Advertisement putting strategy optimization method, device and equipment

Abstract

The application discloses an advertisement putting strategy optimization method, device and equipment, relates to the field of internet advertisement service, and the method comprises the following steps: obtaining the putting effect data of different advertisement content types used by users in different content consumption modes for different product types in a first stage; based on the putting effect data, calculating a first probability distribution of users accepting different advertisement content types for each putting channel and each combination of product types and content consumption modes under the putting channel; and based on the first probability distribution, formulating the advertisement content type putting strategy selected and executed by each putting channel when the user is in different content consumption modes for a target product to be put in a second stage. The application can realize the bidirectional improvement of the advertisement owner putting target and the user content experience by capturing the internal correlation between the user content consumption mode and the advertisement preference.

Description

Technical Field

[0001] This application relates to the field of internet advertising service technology, and in particular to a method, apparatus, and device for optimizing advertising delivery strategies. Background Technology

[0002] Advertising services are widely used in various business scenarios. In traditional advertising and marketing, many companies choose a "wide net" marketing model. Although this model can cover the vast majority of people and help a large number of consumers understand product information, the advertising content is difficult to attract consumers' attention, resulting in unsatisfactory conversion rates. Summary of the Invention

[0003] This application provides a method, apparatus, and device for optimizing advertising delivery strategies, which can improve the conversion efficiency of advertising delivery.

[0004] Firstly, this application provides a method for optimizing an advertising delivery strategy, comprising: Obtain performance data from the first phase of the campaign, which shows the performance of users across different content consumption patterns and for different product types using different ad content types. Based on the aforementioned campaign performance data, for each campaign channel and for each combination of product type and content consumption mode under the campaign channel, calculate the first probability distribution of users receiving different types of advertising content. For the target products to be launched in the second phase, based on the first probability distribution, formulate the advertising content type delivery strategy to be executed by each of the aforementioned delivery channels when users are in different content consumption modes.

[0005] In an optional implementation of the first aspect, the step of calculating a first probability distribution of user acceptance of different advertising content types based on the campaign performance data, for each campaign channel and for each combination of product type and content consumption mode under the campaign channel, includes: Obtain the target product's deployment target in the second phase; Extract the indicator data related to the campaign objective from the campaign performance data; For each combination determined by the delivery channel, the product type, and the content consumption pattern, a first probability distribution of users receiving different types of advertising content under each combination is calculated based on the relevant indicator data.

[0006] In an optional implementation of the first aspect, extracting indicator data related to the campaign objective from the campaign performance data includes: When the campaign objective is to increase brand exposure, the relevant metrics include at least one of clicks, favorites, and shares. When the objective of the campaign is to improve actual conversion rates, the relevant metrics include purchase volume.

[0007] In an optional implementation of the first aspect, the step of calculating a first probability distribution of user acceptance of different advertising content types for each combination determined by the delivery channel, the product type, and the content consumption pattern, based on the relevant indicator data, includes: For each combination determined by the delivery channel, the product type, and the content consumption mode, the initial probability value of users accepting each type of advertising content under each combination is calculated based on the relevant indicator data. Obtain market environment data for the first phase; The market environment data is input into the prediction model, and the probability that users tend to prefer different types of advertising content under the current market environment is output, which is denoted as the market probability value. The initial probability value of each type of advertising content under each combination is multiplied by the corresponding market probability value and then normalized to obtain the user reception probability value of each type of advertising content under each combination. For each combination, the user reception probability values ​​of all ad content types under the corresponding combination are summarized to obtain the first probability distribution of user reception of different ad content types under each combination.

[0008] In an optional implementation of the first aspect, the step of formulating the advertising content type delivery strategy selected by each of the delivery channels based on the first probability distribution when the user is in different content consumption modes includes: Obtain the matching degree between each of the aforementioned delivery channels and each of the aforementioned advertising content types; Based on the product type of the target product, the user acceptance probability value corresponding to different advertising content types in each of the delivery channels and each of the content consumption modes is determined by the first probability distribution. Based on the user acceptance probability value and the corresponding matching degree, calculate the recommendation score for each type of advertising content for the target product under each of the aforementioned delivery channels and each of the aforementioned content consumption modes; Based on the recommendation score, the appropriate advertising content type delivery strategy will be determined for different delivery channels and different content consumption models.

[0009] In an optional implementation of the first aspect, determining the ad content type delivery strategy to be executed on different delivery channels and under different content consumption modes based on the recommendation score includes: Based on each of the aforementioned delivery channels and each of the aforementioned content consumption modes, a recommendation score for each of the aforementioned advertising content types is applied to the target product to determine the delivery ratio for different advertising content types for each delivery channel and each of the aforementioned content consumption modes. Alternatively, based on each of the aforementioned delivery channels and each of the aforementioned content consumption modes, a recommendation score for each of the aforementioned advertising content types is applied to the target product, and the advertising content type with the highest recommendation score is selected as the advertising content type used by the target product.

[0010] In an alternative implementation of the first aspect, the method further includes: When implementing an ad content delivery strategy based on the aforementioned delivery ratio, the following steps are included: Set the fixed weight of each of the aforementioned advertising content types to the corresponding recommendation score; Obtain the dynamic weights of each of the aforementioned ad content types at the end of the previous round, wherein the dynamic weights of each of the aforementioned ad content types in the initial round are 0; When selecting ad content type in each round, all ad content types are traversed, and the dynamic weight of each ad content type at the end of the previous round is added to its corresponding fixed weight to obtain the dynamic weight of each ad content type in the current round. Select the ad content type with the highest dynamic weight in the current round as the selected ad content type for the current round; Subtract the sum of the fixed weights of all ad content types from the current dynamic weight of the selected ad content type to update the dynamic weight of the selected ad content type at the end of the current round.

[0011] In one alternative implementation of the first aspect, the content consumption mode includes a goal-oriented mode, an exploration mode, and a community interaction mode.

[0012] Secondly, this application provides an apparatus for optimizing an advertising delivery strategy, comprising: The acquisition module is used to acquire data on the performance of users in different content consumption modes and for different product types using different ad content types, based on statistics collected in the first phase from various advertising channels. The probability distribution calculation module is used to calculate the first probability distribution of users receiving different types of advertising content based on the advertising performance data, for each advertising channel and for each combination of product type and content consumption mode under the advertising channel. The strategy formulation module is used to formulate, based on the first probability distribution, the advertising content type delivery strategy to be executed by each of the delivery channels when the user is in different content consumption modes for the target products to be delivered in the second stage.

[0013] Thirdly, this application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is processed by the processor, it executes the optimization method for the advertising delivery strategy as described in the first aspect.

[0014] The method, apparatus, and equipment for optimizing advertising strategies provided in this application have the following beneficial effects: This application obtains performance data from the first phase of user campaigns across various channels, analyzing user behavior under different content consumption patterns and targeting different product types with different ad content types. Based on this performance data, a first probability distribution of user acceptance of different ad content types is calculated for each campaign channel and for each combination of product type and content consumption pattern within that channel. For the target products to be advertised in the second phase, an ad content type delivery strategy is developed for each campaign channel based on this first probability distribution, tailored to the specific content consumption patterns of users. By capturing the intrinsic correlation between user content consumption patterns and advertising preferences, this application ensures the actual effectiveness of advertising (improving conversion rates, exposure, etc.) while avoiding ineffective exposure and interference caused by pattern mismatch, reducing user resistance to advertising, and achieving a dual improvement in both advertiser goals and user content experience. Attached Figure Description

[0015] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0016] Figure 1 A flowchart illustrating an optimization method for an advertising delivery strategy provided in an embodiment of this application; Figure 2 This is a schematic diagram of the structure of an electronic device in the hardware operating environment involved in the method for optimizing the advertising delivery strategy according to an embodiment of this application. Detailed Implementation

[0017] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0018] Please see Figure 1 An embodiment of this application provides an optimization method for advertising delivery strategies. This method can be executed by an electronic device. The electronic device referred to in this application means any device that can run on a device with computing and storage capabilities, such as a mobile phone, tablet computer, PC (Personal Computer), laptop, server, server cluster, etc.

[0019] In this embodiment, the method for optimizing the advertising delivery strategy includes steps S10 to S30: S10: Obtain the performance data of users in different content consumption modes and for different product types using different ad content types from the first phase statistics of each advertising channel.

[0020] S20, based on campaign performance data, calculates the first probability distribution of users accepting different types of advertising content for each campaign channel and for each combination of product type and content consumption mode under the corresponding campaign channel.

[0021] S30, for the target products to be launched in the second phase, formulate the advertising content type delivery strategy for each delivery channel based on the first probability distribution when users are in different content consumption modes.

[0022] Specifically, electronic devices (such as those deployed on the advertiser's side) can send requests to the advertising platform interfaces of each advertising channel after the first phase of advertising delivery to obtain structured delivery performance data.

[0023] Among them, the delivery channels refer to the ways and means by which advertisers deliver advertising information to the target audience through various media and platforms, including traditional media channels, digital media and social platforms.

[0024] Traditional media channels include television, radio, newspapers, and magazines. Digital media and social platforms can include platforms such as Xiaohongshu, JD.com, Taobao, Baidu Search, Tencent Video, and Zhihu.

[0025] Among them, product types are divided according to the attributes of daily consumption, which can be referenced from the classification of mainstream e-commerce platforms. For example, they can be divided into food, beauty and skin care, personal care, clothing and shoes, home furnishing and decoration, and electronic products.

[0026] In an alternative implementation, the content consumption mode may include, but is not limited to, a goal-oriented mode, an exploration mode, and a community interaction mode.

[0027] The goal-oriented model refers to users making purposeful searches on the platform where the advertising channel is located. For example, users actively search for "shampoo" in the search box.

[0028] The exploration mode refers to users browsing and discovering content on the platform where the advertising channel is located without a specific purpose.

[0029] Community interaction mode refers to the main behaviors of users on the platform being sharing purchasing experiences and participating in community interactions.

[0030] In practice, the platform can dynamically identify users' current content consumption patterns by analyzing their multi-dimensional behavioral data on the platform.

[0031] If a user initiates a search (such as entering a query in the search box), and the subsequent interactive behavior performed on the search results or related product content page meets the preset target conditions (for example, the page stay time exceeds 30 seconds), then the user is determined to be in goal-oriented mode during the corresponding time period.

[0032] If a user's average page dwell time on a page while browsing the platform is less than a preset dwell threshold (e.g., less than 10 seconds), and the content browsed spans multiple product types, then the user is determined to be in exploration mode during the corresponding time period.

[0033] If a user's behavior on the platform is dominated by social interaction behaviors such as content posting (e.g., posting, writing notes), commenting, liking, and sharing, and the duration or frequency of such behaviors exceeds a preset threshold, then the user is determined to be in community interaction mode.

[0034] Among them, the performance data is a quantitative indicator used to measure the effectiveness of advertising, including but not limited to the number of clicks, the number of favorites, the number of add-to-carts, the number of shares, and the number of purchases.

[0035] The type of advertising content refers to the creative expression of the advertisement. Advertising content types can include promotional, science popularization, interactive, and sales promotion.

[0036] Among these, promotional ads refer to those primarily driven by celebrities and online influencers with significant online influence. Science popularization ads focus on clearly explaining product functions, ingredients, and value. Interactive ads guide users to immerse themselves in the product or service experience through virtual trials, interactive games, etc. Sales promotion ads highlight product discounts and special offers.

[0037] The platform can record every advertising interaction event a user engages with. For the same user within the same content consumption pattern time period, one or more structured combined data records can be generated. Each record must include at least the following fields: content consumption pattern, product type, advertising content type, and corresponding campaign performance data.

[0038] For example, if user A browsed various products aimlessly between 9:30 AM and 10:00 AM on January 20, 2026, multiple sets of data can be generated during this period, as shown in Table 1 below.

[0039] Table 1

[0040] It should be noted that the user information collected by each platform and the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) appearing in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0041] Understandably, users' content consumption patterns are directly related to their behavioral motivations and attention allocation logic. Behavioral motivations, in turn, determine users' preferences and response thresholds to advertising information. For example, in a goal-oriented mode, users' core need is to quickly obtain practical information that aligns with their goals; therefore, they are more receptive to rational, educational advertising content that clearly conveys product functions and value. In an exploration mode, users focus on "discovering new content and satisfying their interests," without significant decision-making pressure, making them more inclined to accept advertising content with emotional resonance and interactive experiences, thus reducing their resistance to advertising. In a community interaction mode, users value social recognition and genuine experience feedback, making them more easily attracted to advertising content that features authentic sharing and contextualized interaction.

[0042] This application captures the inherent connection between user content consumption patterns and advertising preferences, ensuring the actual effectiveness of advertising (improving conversion, exposure, and other goals) while reducing user resistance to advertising by avoiding ineffective exposure and interference caused by pattern mismatch, thus achieving a two-way improvement in both advertiser's advertising goals and user content experience.

[0043] In an optional implementation, S20 above, based on campaign performance data, calculates a first probability distribution of user acceptance of different advertising content types for each campaign channel and for each combination of product type and content consumption mode under the campaign channel, which may include: Obtain the target product's deployment goals for the second phase; Extract relevant metrics from campaign performance data to support campaign objectives; For each combination determined by the placement channel, product type, and content consumption pattern, the first probability distribution of users receiving different types of advertising content under each combination is calculated based on relevant indicator data.

[0044] For example, when the goal of the campaign is to increase brand exposure, the relevant metrics include at least one of clicks, favorites, and shares; when the goal of the campaign is to increase actual conversion, the relevant metrics include purchases.

[0045] Specifically, based on campaign performance data, it is possible to calculate the probability that a user will engage in a specific positive interactive behavior (such as clicking, saving, or purchasing) with a specific type of advertising content under a given campaign channel, product type, and content consumption model.

[0046] Assume that in the j-th distribution channel C j The k-th content consumption model M k Next, for the r-th product type D r Product advertising, ad content type S (tth ad). t When a user views an ad, the probability that the user will engage in the i-th type of positive interactive behavior (such as clicking, saving, sharing, or purchasing) is expressed as: Where i, j, k, r, and t are all integers greater than 0, then Calculated using the following formula: ; in, This indicates that in the first phase, users were using advertising channel C. j And it is in the content consumption model M k Below, regarding product type D r Advertising content type S t The number of times the i-th type of positive interactive behavior is generated by the advertising content, where T is the number of advertising content types.

[0047] For example, in the first stage, assuming that when users in Taobao's statistics are in goal-oriented mode, the number of clicks generated by placing science popularization advertisements on electronic products is 100, and assuming that the total number of clicks generated by placing all types of advertisements on electronic products in goal-oriented mode is 300, then it can be determined that on the Taobao platform, when users are in goal-oriented mode and are placed science popularization advertisements on electronic products, the probability that the user will perform the click behavior is 100 / 300 = 1 / 3.

[0048] Specifically, when the goal of ad placement is to increase brand exposure, the probability corresponding to any one of the metrics—click count, favorite count, or share count—can be selected as the user acceptance probability value P(S|C,M,D) when ad content of ad type S is placed on product type D under ad placement channel C and content consumption mode M. Then, by summing up the user acceptance probability values ​​corresponding to all ad content types under the given condition (C,M,D), the first probability distribution for different ad content types under a specific ad placement channel, specific product type, and specific content consumption mode can be obtained.

[0049] The sum of the user acceptance probabilities for all advertising content types under the given (C, M, D) conditions is 1.

[0050] Alternatively, to more comprehensively assess user acceptance, a weighted average can be calculated based on the user acceptance probabilities derived from the three metrics: click count, favorite count, and share count. This average yields a comprehensive probability, which can then be used to derive a first probability distribution for each ad content type. The weights assigned to click count, favorite count, and share count can be adjusted according to specific circumstances.

[0051] If the goal of the campaign is to improve actual conversion, calculate the probability that a user will make a purchase after the campaign channel C and content consumption mode M delivers the ad content of type S to product type D. This probability is then used as the probability that the user will accept the ad content type under the condition (C, M, D).

[0052] Understandably, different advertisers may pursue different benefit objectives at different marketing stages (such as increasing brand awareness or promoting direct sales). The solution provided in this application, by dynamically linking the delivery targets with the indicator data on which the probabilities are calculated, enables the quantitative measurement of users' willingness to accept advertisements from different business dimensions. This mechanism allows the optimization of advertising strategies not only to be based on historical results, but also to accurately align with current delivery objectives, thereby improving the overall return on advertising investment.

[0053] To improve the robustness of the user acceptance probability distribution calculation model, in an optional embodiment of this application, the above steps, for each combination determined by the delivery channel, product type, and content consumption mode, calculating the first probability distribution of user acceptance of different advertising content types under each combination based on relevant indicator data, may include: For each combination determined by the placement channel, product type, and content consumption mode, the initial probability value of users accepting each type of advertising content under each combination is calculated based on relevant indicator data; Obtain market environment data for the first phase; Input market environment data into the prediction model, and output the probability that users tend to prefer different types of advertising content under the current market environment, which is denoted as the market probability value. The initial probability value of each ad content type under each combination is multiplied by the corresponding market probability value and then normalized to obtain the user reception probability value of each ad content type under each combination. For each combination, the user reception probability values ​​of all ad content types under that combination are summarized to obtain the first probability distribution of user reception of different ad content types under each combination.

[0054] For example, suppose there are three types of ad content, and suppose there exists a combination where the initial probabilities of the three ad content types are 0.1, 0.2, and 0.7, and the market probabilities of the three ad content types are 0.2, 0.3, and 0.5, respectively. Then, for this combination, multiply the initial probability value of each ad content type by its market probability value to obtain [0.1×0.2, 0.2×0.3, 0.7×0.5] = [0.02, 0.06, 0.35]. Calculate the sum of these probabilities: 0.02 + 0.06 + 0.35 = 0.43. The final user acceptance probability value is... [0.02 / 0.43,0.06 / 0.43,0.35 / 0.43]≈[0.0465,0.1395,0.8140].

[0055] Market environment data may include macroeconomic indicators (such as the consumer spending index and consumer confidence index), industry trend indices, and competitor advertising intensity, which reflect market conditions.

[0056] Specifically, the prediction model uses a deep neural network, with market environment data as input and the probability that users tend to prefer different types of advertising content under the current market environment as output.

[0057] In an optional implementation, the above-mentioned S30, which formulates the advertising content type delivery strategy for each delivery channel based on the first probability distribution when the user is in different content consumption modes, may include: Calculate the matching degree between each delivery channel and each ad content type; Based on the product type of the target product, the user acceptance probability value corresponding to different advertising content types in each delivery channel and content consumption mode is determined by the first probability distribution. Based on the user acceptance probability value and the corresponding matching degree, calculate the recommendation score for each type of advertising content for the target product under each delivery channel and each content consumption mode. The recommendation score determines the ad content type delivery strategy to be implemented on different delivery channels and under different content consumption models.

[0058] Furthermore, the ad content type delivery strategy can be: Based on each advertising channel and each content consumption mode, a recommendation score is applied to each type of advertising content for the target product to determine the appropriate placement ratio for different types of advertising content for each advertising channel and each content consumption mode.

[0059] Alternatively, based on each advertising channel and each content consumption model, a recommendation score for each type of advertising content is used for the target product, and the advertising content type with the highest recommendation score is selected as the advertising content type used for the target product.

[0060] Among them, the platform attributes of the distribution channels can be popular science type (such as Baidu search, Zhihu), community type (such as Xiaohongshu, Weibo), online shopping type (such as Taobao, JD.com), and video interaction type (such as Tencent Video).

[0061] Specifically, based on marketing consensus and platform user group research and analysis, a matching degree F is preset for each pair (platform attribute type, advertising content type), with the score range usually being [0,1].

[0062] As an example, F(community type, expert recommendation type) = 0.9, F(science popularization type, science popularization promotion type) = 0.9, F(video interaction type, scenario interaction type) = 0.8, F(online shopping type, promotion type) = 0.9, M(science popularization type, scenario interaction type) = 0.3.

[0063] Then, the recommendation score for selecting ad content type S under the condition combination (C, M, D) is calculated using the following formula. : .

[0064] Where α and β are adjustable exponential parameters, α+β=1, and M(C,S) represents the matching degree between the placement channel C and the advertising content type S.

[0065] Then, for each combination of (C, M, D) conditions, the ad content type with the highest recommendation score is selected as the ad content type used by the target product in the second stage. Alternatively, the normalized recommendation score can be directly used as the placement ratio.

[0066] For example, if for a target product of product type M, under content consumption mode M in delivery channel C, if the recommendation scores for ad content types S1, S2, and S3 are 0.5, 0.3, and 0.2 respectively, then in this scenario, these three types of ad content will be allocated in a ratio of 5:3:2. Alternatively, ad content type S1 can be directly selected as the ad content type in this scenario.

[0067] It should be noted that the second phase was later than the first phase.

[0068] More specifically, when delivering advertising content according to the delivery ratio, the following steps can be taken: Set a fixed weight for each ad content type to the corresponding recommendation score; Obtain the dynamic weights of each ad content type at the end of the previous round, where the dynamic weights of each ad content type are 0 in the initial round; When selecting ad content type in each round, all ad content types are iterated through, and the dynamic weight of each ad content type at the end of the previous round is added to its fixed weight to obtain the dynamic weight of the current round. Select the ad content type with the highest dynamic weight in the current round as the selected ad content type for the current round; Subtract the sum of the fixed weights of all ad content types from the current dynamic weight of the selected ad content type to update the dynamic weight of the selected ad content type at the end of the current round.

[0069] For example, assuming the recommendation scores for ad content types S1, S2, and S3 are 0.6, 0.25, and 0.15 respectively, then the fixed weights for ad content types S1, S2, and S3 are 0.6, 0.25, and 0.15 respectively.

[0070] In the first round, the dynamic weights of ad content types S1, S2, and S3 are updated to 0.6+0=0.6, 0.25+0=0.25, and 0.15+0=0.15, respectively. Therefore, ad content type S1 with the highest weight in the first round is selected as the ad content type for this content consumption model. Then, the dynamic weight of ad content type S1 is updated to 0.6-1=-0.4. At the end of the first round, the dynamic weights of ad content types S1, S2, and S3 are -0.4, 0.25, and 0.15, respectively. In the second round, the dynamic weights of ad content types S1, S2, and S3 are updated to -0.2 + 0.6 = 0.4, 0.25 + 0.25 = 0.5, and 0.15 + 0.15 = 0.3, respectively. Therefore, ad content type S2 with the highest weight is selected as the ad content type for this content consumption model in the second round. At the end of the second round, the dynamic weights of ad content types S1, S2, and S3 are 0.4, -0.5, and 0.3, respectively. In the third round, the dynamic weights of ad content types S1, S2, and S3 are updated to 0.4 + 0.6 = 1, 0.25 - 0.5 = -0.25, and 0.15 + 0.3 = 0.45, respectively. Therefore, ad content type S1 with the highest dynamic weight is selected in the third round, and so on.

[0071] In this way, high-weight ad content types will be selected more frequently, while ensuring smoothness.

[0072] Accordingly, embodiments of this application also provide an apparatus for optimizing advertising delivery strategies, including: The acquisition module is used to acquire data on the performance of users in different content consumption modes and for different product types using different ad content types, based on statistics collected in the first phase from various advertising channels. The probability distribution calculation module is used to calculate the first probability distribution of users receiving different types of advertising content based on the campaign performance data, for each campaign channel and for each combination of product type and content consumption mode under the campaign channel. The strategy formulation module is used to formulate the ad content type delivery strategy for each delivery channel based on the first probability distribution for the target products to be launched in the second phase, when users are in different content consumption modes.

[0073] The technical principles and specific implementation processes of the above modules can be found in the various steps of the advertising placement strategy optimization method in the above embodiments, and will not be repeated here.

[0074] This application provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the advertising delivery strategy optimization method of any of the above embodiments. Reference is made below. Figure 2 It shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of this application.

[0075] The electronic devices in this application embodiment may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (such as in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 2 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this application. Figure 2As shown, the electronic device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. Various programs and data required for the operation of the electronic device are also stored in the RAM 1004 30. The processing unit 1001, ROM 1002 23, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. While electronic devices with various systems are shown in the figures, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0076] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0077] The electronic device provided in this application employs the advertising placement strategy optimization method described in the above embodiments. Compared with the prior art, the beneficial effects of the electronic device provided in this application are the same as those provided in the above embodiments, and other technical features of the electronic device are the same as those disclosed in the method of the previous embodiment, and will not be repeated here. It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples. The above are merely specific embodiments of this application, but the protection scope of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.

[0078] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the display rule determination method in the above embodiments. The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. Program code contained on a computer-readable storage medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (Radio Frequency), etc., or any suitable combination thereof. The aforementioned computer-readable storage medium may be contained within an electronic device; or it may exist independently, not assembled into an electronic device.

[0079] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0080] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions. Modules described in the embodiments of this application can be implemented in software or hardware. The names of modules do not, in some cases, constitute a limitation on the unit itself.

[0081] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the optimization method of the above-described advertising delivery strategy. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those provided in the above embodiments, and will not be repeated here. This application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps described above.

[0082] Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the advertising placement strategy optimization method provided in the above embodiments, and will not be repeated here.

[0083] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for optimizing an advertising delivery strategy, characterized in that, include: Obtain performance data from the first phase of the campaign, which shows the performance of users across different content consumption patterns and for different product types using different ad content types. Based on the aforementioned campaign performance data, for each campaign channel and for each combination of product type and content consumption mode under the campaign channel, calculate the first probability distribution of users receiving different types of advertising content. For the target products to be launched in the second phase, based on the first probability distribution, formulate the advertising content type delivery strategy to be executed by each of the aforementioned delivery channels when users are in different content consumption modes.

2. The method for optimizing advertising delivery strategies as described in claim 1, characterized in that, Based on the aforementioned campaign performance data, for each campaign channel and for each combination of product type and content consumption mode under that campaign channel, a first probability distribution of user acceptance of different advertising content types is calculated, including: Obtain the target product's deployment target in the second phase; Extract the indicator data related to the campaign objective from the campaign performance data; For each combination determined by the delivery channel, the product type, and the content consumption pattern, a first probability distribution of users receiving different types of advertising content under each combination is calculated based on the relevant indicator data.

3. The method for optimizing advertising placement strategies as described in claim 2, characterized in that, The step of extracting indicator data related to the campaign objective from the campaign performance data includes: When the campaign objective is to increase brand exposure, the relevant metrics include at least one of clicks, favorites, and shares. When the objective of the campaign is to improve actual conversion rates, the relevant metrics include purchase volume.

4. The method for optimizing advertising placement strategies as described in claim 2, characterized in that, For each combination determined by the delivery channel, the product type, and the content consumption pattern, the first probability distribution of user acceptance of different advertising content types under each combination is calculated based on the relevant indicator data, including: For each combination determined by the delivery channel, the product type, and the content consumption mode, the initial probability value of users accepting each type of advertising content under each combination is calculated based on the relevant indicator data. Obtain market environment data for the first phase; The market environment data is input into the prediction model, and the probability that users tend to prefer different types of advertising content under the current market environment is output, which is denoted as the market probability value. The initial probability value of each type of advertising content under each combination is multiplied by the corresponding market probability value and then normalized to obtain the user reception probability value of each type of advertising content under each combination. For each combination, the user reception probability values ​​of all ad content types under the corresponding combination are summarized to obtain the first probability distribution of user reception of different ad content types under each combination.

5. The method for optimizing advertising placement strategies as described in claim 1, characterized in that, The step of formulating the advertising content type delivery strategy for each delivery channel based on the first probability distribution when users are in different content consumption modes includes: Obtain the matching degree between each of the aforementioned delivery channels and each of the aforementioned advertising content types; Based on the product type of the target product, the user acceptance probability value corresponding to different advertising content types in each of the delivery channels and each of the content consumption modes is determined by the first probability distribution. Based on the user acceptance probability value and the corresponding matching degree, calculate the recommendation score for each type of advertising content for the target product under each of the aforementioned delivery channels and each of the aforementioned content consumption modes; Based on the recommendation score, the appropriate advertising content type delivery strategy will be determined for different delivery channels and different content consumption models.

6. The method for optimizing advertising delivery strategies as described in claim 5, characterized in that, The method for determining the ad content type delivery strategy based on the recommendation score for different delivery channels and different content consumption modes includes: Based on each of the aforementioned delivery channels and each of the aforementioned content consumption modes, a recommendation score for each of the aforementioned advertising content types is applied to the target product to determine the delivery ratio for different advertising content types for each delivery channel and each of the aforementioned content consumption modes. Alternatively, based on each of the aforementioned delivery channels and each of the aforementioned content consumption modes, a recommendation score for each of the aforementioned advertising content types is applied to the target product, and the advertising content type with the highest recommendation score is selected as the advertising content type used by the target product.

7. The method for optimizing advertising delivery strategies as described in claim 5, characterized in that, The method further includes: When implementing an ad content delivery strategy based on the aforementioned delivery ratio, the following steps are included: Set the fixed weight of each of the aforementioned advertising content types to the corresponding recommendation score; Obtain the dynamic weights of each of the aforementioned ad content types at the end of the previous round, wherein the dynamic weights of each of the aforementioned ad content types in the initial round are 0; When selecting ad content type in each round, all ad content types are traversed, and the dynamic weight of each ad content type at the end of the previous round is added to its corresponding fixed weight to obtain the dynamic weight of each ad content type in the current round. Select the ad content type with the highest dynamic weight in the current round as the selected ad content type for the current round; Subtract the sum of the fixed weights of all ad content types from the current dynamic weight of the selected ad content type to update the dynamic weight of the selected ad content type at the end of the current round.

8. The method for optimizing an advertising delivery strategy as described in any one of claims 1 to 7, characterized in that, The content consumption models include goal-oriented model, exploration model, and community interaction model.

9. An optimization device for advertising delivery strategies, characterized in that, include: The acquisition module is used to acquire data on the performance of users in different content consumption modes and for different product types using different ad content types, based on statistics collected in the first phase from various advertising channels. The probability distribution calculation module is used to calculate the first probability distribution of users receiving different types of advertising content based on the advertising performance data, for each advertising channel and for each combination of product type and content consumption mode under the advertising channel. The strategy formulation module is used to formulate, based on the first probability distribution, the advertising content type delivery strategy to be executed by each of the delivery channels when the user is in different content consumption modes for the target products to be delivered in the second stage.

10. An electronic device, characterized in that, The device includes a memory and a processor, the memory storing a computer program that, when processed by the processor, executes an optimization method for an advertising delivery strategy as described in any one of claims 1 to 8.

Images