004] However, in the direct advertisement method, only user data mastered by the media platform can be used to generate advertisements, and user data mastered by the advertiser cannot be used, resulting in a low matching degree between the advertisements and the users, thereby affecting the effect of advertisement delivery. SUMMARY

[0005] The present application provides an advertisement delivery method, an electronic device and a storage medium to solve the problem that only user data mastered by the media platform can be used to generate advertisements, and user data mastered by the advertiser cannot be used, resulting in a low matching degree between the advertisements and the users, thereby affecting the effect of advertisement delivery, and achieves the purpose of improving the effect of advertisement delivery.

[0006] In a first aspect, the present application provides an advertisement delivery method, comprising: obtaining value features and demand features of a user generated on a business platform within a historical time period; the value features are used to indicate the consumption ability of the user, and the demand features are used to indicate the business demand of the user; synthesizing advertisement materials corresponding to the user according to the value features, the demand features and a preset material template library; sending the advertisement materials to a media platform, receiving material identifiers sent by the media platform, and pairing and storing the material identifiers and device identifiers of the user; after receiving a delivery request sent by the media platform, generating a participation price according to a preset participation label in a case where it is determined that the user participates, and obtaining the material identifiers according to the device identifiers; the delivery request is used to request to deliver the advertisements, the delivery request carries the device identifiers, and the preset participation label is used to indicate the value of the participation of the user; sending the material identifiers and the participation price to the media platform, so that the media platform exposes the advertisement materials to the user according to the material identifiers.

[0007] In a possible design, the preset material template library includes a plurality of material templates, each of which corresponds to a material type and a material weight, and the synthesizing of the advertisement material corresponding to the user according to the value feature, the demand feature, and the preset material template library includes: determining the target type according to the value feature; determining, as candidate templates, the material templates in the preset material template library whose material types are the target type; determining, as the target template, a material template from the candidate templates according to the material weight corresponding to the candidate template; synthesizing the advertisement material corresponding to the user according to the target template and the demand feature.

[0008] In a possible design, the determining, as the target template, a material template from the candidate templates according to the material weight corresponding to the candidate template includes: calculating the sum of all the material weights corresponding to the candidate templates; generating a random number uniformly distributed between 0 and the sum; determining, as the target template, a material template from the candidate templates according to the random number and the material weight corresponding to each of the candidate templates.

[0009] In a possible design, after the user is exposed to the advertisement material, the method further includes: obtaining, for each material template, effect data in a historical period, the effect data including a total number of clicks, a total number of exposures, a total number of activations, a total number of plays, a total number of play completions, an average stay duration, an average play progress, and an average click price; performing normalization processing on each of the effect data corresponding to the material template, for each material template; calculating a new weight corresponding to the material template according to the effect data after the normalization processing; updating the material weight corresponding to the material template to the new weight.

[0010] In a possible design, the material type includes a video type and a picture type, and the determining of the target type according to the value feature includes: when the value feature indicates that the consumption ability of the user is greater than or equal to a first threshold, determining the target type as the video type; when the value feature indicates that the consumption ability of the user is less than the first threshold, determining the target type as the picture type.

[0011] In a possible design, the value feature includes an intention value of the user and a device type of the user, and the demand feature includes a delivery route, a vehicle type, and a vehicle length required by the user.

[0012] In a possible design, after receiving the delivery request sent by the media platform, the method further includes: According to the real-time media data of the user and the preset participation label, it is determined whether the user participates in the competition; the real-time media data is obtained from a media platform in real time, and the real-time media data is used to indicate the necessity of advertising to the user.

[0013] According to the method provided by the first aspect, the value feature and the demand feature of the user generated in the business platform in the historical time period are obtained, the value feature is used to indicate the consumption ability of the user, and the demand feature is used to indicate the business demand of the user, so as to generate the advertising material for the corresponding user according to the value feature and the demand feature. According to the value feature, the demand feature and the preset material template library, the advertising material corresponding to the user is synthesized, based on this, without using the data of the media platform side to generate the advertising material, but synthesizing the personalized advertising material according to the value feature and the demand feature in advance, realizing the accurate matching of the advertising material and the user, and improving the relevance of the advertising. The advertising material is sent to the media platform, and the material identifier sent by the media platform is received, the material identifier and the device identifier of the user are stored in pairs, so as to match the user and the advertising material. After receiving the delivery request sent by the media platform, in the case that the user participates in the competition, the participation price is generated according to the preset participation label, the material identifier is obtained according to the device identifier, and the material identifier and the participation price are sent to the media platform, so that the media platform exposes the advertising material to the user according to the material identifier. Since the advertising material is customized based on the demand feature and the value feature of the user, the relevance between the advertising material and the user is high, and when the advertising material is exposed to the user, the user can see the advertising which is accurately matched with the demand, thereby improving the interest degree of the user to the advertising and improving the delivery effect of the advertising.

[0014] In the second aspect, the present application provides an advertising delivery device, comprising: a module for executing the advertising delivery method in the first aspect and any possible design of the first aspect.

[0015] In the third aspect, the present application provides an electronic device, comprising a first processor, which realizes the advertising delivery method in the first aspect and any possible design of the first aspect when executing the computer executable program or instruction in the memory.

[0016] In the fourth aspect, the present application provides an electronic device, comprising at least one memory and at least one second processor, the memory stores the computer executable program or instruction, and the second processor realizes the advertising delivery method in the first aspect and any possible design of the first aspect when executing the computer executable program or instruction.

[0017] In the fifth aspect, the present application provides a computer readable storage medium, which stores the computer executable program or instruction, and the computer executable program or instruction is executed by the processor to realize the advertising delivery method in the first aspect and any possible design of the first aspect.

[0018] Sixthly, this application provides a computer program product, comprising: execution instructions stored in a readable storage medium, at least one processor of an electronic device being able to read the execution instructions from the readable storage medium, and the at least one processor executing the execution instructions causing the electronic device to implement the advertising delivery method as described in the first aspect and any possible design of the first aspect.

[0019] The above description is merely an overview of the technical solutions of the embodiments of this application. In order to better understand the technical means of the embodiments of this application and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of this application more obvious and understandable, specific implementation methods of this application are described below. Attached Figure Description

[0020] Figure 1 This is a flowchart illustrating an advertising delivery method provided in one embodiment of this application.

[0021] Figure 2 This is a flowchart illustrating a method for synthesizing user-specific advertising materials according to an embodiment of this application.

[0022] Figure 3 This is a schematic diagram of a target template provided in an embodiment of this application.

[0023] Figure 4 This is a schematic diagram of an advertising material provided in an embodiment of this application.

[0024] Figure 5 This is a flowchart illustrating a method for determining a target template from candidate templates, as provided in an embodiment of this application.

[0025] Figure 6 A flowchart illustrating a method for updating material weights according to an embodiment of this application.

[0026] Figure 7 This is a schematic diagram of an advertising delivery device provided in an embodiment of this application.

[0027] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 1 .

[0028] Figure 9 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 2 . Detailed Implementation

[0029] In this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c alone can mean: a alone, b alone, c alone, a combination of a and b, a combination of a and c, a combination of b and c, or a, b, and c, where a, b, and c can be single or multiple. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0030] The terms “center,” “longitudinal,” “lateral,” “up,” “down,” “left,” “right,” “front,” and “rear,” etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0031] The terms "connected" and "connected" should be interpreted broadly. For example, in circuit structures, "connected" or "connected" can refer not only to physical connections but also to electrical or signal connections. This could be a direct connection (physical connection) or an indirect connection via at least one intermediate component, as long as the circuit is connected. It could also refer to the internal connection between two components. Similarly, a signal connection can refer to a connection via a circuit or a medium, such as radio waves. Those skilled in the art will understand the specific meaning of these terms in this application based on the specific circumstances.

[0032] For example, this application provides an advertising delivery method, electronic device, and storage medium. By pre-compiling advertising materials using user data from the advertiser's side and a pre-set material template library before delivering the advertisement to the media platform, advertising materials with a high degree of user matching are obtained, and then stored on the media platform. When advertising needs to be delivered to users, the corresponding advertising materials are selected and exposed to the users, thereby improving the advertising delivery effect.

[0033] The advertising delivery method provided in this application is executed by an electronic device, or by an advertising delivery device in an electronic device.

[0034] The electronic devices can include servers, desktop computers, mobile phones, tablets, laptops, wearable devices, in-vehicle devices, augmented reality (AR) / virtual reality (VR) devices, etc. Advertising delivery devices can be implemented through a combination of software and / or hardware; for example, an advertising delivery device can be a central processing unit (CPU). Alternatively, an advertising delivery device can be an application (APP), a webpage, or a public account, etc.

[0035] To simplify the explanation, this application uses an advertising delivery device as an example.

[0036] The following embodiments of this application will be combined with Figures 1 to 6 This application provides a detailed description of the advertising placement methods provided.

[0037] Please see Figure 1 , Figure 1 This is a flowchart illustrating an advertising delivery method provided in one embodiment of this application. Figure 1 As shown, the method includes: S101. The advertising delivery device acquires the value characteristics and demand characteristics generated by users on the business platform within a historical period.

[0038] The historical duration is a configurable time window. For example, the historical duration can be the past 30 days, the past 7 days, or the past 24 hours. Advertising devices can capture long-term, stable value characteristics and demand characteristics generated by users on the business platform, or short-term, sudden value characteristics and demand characteristics generated on the business platform, by configuring different historical durations.

[0039] In this context, the business platform refers to the platform operated by the advertiser that interacts with users. For example, in a freight scenario, the business platform could be a freight platform, and the users could be cargo owners.

[0040] Among these features, value characteristics are used to indicate a user's spending power. Ad delivery devices can measure a user's spending power on the business platform using these value characteristics, thereby determining the cost of advertising to be delivered to that user. Based on this determination, the device then selects appropriate creative templates when creating ad creatives for that user. For example, if the value characteristics indicate a user's low spending power, the ad delivery device can determine that lower-cost advertising should be delivered to that user, and thus select low-cost creative templates, such as image-based templates, when creating ad creatives. Conversely, if the value characteristics indicate a user's high spending power, the ad delivery device can determine that higher-cost advertising should be delivered to that user, and thus select high-cost creative templates, such as video-based templates, when creating ad creatives.

[0041] In freight scenarios, value characteristics can include the user's intended value, the user's equipment type, etc.

[0042] Intended value refers to the amount a user is willing to pay for a carrier (such as a driver), which can be based on factors such as waybill budget, transportation distance, cargo type, cargo weight, historical order completion rate, or waybill posting frequency.

[0043] Among them, device type refers to the type of device used by the user to log in to the business platform, such as device model, device price, etc.

[0044] Among these features, demand characteristics are used to indicate a user's business needs. The ad delivery device can use these demand characteristics to understand a user's current business needs and then generate ad creatives that match those needs. For example, if the demand characteristics indicate that a user needs a 4-meter van to transport goods from Haidian District in Beijing to Pudong New Area in Shanghai, the ad delivery device can use phrases like "from Haidian District in Beijing to Pudong New Area in Shanghai" and "4-meter van" as keywords when creating ad creatives.

[0045] In freight scenarios, demand characteristics can include the user's required delivery routes, vehicle types, and vehicle lengths.

[0046] The shipping route refers to the origin and destination of the goods that the user needs to transport, such as "Shanghai Pudong New Area to Beijing Haidian District".

[0047] Among them, vehicle type refers to the type of transport vehicle that the user needs to use, such as a van, refrigerated truck, container truck, or flatbed truck.

[0048] The vehicle length refers to the length of the cargo box required by the user, such as "4 meters", "6 meters" or "9.6 meters".

[0049] Based on this, the advertising delivery device obtains the value characteristics and demand characteristics generated by users on the business platform within a historical period, so as to generate advertising materials for corresponding users according to the value characteristics and demand characteristics, thereby helping to improve the matching degree between advertising materials and users, and thus helping to improve the delivery effect after the advertisement is delivered to the media platform.

[0050] S102. The advertising delivery device synthesizes advertising materials corresponding to the user based on value characteristics, demand characteristics, and a preset material template library.

[0051] The preset template library is a collection of pre-set, dynamically populated templates. It includes multiple templates, each composed of constant and variable elements. Constant elements include layout, brand colors, background patterns, and fonts. Variable elements include text, images, and promotional information.

[0052] There are various types of creative templates, such as image templates, video templates, and H5 page templates. Different types of creative templates have different costs; for example, image templates are generally less expensive than video templates or H5 page templates. Ad placement devices can select the appropriate type of creative template based on value characteristics, and then fill the selected template with the content indicated by the demand characteristics to create the corresponding ad creative for the user.

[0053] Based on this, the advertising delivery device can pre-synthesize personalized advertising materials according to the user's value characteristics and needs, achieving precise matching between advertising materials and users, improving the relevance of the advertisement, and thus helping to improve the delivery effect after the advertisement is placed on the media platform.

[0054] S103. The advertising delivery device sends advertising materials to the media platform and receives material identifiers sent by the media platform, and pairs and stores the material identifiers and the user's device identifiers.

[0055] The advertising delivery device sends advertising materials to the media platform so that the media platform can store the advertising materials and quickly retrieve and expose the corresponding advertising materials to users when it needs to deliver the advertisement.

[0056] The creative identifier is used to identify the advertising creative, and can be, for example, a hash value. After receiving the advertising creative, the media platform will return a creative identifier to the ad delivery device so that the ad delivery device and the media platform can identify and use the advertising creative.

[0057] The device identifier is used to identify the user's device; for example, it can be an Identifier for Advertising (IDFA) or a Google Advertising Identifier (GAID). After receiving the creative identifier, the ad delivery device pairs and stores the creative identifier and the device identifier, so that when it receives a delivery request from a media platform, it can return the corresponding creative identifier to the media platform to participate in ad delivery.

[0058] For example, ad delivery devices can store paired creative identifiers and device identifiers in a Hadoop database (HBase).

[0059] S104. After receiving the placement request sent by the media platform, the advertising placement device, upon confirming the user's participation, generates a bidding price based on preset bidding tags and obtains material identifiers based on the device identifier.

[0060] The delivery request is used to request advertising placement. When a media platform obtains an advertising exposure opportunity, the media platform will send a delivery request to the advertising placement device. The delivery request carries a device identifier so that the advertising placement device can determine whether the user corresponding to the device identifier needs to participate in the competition.

[0061] Once a user is identified as a participant, the ad delivery device generates a bid price based on preset bid tags and extracts the material identifier from the paired stored material identifier and device identifier based on the device identifier.

[0062] Among them, the preset participation label is used to indicate the value of a user's participation in the competition.

[0063] For example, the preset participation tags can be either active or inactive users. This means that if the ad creative is for user activation, then inactive users have a higher value in participating in the bidding for that type of ad. Based on this, the ad delivery device can generate a bidding price according to the preset participation tags, allowing the ad budget to be allocated to users with higher ROI, further helping to improve the effectiveness of ad delivery.

[0064] S105. The advertising delivery device sends the material identifier and bidding price to the media platform so that the media platform can expose the advertising material to users based on the material identifier.

[0065] The advertising delivery device returns the calculated bid price and extracted creative identifier to the media platform, which then participates in the bidding. If the bid price sent by the advertising delivery device wins the bid, the media platform finds the corresponding advertising creative based on the creative identifier and exposes it to the user.

[0066] Because the advertising material is customized based on the user's needs and value characteristics, it is highly relevant to the user. When the advertising material is shown to the user, the user can see an ad that is precisely matched to their needs, thereby increasing the user's interest in the ad and improving the effectiveness of the ad campaign.

[0067] In this embodiment, the advertising delivery device acquires the value characteristics and demand characteristics generated by users on the business platform within a historical period. The value characteristics indicate the user's spending power, and the demand characteristics indicate the user's business needs, enabling the generation of advertising materials for the corresponding user based on these characteristics. The advertising delivery device synthesizes advertising materials corresponding to the user based on the value characteristics, demand characteristics, and a pre-set material template library. Therefore, the advertising delivery device does not need to use data from the media platform to generate advertising materials; instead, it pre-synthesizes personalized advertising materials based on the value characteristics and demand characteristics, achieving precise matching between advertising materials and users and improving advertising relevance. The advertising delivery device sends the advertising materials to the media platform and receives the material identifier sent by the media platform, pairing and storing the material identifier and the user's device identifier to facilitate matching users with advertising materials. After receiving a placement request from a media platform, the advertising delivery device, upon confirming user participation, generates a bidding price based on preset bidding tags and obtains a creative identifier based on the device identifier. The advertising delivery device then sends the creative identifier and bidding price to the media platform, enabling the media platform to expose the advertising creative to users based on the creative identifier. Since the advertising creative is customized based on the user's needs and value characteristics, it is highly relevant to the user. When the advertising creative is exposed to the user, the user can see an advertisement that precisely matches their needs, thereby increasing the user's interest in the advertisement and improving the advertising delivery effect.

[0068] Based on the above exemplary description, the preset material template library includes multiple material templates, each material template corresponding to a material type and a material weight.

[0069] The "material type" indicates the media format of the material template. Different material types have different costs, information carrying capacity, and visual impact. For example, material types can include video and image types. Video material templates include cover images, audio materials, playback duration, and video footage, which are more expensive but have a stronger information carrying capacity and visual impact. Image material templates include text, background images, and styles, which have a weaker information carrying capacity and visual impact but are less expensive.

[0070] The material weight is a dynamically adjustable value used to evaluate the quality of different material templates. A higher weight means that the material template performs better, and a lower weight means that the material template performs worse. Initially, each material template can be set with the same weight, and the delivery module can periodically update the material weight corresponding to each material template based on the performance of the advertisement, so that the advertising delivery device can automatically tend to select the template with better performance.

[0071] Based on this, advertising delivery devices can, for example, Figure 2 The method shown is used to synthesize advertising materials corresponding to the user.

[0072] Please see Figure 2 , Figure 2 This is a flowchart illustrating a method for synthesizing user-specific advertising materials according to an embodiment of this application. Figure 2 As shown, the method includes: S201. The advertising placement device determines the target type based on value characteristics.

[0073] Advertising delivery devices can determine the template type based on value characteristics and the type of material that is suitable for the user.

[0074] In some examples, the content types include video and image types. The ad delivery device can determine the target type as video when the value characteristics indicate that the user's spending power is greater than or equal to a first threshold, and determine the target type as image when the value characteristics indicate that the user's spending power is less than the first threshold.

[0075] Specifically, the advertising device can first quantify the user's spending power based on value characteristics, and then compare it with a first threshold.

[0076] For example, when the value characteristic includes intention value, if the intention value is the shipping budget, the shipping budget directly indicates the user's spending power. Based on this, a first threshold can be set as a price, and the shipping budget can be directly compared with the first threshold to determine the target type. For example, if the first threshold is 5,000 yuan and the shipping budget is 6,000 yuan, then the advertising device can determine the target type as video.

[0077] For example, when the value characteristics include intention value and device type, the advertising device can score intention value and device type separately. Based on the scores of intention value and device type, the user's spending power can be determined. A first threshold can be set as a score, and the target type can be determined based on the scores of intention value and device type. When determining the target type based on the scores of intention value and device type, the advertising device can also set corresponding weights for the scores of intention value and device type, thereby controlling the influence of intention value and device type on the judgment result. For example, if the first threshold is 100 points, and the scoring system is out of 100, if the intention value is a shipping budget of 3000 yuan, the corresponding score is 30 points; if the device type is an Android phone, the corresponding score is 30 points; and the weights of the intention value score and device type score are 1 each, then the total score is 60 points, which is less than the first threshold. Therefore, the advertising device can determine the target type as image-based.

[0078] Based on this, the ad delivery device can ensure that it matches the material templates of equivalent value to different user groups, thereby improving the return on investment and further helping to improve the effectiveness of ad delivery.

[0079] S202. The advertising delivery device identifies the material templates of the target type in the preset material template library as candidate templates.

[0080] Based on the target type, the ad delivery device filters out templates for all target types to form candidate templates, thereby narrowing down the selection range and improving the efficiency of subsequent selection.

[0081] S203. The advertising delivery device determines the target template from the candidate templates based on the material weights corresponding to the candidate templates.

[0082] The ad delivery device can select the material template with the highest weight from the candidate templates as the target template. Of course, the ad delivery device can also calculate the probability of each material template in the candidate templates being selected based on the weight, and select the material template as the target template based on the probability.

[0083] Based on this, the advertising delivery device can automatically select the material template with better delivery effect to synthesize advertising materials, thereby helping to improve the delivery effect of advertising.

[0084] S204. The advertising delivery device synthesizes advertising materials corresponding to the user based on the target template and demand characteristics.

[0085] The advertising delivery device fills the target template with demand characteristics, thereby synthesizing personalized advertising materials that match the user. This ensures that the content of the advertising materials matches the user's needs, achieving a precise match between the advertising materials and the user, which further helps to improve the effectiveness of advertising.

[0086] For example, the target template is as follows Figure 3 As shown, the demand characteristics include: "4 meters", "van-type truck", "from Shanghai Pudong New Area to Beijing Haidian District", and the synthesized advertising materials can be as follows: Figure 4 As shown.

[0087] Based on the above exemplary description, the following, in conjunction with Figure 5 This paper introduces a method for determining the target template from candidate templates.

[0088] Please see Figure 5 , Figure 5 This is a flowchart illustrating a method for determining a target template from candidate templates, provided as an embodiment of this application. Figure 5 As shown, the method includes: S301, The advertising delivery device calculates the sum of the weights of all materials corresponding to the candidate template.

[0089] The sum is used to define a continuous probability interval from 0 to the sum, in which each candidate template occupies a different sub-interval according to its corresponding weight.

[0090] For example, if the candidate templates include material template A, material template B, and material template C, with corresponding material weights of 50, 30, and 20 respectively, then the ad delivery device can determine that the sum is 100.

[0091] S302, The advertising device generates a random number that is uniformly distributed between 0 and the sum of the values.

[0092] A random number can be used as a pointer between 0 and the sum of values ​​to select a target template. Since the random number is generated randomly, the probability of each real number between 0 and the sum of values ​​being selected as a random number is equal. This ensures that while introducing randomness when using random numbers to select a target template, the fairness of the selection is also guaranteed.

[0093] Based on the above example, the advertising delivery device can generate a random number that is evenly distributed between 0 and 100, which can be 65.

[0094] S303. The advertising delivery device determines the target template based on a random number and the material weight corresponding to each candidate template.

[0095] Specifically, the ad delivery device can initialize an accumulator s and iterate through each candidate template. For each candidate template: Calculate s = s + weight; where weight is the weight of the candidate template currently being traversed; Determine if the random number is less than s; If the random number is less than s, the currently iterated candidate template is selected as the target template; if the random number is greater than or equal to s, the next candidate template is iterated.

[0096] Based on the above example, the ad delivery device iterates through material templates A, B, and C.

[0097] For template A: s = 0 + 50 = 50; random number 65 > 50, continue iterating through template B; For material template B: s=50+30=80; random number 65<80, then the advertising delivery device will determine material template B as the target template.

[0098] Based on this, the ad delivery device determines the target template and uses random numbers to ensure non-deterministic selection, avoiding fixed template materials and thus helping to improve ad delivery effectiveness. This method is simple to implement, has low computational complexity, and can adapt to scenarios with high queries per second (QPS).

[0099] The pseudocode implementation of the method for determining the target template from candidate templates described above can be shown below: import random (random number generator library); def select_template(templates): #templates are candidate templates, each candidate template is (template_id, weight), where template_id is the candidate template identifier and weight is the corresponding material weight; total_weight = sum(weight for _, weight in templates) # Calculate the sum of the weights of all materials corresponding to the candidate template; if total_weight <= 0: # Handle the case where all weights are 0; return random.choice(templates)[0] # Random and uniform selection; r = random.uniform(0, total_weight) # Generates a random number r that is uniformly distributed between 0 and the sum of values; s = 0 # Initialize an accumulator s; for template_id, weight in templates: # For a candidate template; s += weight#Calculate s=s+weight; if s>=r: # Check if s is greater than or equal to the random number r; return template_id # If so, return the identifier of the selected candidate template.

[0100] Based on the above exemplary description, after exposing advertising creatives to users, the advertising delivery device can also update the creative weights.

[0101] Please see Figure 6 , Figure 6 This is a flowchart illustrating a method for updating material weights according to an embodiment of this application. Figure 6 As shown, the method includes: S401, The advertising delivery device acquires the performance data corresponding to each material template within the historical period.

[0102] The historical period is configurable, and can be set to, for example, 24 hours or 7 days.

[0103] The performance data includes total clicks, total impressions, total activations, total plays, total play completions, average dwell time, average play progress, and average cost per click.

[0104] For a single resource template: Total clicks represent the number of times a user clicks on an ad creative created using this template.

[0105] Total exposures represent the total number of times that the ad creative created using this template is shown to users.

[0106] Total activations represent the total number of times a user completes a specific expected action (such as downloading, placing an order, or registering) after clicking on an ad creative.

[0107] For video creative templates, the total number of plays indicates the number of times a user starts playing an ad creative created using that template; the total number of plays completed indicates the number of times a user finishes playing an ad creative created using that template; and the average playback progress indicates the average progress of a user playing an ad creative created using that template.

[0108] Average dwell time represents the average length of time a user stays on an ad creative created using this particular template after clicking on it. Using an average value helps avoid discrepancies caused by varying exposure times.

[0109] Average cost-per-click (CPC) represents the average cost an advertiser has to pay when a user clicks on an ad creative created using that particular creative template.

[0110] The advertising delivery system acquires multi-dimensional performance data from historical periods to update creative weights based on comprehensive and rich data, avoiding the limitations of a single indicator and thus helping to improve update effectiveness.

[0111] For each material template, the ad delivery device executes the following steps S402 to S404.

[0112] S402, The advertising delivery device normalizes each item in the effect data corresponding to the material template.

[0113] Since the dimensions of the various items in the effect data are different, each item in the effect data can be normalized to eliminate the difference in dimensions.

[0114] Total clicks, total impressions, total activations, total plays, total play completions, average dwell time, and average play progress are positive metrics; the higher the value, the better the performance of the creative template. Average cost-per-click is a negative metric; the lower the value, the lower the cost. Therefore, the advertising device can normalize the positive metrics based on the following formula: Formula 1; in, This is the normalized value of the positive indicator currently pending processing. The value of the positive indicator to be processed. The minimum value of the positive metric currently pending processing among all material templates. This represents the maximum value of the currently pending positive indicator across all material templates.

[0115] If the current positive indicator to be processed has the same value in all material templates, then set It is 0.5.

[0116] Based on the following Formula 2, the negative indicators are normalized: Formula 2; in, This is the normalized value of the negative indicator currently pending processing. The value of the negative indicator to be processed. This represents the minimum value of the currently pending negative indicator among all material templates. This represents the maximum value of the currently pending negative indicator across all material templates.

[0117] If the negative indicator to be processed has the same value in all material templates, then set It is 0.5.

[0118] S403. The advertising delivery device calculates the new weights corresponding to the material templates based on the normalized effect data.

[0119] The ad delivery system can sum the normalized values ​​of each item in the normalized performance data. The weight of each item is set to 1 by default during the summation, thus determining the sum of each item as the new weight for the ad template. Furthermore, if the importance of different metrics needs to be adjusted, the weight of each item can be modified.

[0120] S404. The advertising delivery device updates the material weights corresponding to the material templates to the new weights.

[0121] The advertising delivery device can update the material weights regularly according to a preset frequency. This allows for real-time adjustment of the weights based on the new performance data accumulated during actual campaigns. This enables the scientific and accurate selection of better-performing material templates when creating advertising materials, thereby improving the effectiveness of advertising and increasing the return on investment.

[0122] The pseudocode implementation of the above method for updating material weights can be shown below: import numpy as np def compute_weights(templates_data): #templates_data contains the effect data for each material template; #The value of each item in the extracted data is used for normalization. all_clicks = [data['clicks'] for data in templates_data] # Total number of clicks; all_impressions = [data['impressions'] for data in templates_data] # Total impressions; all_activations = [data['activations'] for data in templates_data] # Total number of activations; all_plays = [data['plays'] for data in templates_data] # Total number of plays; all_completions = [data['completions'] for data in templates_data] # Total number of playback completions; all_dwell_times = [data['dwell_time'] for data in templates_data] # Average duration of stay; all_play_progresses = [data['play_progress'] for data in templates_data] # Average playback progress; all_avg_prices = [data['avg_click_price'] for data in templates_data] # Average cost per click; #Calculate the maximum and minimum values; min_max = { 'clicks': (min(all_clicks), max(all_clicks)), # Calculate the minimum and maximum total number of clicks across all template materials; 'impressions': (min(all_impressions), max(all_impressions)), # Calculate the minimum and maximum total exposures across all material templates; 'activations': (min(all_activations), max(all_activations)), # Calculate the minimum and maximum total activations across all resource templates; 'plays': (min(all_plays), max(all_plays)), # Calculate the minimum and maximum total number of plays among all material templates; 'completions': (min(all_completions), max(all_completions)), # Calculate the minimum and maximum total number of completed playbacks across all media templates; 'dwell_time': (min(all_dwell_times), max(all_dwell_times)), # Calculate the minimum and maximum average dwell time among all material templates; 'play_progress': (min(all_play_progresses), max(all_play_progresses)), # Calculate the minimum and maximum average playback progress across all media templates; 'avg_price': (min(all_avg_prices), max(all_avg_prices)) # Calculates the minimum and maximum average cost-per-click across all asset templates; } #Normalize each item in the effect data corresponding to each material template; weights = [] for data in templates_data: #Normalization of positive indicators; def normalize_positive(value, key): min1, max1 = min_max[key] if max1==min1: return 0.5 # If the positive indicator has the same value in all material templates; return (value1-min1) / (max1-min1) #Normalization of negative indicators; (avg_click_price) min2, max2= min_max['avg_price'] if max2==min2: norm_price = 0.5 # If the negative index has the same value in all material templates; else: norm_price=(max2- data['avg_click_price']) / (max2-min2) # Calculation of normalized values ​​for positive indicators; norm_clicks=normalize_positive(data['clicks'], 'clicks') # Normalized value of total clicks; norm_impressions=normalize_positive(data['impressions'],'impressions') # Normalized value of total exposures; norm_activations = normalize_positive(data['activations'], 'activations') # Normalized value of total activations; norm_plays = normalize_positive(data['plays'], 'plays') # Normalized value of total play count; norm_completions = normalize_positive(data['completions'], 'completions') # Normalized value of total number of playback completions; norm_dwell_time = normalize_positive(data['dwell_time'], 'dwell_time') # Normalized value of average dwell time; norm_play_progress = normalize_positive(data['play_progress'], 'play_progress') # Normalized value of average playback progress; #Calculate the new weight for each material template; New weight = sum of the normalized values ​​of each item in the normalized effect data; w=norm_clicks+norm_impressions+norm_activations+norm_plays+norm_completions+norm_dwell_time+norm_play_progress+norm_price; #w is the new weight; weights.append({'template_id': data['template_id'], 'weight': w}) return weights # Returns all new weights.

[0123] Based on the above exemplary description, after receiving a delivery request from a media platform, the advertising delivery device can also determine whether a user should participate in the bidding based on the user's real-time media data and preset bidding tags.

[0124] Real-time media data is obtained from the media platform in real time, and the advertising device can request real-time media data from the media platform in real time. Real-time media data includes, for example, total impressions, total clicks, total plays, and total participants. Total impressions refer to the number of times all ads are shown to users on the media platform; total clicks refer to the number of times users click on all ads on the media platform; total plays refer to the number of times users play all ads on the media platform; and total participants refer to the total number of times users participate in competitions on the media platform. Real-time media data is used to indicate the necessity of advertising to users.

[0125] Specifically, the advertising delivery device can pre-set frequency control strategies. For example, the frequency control strategy can be: when the total number of impressions, total number of clicks, total number of plays, or total number of participants is less than a preset frequency threshold, it can be preliminarily determined that the user is worth participating in the competition; or, the frequency control strategy can also be: score the user based on the total number of impressions, total number of clicks, total number of plays, and total number of participants, and when the score is greater than or equal to the preset score, it can be preliminarily determined that the user is worth participating in the competition.

[0126] When a user is initially determined to be worthy of participation based on real-time media data, the ad delivery device can further determine whether the user should participate based on preset participation tags. For example, the preset participation tags can be active users or inactive users. In other words, if the ad creative is an activation-type ad, then for this type of ad, inactive users have higher value in participating. The ad delivery device can determine that a user can participate when the preset participation tag is inactive user.

[0127] Based on this, by using users' real-time media data and preset bidding tags, the ad delivery device can determine whether a user is willing to participate in a bidding process, thereby filtering out low-value bidding opportunities and saving costs. By combining real-time media data, the device can also improve the accuracy of ad exposure to users, further enhancing the effectiveness of ad delivery.

[0128] Figure 7 This is a schematic diagram of an advertising delivery device provided in one embodiment of this application. Figure 7 As shown, the device includes: an acquisition module 101, a synthesis module 102, a storage module 103, and a competition module 104.

[0129] The acquisition module 101 is used to acquire the value characteristics and demand characteristics generated by users on the business platform within a historical period; the value characteristics are used to indicate the user's spending power, and the demand characteristics are used to indicate the user's business needs. The synthesis module 102 is used to synthesize advertising materials corresponding to users based on value characteristics, demand characteristics and a preset material template library; Storage module 103 is used to send advertising materials to the media platform and receive material identifiers sent by the media platform, and to pair and store material identifiers and user device identifiers. The bidding module 104 is used to generate a bidding price based on preset bidding tags and obtain a material identifier based on the device identifier after receiving a delivery request from the media platform and confirming that the user is participating in the bidding. The delivery request is used to request advertising delivery, and the delivery request carries the device identifier. The preset bidding tags are used to indicate the value of the user's participation. The material identifier and bidding price are sent to the media platform so that the media platform can expose advertising materials to the user based on the material identifier.

[0130] It should be noted that the advertising delivery device in this application embodiment can be used to execute the technical solutions of the above method embodiments, and its implementation principle and technical effect are similar, so it will not be repeated here.

[0131] In some examples, the preset material template library includes multiple material templates, each corresponding to a material type and a material weight. The compositing module 102 is specifically used for: Determine the target type based on value characteristics; Select the material templates of the target type from the preset material template library as candidate templates; The target template is determined from the candidate templates based on the material weights corresponding to the candidate templates. Based on the target template and user needs, create advertising creatives that correspond to the user.

[0132] In some examples, the synthesis module 102 is specifically used for: Calculate the sum of the weights of all materials corresponding to the candidate template; Generate random numbers that are uniformly distributed between 0 and the sum of the values; The target template is determined based on the random number and the material weight corresponding to each candidate template.

[0133] In some examples, the ad delivery device also includes an update module, which is specifically used to: after exposing the ad creative to the user, obtain the performance data corresponding to each creative template in the historical period, including total clicks, total impressions, total activations, total plays, total play completions, average dwell time, average play progress, and average cost per click; For each material template, normalize each item in the corresponding effect data; Calculate the new weights corresponding to the material templates based on the normalized effect data; Update the material weights corresponding to the material templates to the new weights.

[0134] In some examples, the material types include video and image types. The compositing module 102 is specifically used to: determine the target type as video when the value feature indicates that the user's spending power is greater than or equal to a first threshold; and determine the target type as image when the value feature indicates that the user's spending power is less than the first threshold.

[0135] In some examples, value characteristics include the user's intended value and the user's device type, while demand characteristics include the user's desired delivery route, vehicle type, and vehicle length.

[0136] In some examples, the ad delivery device also includes a determination module, which is specifically used to: after receiving a delivery request from the media platform, determine whether the user should participate in the bidding based on the user's real-time media data and preset bidding tags; the real-time media data is obtained from the media platform in real time and is used to indicate the necessity of ad delivery to the user.

[0137] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 1 .like Figure 8 As shown, the electronic device may include a first processor 201, which, when executing a computer-executable program or instruction stored in a memory, implements the embodiments of this application. Figures 1 to 6 The advertising placement method shown.

[0138] The electronic device can be used to perform the various steps and / or processes corresponding to the electronic devices in the above method embodiments.

[0139] Figure 9 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 2 .like Figure 9 As shown, the electronic device may include a second processor 301 and a memory 302. The memory 302 stores a computer program. When the second processor 301 executes the computer program, it implements the embodiments of this application. Figures 1 to 6 The advertising placement method shown.

[0140] The electronic device can be used to perform the various steps and / or processes corresponding to the electronic devices in the above method embodiments.

[0141] The electronic device of this application can be used to execute the technical solutions of the method embodiments described above. Its implementation principle and technical effects are similar. The operations implemented by each module can be further referred to the relevant descriptions of the method embodiments, which will not be repeated here. The modules here can also be replaced by components or circuits.

[0142] This application can divide electronic devices into functional modules based on the above method examples. For example, each function can be divided into its own functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in the embodiments of this application is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0143] Another embodiment of this application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it can implement the embodiments of this application. Figures 1 to 6 The advertising placement method shown.

[0144] This application also provides a program product including executable instructions stored in a computer-readable storage medium. At least one processor of an electronic device can read the executable instructions from the computer-readable storage medium, and the at least one processor executes the executable instructions to cause the electronic device to implement embodiments of this application. Figures 1 to 6 The advertising placement method shown.

[0145] This application also provides a chip that is connected to a memory, or a chip that integrates a memory. When a software program stored in the memory is executed, it implements the embodiments of this application. Figures 1 to 6 The advertising placement method shown.

[0146] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0147] Those skilled in the art will understand that although some embodiments herein include certain features included in other embodiments, combinations of features from different embodiments are intended to be within the scope of this application and form different embodiments. For example, in the claims, any of the claimed embodiments can be used in any combination.

[0148] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. An advertising placement method, characterized in that, The method includes: Obtain the value characteristics and demand characteristics generated by users on the business platform within a historical period; the value characteristics are used to indicate the user's spending power, and the demand characteristics are used to indicate the user's business needs; Based on the value characteristics, the demand characteristics, and the preset material template library, the advertising material corresponding to the user is synthesized; The advertising material is sent to the media platform, and the material identifier sent by the media platform is received. The material identifier and the user's device identifier are paired and stored. Upon receiving a placement request from the media platform, and upon confirming that the user is participating in the bidding, a bidding price is generated based on preset bidding tags, and the material identifier is obtained based on the device identifier; the placement request is used to request advertising placement, the placement request carries the device identifier, and the preset bidding tags are used to indicate the value of the user's participation in the bidding; The material identifier and the bidding price are sent to the media platform so that the media platform can expose the advertising material to the user based on the material identifier. The preset material template library includes multiple material templates, each material template corresponding to a material type and a material weight. The process of synthesizing the user's corresponding advertising material based on the value characteristics, the demand characteristics, and the preset material template library includes: Based on the aforementioned value characteristics, the target type is determined; The material templates of the target type in the preset material template library are identified as candidate templates; Based on the material weights corresponding to the candidate templates, the target template is determined from the candidate templates; Based on the target template and the required characteristics, the advertising materials corresponding to the user are synthesized.

2. The method according to claim 1, characterized in that, The step of determining the target template from the candidate templates based on the material weights corresponding to the candidate templates includes: Calculate the sum of the weights of all materials corresponding to the candidate template; Generate a random number that is uniformly distributed between 0 and the sum value; The target template is determined based on the random number and the material weight corresponding to each candidate template.

3. The method according to claim 1 or 2, characterized in that, After exposing the advertising material to the user, the method further includes: Obtain the performance data for each material template within the historical period. The performance data includes total clicks, total exposures, total activations, total plays, total play completions, average dwell time, average play progress, and average cost per click. For each material template, normalize each item in the effect data corresponding to the material template; Based on the normalized effect data, calculate the new weight corresponding to the material template; Update the material weight corresponding to the material template to the new weight.

4. The method according to claim 1, characterized in that, The material types include video and image types. Determining the target type based on the value characteristics includes: When the value feature indicates that the user's spending power is greater than or equal to a first threshold, the target type is determined to be video. When the value characteristic indicates that the user's spending power is less than a first threshold, the target type is determined to be an image type.

5. The method according to claim 1 or 2, characterized in that, The value characteristics include the user's intended value and the user's device type, while the demand characteristics include the user's desired delivery route, vehicle type, and vehicle length.

6. The method according to claim 1 or 2, characterized in that, After receiving a delivery request from a media platform, the method further includes: Based on the user's real-time media data and the preset competition tags, it is determined whether the user is participating in the competition; the real-time media data is obtained from the media platform in real time, and the real-time media data is used to indicate the necessity of advertising to the user.

7. An electronic device, characterized in that, include: First processor; The first processor is configured to execute a computer-executable program or instructions in the memory, causing the electronic device to perform the advertising delivery method according to any one of claims 1-6.

8. An electronic device, characterized in that, include: At least one memory and at least one second processor; The memory is used to store computer-executable programs or instructions; The second processor is used to invoke a computer-executable program or instruction in the memory, causing the electronic device to execute the advertising delivery method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer-executable program or instructions, the computer-executable program or instructions being configured to perform the advertising delivery method according to any one of claims 1-6.

Images