Advertisement resource putting method and computer device

Abstract

The application relates to an advertisement resource putting method and a computer device. When there is failure data in the execution result of an advertisement resource executing a corresponding putting strategy, the application feeds back suggestion correction data of the difference data of the target advertisement resource executing the target putting strategy to the media side, receives confirmation information, judges whether to agree to modify the difference data of the target advertisement resource into the suggestion correction data, executes the target advertisement resource according to the suggestion correction data when the modification is agreed, executes the target advertisement resource according to the modified putting strategy when the modification is not agreed, optimizes the advertisement resource modification mode and the putting strategy modification mode according to the comparison result of the execution effect index value and historical data, can not only timely adjust the advertisement resource and / or the putting strategy content to improve the resource putting efficiency, but also can optimize the adjustment and modification mode and reduce the time consumption of the confirmation correction information.

Description

Technical Field

[0001] This application relates to the field of resource delivery technology, and in particular to an advertising resource delivery method and computer equipment. Background Technology

[0002] To improve resource allocation efficiency, it's crucial to categorize and allocate resources based on the demand side. For example, when allocating advertising resources on media platforms, advertisers develop corresponding placement strategies based on the advertising resource plan, such as bidding, target gender, and age. Currently, advertising resources are adjusted frequently based on the purpose of the campaign, and placement strategies are also adjusted according to feedback. Therefore, the advertising resources provided by the media platform may not match the advertiser's placement strategy, leading to ineffective placement of advertising resources. Currently, for a large number of advertising resources requiring adjustments to placement strategies, the advertiser's business personnel need to determine the specific adjustments and relay them to different media agencies for different adjustments. This process is not only time-consuming and prone to errors, but also cannot guarantee that every media agency will make timely adjustments, resulting in low resource allocation efficiency. Summary of the Invention

[0003] Based on this, an advertising resource delivery method and computer equipment are provided to solve the technical problems of mismatch caused by current adjustments to advertising resources and / or delivery strategy content, which leads to the failure of advertising resource delivery demanders, and the time-consuming and error-prone process of determining the adjustment content of the delivery strategy, resulting in low resource delivery efficiency.

[0004] On the one hand, a method for placing advertising resources is provided, the method comprising:

[0005] Receive the advertising resources to be delivered and the delivery strategy selected for the corresponding advertising resources, add the advertising resources to the advertising resource delivery list in sequence, and record the delivery strategy corresponding to each advertising resource in the advertising resource delivery list;

[0006] According to the advertising resource placement list, execute the corresponding placement strategy for each advertising resource in sequence, obtain the execution result of each advertising resource, and record the execution result in the advertising resource placement list;

[0007] The execution results include statistics on failure data of the target advertising resources in executing the target delivery strategy, analysis of the difference data of the failure of the target advertising resources in executing the target delivery strategy, acquisition of suggested correction data for correcting the difference data, and feedback.

[0008] Upon receiving confirmation information, determine whether to agree to modify the difference data of the target advertising resource to the suggested correction data;

[0009] In response to agreeing to modify the difference data of the target advertising resource to the suggested correction data, the corrected advertising resource is obtained, the corrected advertising resource is executed according to the target delivery strategy and the first execution performance index value is obtained, the first execution performance index value is compared with the first historical execution performance index value of the historical advertising resources executed according to the target delivery strategy, and the advertising resource modification method is optimized based on the comparison result.

[0010] In response to disagreement with modifying the difference data of the target advertising resource to the suggested correction data, the target delivery strategy is modified according to the target advertising resource to form a modified delivery strategy. The target advertising resource is executed according to the modified delivery strategy and a second performance indicator value is obtained. The second performance indicator value is compared with the second historical performance indicator value of the target advertising resource executed according to its corresponding delivery strategy in the past. The delivery strategy modification method is optimized according to the comparison result.

[0011] In one embodiment, the step of sequentially executing the corresponding delivery strategy for each advertising resource according to the advertising resource delivery list, obtaining the execution result for each advertising resource, and recording the execution result in the advertising resource delivery list includes:

[0012] According to the advertising resource placement list, obtain the data of each advertising resource and its corresponding placement strategy, and determine whether the data of the advertising resource and / or the placement strategy has changed;

[0013] In response to changes in the data of the advertising resource and / or the delivery strategy, the advertising resource executes the delivery strategy, and the execution result is recorded in the advertising resource delivery list;

[0014] If the data of the advertising resource and the delivery strategy have not changed, it is determined whether the advertising resource has result data after executing the delivery strategy. If the result data exists, the advertising resource does not execute the delivery strategy. If it does not exist, the advertising resource executes the delivery strategy, and the execution result is recorded in the advertising resource delivery list.

[0015] In one embodiment, the steps of receiving the advertising resources to be delivered and the delivery strategy selected for the corresponding advertising resources, adding the advertising resources to the advertising resource delivery list in sequence, and recording the delivery strategy corresponding to each advertising resource in the advertising resource delivery list include:

[0016] Receive advertising resources to be delivered, parse the advertising resources to obtain advertising structure data, the advertising structure data including advertising content and advertising delivery plan configuration data;

[0017] The advertising structure data is converted into data transmission unit messages, and the data transmission unit messages are standardized to form standardized transmission unit messages.

[0018] Add the primary key ID of the object table in the standardized transmission unit message to the advertising resource delivery list in the order of receipt;

[0019] The advertising placement strategy corresponding to the advertising resource is obtained based on the advertising placement plan configuration data in the standardized transmission unit message. The advertising placement strategy corresponding to the advertising resource is recorded in the advertising resource placement list. The placement strategy includes advertising placement time period, bid, target audience attributes and geographic targeting data.

[0020] After the corresponding delivery strategy is executed in response to the advertising resource, the number of executions and the execution result are recorded in the advertising resource delivery list.

[0021] In one embodiment, the step of obtaining the delivery strategy corresponding to the advertising resource based on the advertising delivery plan configuration data in the standardized transmission unit message, and recording the delivery strategy corresponding to the advertising resource in the advertising resource delivery list includes:

[0022] Obtain historical user exposure data, historical ad resource time-based consumption report data, and historical user quality score data;

[0023] Based on the historical user exposure data, historical advertising resource time-sharing consumption report data, and historical user quality score data, construct a data model of advertising plan performance based on the relationship between time-sharing user quality and consumption.

[0024] Using the time-segmented user quality and consumption relationship advertising plan performance data model, the corresponding advertising resource delivery strategy is obtained based on the advertising delivery plan configuration data in the standardized transmission unit message;

[0025] Set a strategy name and version number for the delivery strategy, and record the strategy name and version number of the delivery strategy in the ad resource delivery list.

[0026] In one embodiment, the step of constructing a time-segmented user quality and consumption relationship advertising plan performance data model based on the historical user exposure data, historical advertising resource time-segmented consumption report data, and historical user quality score data includes:

[0027] A data model of advertising campaign performance based on the relationship between user quality and consumption in different time periods is constructed using the Q-Learning algorithm, and the model is trained until convergence.

[0028] Obtain the advertising delivery plan configuration data from the standardized transmission unit message, and use the historical user exposure data, historical advertising resource time-sharing consumption report data, and historical user quality score data as performance data. Encode the advertising delivery plan configuration data and the performance data into a numerical vector.

[0029] In the time-segmented user quality and consumption relationship advertising plan performance data model, actions to adjust the delivery strategy are defined. These actions include changing the delivery time, increasing bids, decreasing bids, and changing the target audience attributes and geographic targeting data.

[0030] In one embodiment, the step of training the time-segmented user quality and consumption relationship advertising campaign performance data model until convergence includes:

[0031] The data model for the relationship between user quality and spending across different time periods in the advertising campaign performance is set up to update the Q-value using the Bellman equation: Where Q(s,a) represents the expected cumulative reward that may be obtained after taking action a in state s, α is the learning rate, r is the immediate reward, γ is the discount factor, s is the current state, a is the current action, s′ is the next state, and a′ is the next action. It is to choose the action that maximizes the Q value in the next state s′;

[0032] When training the data model of the relationship between user quality and consumption in the time period of the advertising plan, the Q value Q(s,a) is initialized to zero. The current state s is observed. An action a is selected according to the current delivery strategy. The action a is executed. The instant reward r and the next state s′ are observed. The Q value is updated using the Bellman equation. The state is transferred to s′. The above steps are repeated until the Q value converges.

[0033] In one embodiment, the step of obtaining the corresponding advertising resource delivery strategy based on the advertising delivery plan configuration data in the standardized transmission unit message using the time-segmented user quality and consumption relationship advertising plan performance data model includes:

[0034] The advertising campaign performance data model based on the time-segmented user quality and consumption relationship is used to adjust the bid of the advertising resources in real time according to the delivery strategy.

[0035] Obtain real-time user exposure data and real-time time-based consumption reports of advertising resources;

[0036] The advertising plan performance data model is adjusted in real time based on the real-time user exposure data and the time-sharing consumption report data of the real-time advertising resources to reflect the relationship between user quality and consumption in different time periods.

[0037] The revised data model of advertising campaign performance based on the relationship between user quality and consumption in different time periods is used to re-form the corresponding advertising resource delivery strategy.

[0038] In one embodiment, the step of real-time correction of the advertising plan performance data model based on the real-time user exposure data and the time-sharing consumption report data of the real-time advertising resources includes:

[0039] Obtain the hyperparameters of the advertising plan performance data model that shows the relationship between user quality and consumption across different time periods. The hyperparameters include the learning rate, discount factor, and network structure.

[0040] The performance of the time-segmented user quality and consumption relationship advertising campaign performance data model is evaluated using a test set or online A / B testing. The model is then optimized by adjusting the hyperparameters.

[0041] In one embodiment, the step of optimizing the delivery strategy modification method based on the comparison results includes:

[0042] Analyze the optimal click-through rate, conversion rate, cost per conversion, and return on investment among the comparison results. If the value of the second performance indicator is greater than the value of the second historical performance indicator of the historical target advertising resources executed according to their corresponding delivery strategies, it is determined to be positive feedback; otherwise, it is determined to be negative feedback.

[0043] When the probability of positive feedback is greater than a preset probability threshold, the system is set to not provide feedback and to receive confirmation information by suggesting correction data. The system automatically corrects the advertising time period, bid, target audience attributes, and geographic targeting data of the target advertising resource to form a corrected advertising strategy, and then executes the target advertising resource according to the corrected advertising strategy.

[0044] On the other hand, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor performs the following steps when executing the computer program:

[0045] Receive the advertising resources to be delivered and the delivery strategy selected for the corresponding advertising resources, add the advertising resources to the advertising resource delivery list in sequence, and record the delivery strategy corresponding to each advertising resource in the advertising resource delivery list;

[0046] According to the advertising resource placement list, execute the corresponding placement strategy for each advertising resource in sequence, obtain the execution result of each advertising resource, and record the execution result in the advertising resource placement list;

[0047] The execution results include statistics on failure data of the target advertising resources in executing the target delivery strategy, analysis of the difference data of the failure of the target advertising resources in executing the target delivery strategy, acquisition of suggested correction data for correcting the difference data, and feedback.

[0048] Upon receiving confirmation information, determine whether to agree to modify the difference data of the target advertising resource to the suggested correction data;

[0049] In response to agreeing to modify the difference data of the target advertising resource to the suggested correction data, the corrected advertising resource is obtained, the corrected advertising resource is executed according to the target delivery strategy and the first execution performance index value is obtained, the first execution performance index value is compared with the first historical execution performance index value of the historical advertising resources executed according to the target delivery strategy, and the advertising resource modification method is optimized based on the comparison result.

[0050] In response to disagreement with modifying the difference data of the target advertising resource to the suggested correction data, the target delivery strategy is modified according to the target advertising resource to form a modified delivery strategy. The target advertising resource is executed according to the modified delivery strategy and a second performance indicator value is obtained. The second performance indicator value is compared with the second historical performance indicator value of the target advertising resource executed according to its corresponding delivery strategy in the past. The delivery strategy modification method is optimized according to the comparison result.

[0051] The aforementioned advertising resource delivery method and computer equipment, when there is failure data in the execution result of the corresponding delivery strategy of the advertising resource, provide the media end with suggested correction data to correct the difference data of the target advertising resource failing to execute the target delivery strategy, receive confirmation information, determine whether to agree to modify the difference data of the target advertising resource to the suggested correction data, if agree, execute the corrected advertising resource according to the target delivery strategy, if disagree, execute the target advertising resource according to the corrected delivery strategy, and optimize the advertising resource modification method and delivery strategy modification method based on the comparison results of the execution effect index value and historical data. This not only can timely adjust the content of advertising resources and / or delivery strategies to improve resource delivery efficiency, but also optimize the adjustment and modification method and reduce the time spent confirming correction information. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1This is a diagram illustrating the application environment of an advertising resource delivery method in one embodiment of this application.

[0054] Figure 2 This is a logic diagram of an advertising resource delivery method in one embodiment of this application;

[0055] Figure 3 This is a flowchart illustrating an advertising resource delivery method in one embodiment of this application;

[0056] Figure 4 This is a logic diagram of optimizing the delivery strategy in one embodiment of this application;

[0057] Figure 5 This is a structural block diagram of an advertising resource delivery device in one embodiment of this application;

[0058] Figure 6 This is an internal structural diagram of a computer device in one embodiment of this application. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0060] The advertising resource delivery method provided in this application can be applied to, for example... Figure 1 In the application environment shown, the media terminal 101 and the resource delivery terminal 102 communicate via a network. The media terminal 101 has multiple agents, including advertising platforms such as Douyin, Toutiao, and Baidu. The media terminal 101 pushes advertising resources to be delivered to the resource delivery terminal 102, and synchronously selects the corresponding delivery strategy for the advertising resources. The resource delivery terminal 102 executes the corresponding delivery strategy for the advertising resources. The media terminal 101 and the resource delivery terminal 102 can be implemented using independent servers or a server cluster consisting of multiple servers.

[0061] In one embodiment, such as Figure 2 , Figure 3 As shown, an advertising resource delivery method is provided, which can be applied to... Figure 1 Taking resource delivery terminal 102 as an example, the explanation includes the following steps:

[0062] Step S1: Receive the advertising resources to be delivered and the delivery strategy selected for the corresponding advertising resources, add the advertising resources to the advertising resource delivery list in sequence, and record the delivery strategy corresponding to each advertising resource in the advertising resource delivery list;

[0063] Step S2: Execute the corresponding delivery strategy for each advertising resource in the order of the advertising resource delivery list, obtain the execution result of each advertising resource, and record the execution result in the advertising resource delivery list;

[0064] Step S3: Collect the failure data of the target advertising resources in the execution results for executing the target delivery strategy, analyze the difference data of the failure of the target advertising resources in executing the target delivery strategy, obtain the suggested correction data for correcting the difference data and provide feedback;

[0065] Step S4: Receive confirmation information and determine whether to agree to modify the difference data of the target advertising resource to the suggested correction data;

[0066] Step S5: In response to agreeing to modify the difference data of the target advertising resource to the suggested correction data, the returned corrected advertising resource is obtained, the corrected advertising resource is executed according to the target delivery strategy and the first execution effect index value is obtained, the first execution effect index value is compared with the first historical execution effect index value of the historical advertising resource executed according to the target delivery strategy, and the advertising resource modification method is optimized according to the comparison result.

[0067] Step S6: In response to disagreeing with modifying the difference data of the target advertising resource to the suggested correction data, the target delivery strategy is modified according to the target advertising resource to form a modified delivery strategy. The target advertising resource is executed according to the modified delivery strategy and a second performance indicator value is obtained. The second performance indicator value is compared with the second historical performance indicator value of the target advertising resource executed according to its corresponding delivery strategy in the past. The delivery strategy modification method is optimized according to the comparison result.

[0068] Specifically, when there is failure data in the execution result of the corresponding delivery strategy of the advertising resource, the system provides the media with suggested correction data to correct the difference data of the target advertising resource in the execution of the target delivery strategy. After receiving confirmation information, the system determines whether to agree to modify the difference data of the target advertising resource to the suggested correction data. If the system agrees, the corrected advertising resource is executed according to the target delivery strategy; if the system disagrees, the target advertising resource is executed according to the corrected delivery strategy. The system optimizes the modification method of advertising resources and delivery strategy based on the comparison results of the execution effect index value and historical data. This not only allows for timely adjustment of advertising resources and / or delivery strategy content to improve resource delivery efficiency, but also optimizes the adjustment and modification method and reduces the time spent confirming correction information.

[0069] In this embodiment, the steps of sequentially executing the corresponding delivery strategy for each advertising resource according to the advertising resource delivery list, obtaining the execution result for each advertising resource, and recording the execution result in the advertising resource delivery list include:

[0070] According to the advertising resource placement list, obtain the data of each advertising resource and its corresponding placement strategy, and determine whether the data of the advertising resource and / or the placement strategy has changed;

[0071] In response to changes in the data of the advertising resource and / or the delivery strategy, the advertising resource executes the delivery strategy, and the execution result is recorded in the advertising resource delivery list;

[0072] If the data of the advertising resource and the delivery strategy have not changed, it is determined whether the advertising resource has result data after executing the delivery strategy. If the result data exists, the advertising resource does not execute the delivery strategy. If it does not exist, the advertising resource executes the delivery strategy, and the execution result is recorded in the advertising resource delivery list.

[0073] In this embodiment, the steps of receiving the advertising resources to be delivered and the delivery strategy selected for the corresponding advertising resources, adding the advertising resources to the advertising resource delivery list in sequence, and recording the delivery strategy corresponding to each advertising resource in the advertising resource delivery list include:

[0074] Receive advertising resources to be delivered, parse the advertising resources to obtain advertising structure data, the advertising structure data including advertising content and advertising delivery plan configuration data;

[0075] The advertising structure data is converted into data transmission unit messages, and the data transmission unit messages are standardized to form standardized transmission unit messages.

[0076] Add the primary key ID of the object table in the standardized transmission unit message to the advertising resource delivery list in the order of receipt;

[0077] The advertising placement strategy corresponding to the advertising resource is obtained based on the advertising placement plan configuration data in the standardized transmission unit message. The advertising placement strategy corresponding to the advertising resource is recorded in the advertising resource placement list. The placement strategy includes advertising placement time period, bid, target audience attributes and geographic targeting data.

[0078] After the corresponding delivery strategy is executed in response to the advertising resource, the number of executions and the execution result are recorded in the advertising resource delivery list.

[0079] Among them, the data transmission unit message is preferably a Kafka message. A message in Kafka consists of two parts: the message body and the message header.

[0080] The message body is the actual data portion being transmitted; it can be any form of data, such as text, images, or videos. In Kafka, the message body is typically stored as a byte array.

[0081] The message header provides additional information that can be very important to consumers. For example, it can contain message metadata such as timestamps, sequence numbers, and version information. This information helps consumers better understand or process the message.

[0082] In Kafka, a complete message typically includes: key, value, timestamp, partition, and offset.

[0083] Key: Optional, used to distinguish different message streams. Within the same topic, messages with the same key will be sent to the same partition, which helps ensure message ordering.

[0084] Value: The actual content of the message, which can be data in any form.

[0085] Timestamp: The time when the message was created.

[0086] Partition: The partition to which a message is assigned.

[0087] Offset: A unique identifier within a partition, used to identify the location of a message within that partition.

[0088] The purpose of standardizing the data transmission unit messages to form standardized transmission unit messages is to eliminate the name differences in the advertising placement plan configuration data in the advertising resources to be placed by various agents, thereby achieving uniformity in the names of standardized transmission unit messages. For example, the names for user age attributes include the following:

[0089] Children: 0-12 years old, including infants (0-1 years old), toddlers (1-3 years old), and children (6-12 years old).

[0090] Adolescents: 13-19 years old, usually referred to as teenagers or young people.

[0091] Youth: 20-39 years old, people in this stage are in the development stage both physically and mentally.

[0092] Middle age: 40-59 years old. People in this stage are usually referred to as middle-aged or middle-aged.

[0093] Elderly: 60 years and older, including the elderly (60-74 years old) and the very old (75 years and older).

[0094] In this method, adding the primary key ID of the object table in the standardized transmission unit message to the advertising resource delivery list in the order of receipt can enable the corresponding advertising resource to be queried in the advertising resource delivery list by primary key ID.

[0095] In this embodiment, the step of obtaining the delivery strategy corresponding to the advertising resource based on the advertising delivery plan configuration data in the standardized transmission unit message, and recording the delivery strategy corresponding to the advertising resource in the advertising resource delivery list includes:

[0096] Obtain historical user exposure data, historical ad resource time-based consumption report data, and historical user quality score data;

[0097] Based on the historical user exposure data, historical advertising resource time-sharing consumption report data, and historical user quality score data, construct a data model of advertising plan performance based on the relationship between time-sharing user quality and consumption.

[0098] Using the time-segmented user quality and consumption relationship advertising plan performance data model, the corresponding advertising resource delivery strategy is obtained based on the advertising delivery plan configuration data in the standardized transmission unit message;

[0099] Set a strategy name and version number for the delivery strategy, and record the strategy name and version number of the delivery strategy in the ad resource delivery list.

[0100] In this embodiment, the step of constructing a time-segmented user quality and consumption relationship advertising plan performance data model based on the historical user exposure data, historical advertising resource time-segmented consumption report data, and historical user quality score data includes:

[0101] A data model of advertising campaign performance based on the relationship between user quality and consumption in different time periods is constructed using the Q-Learning algorithm, and the model is trained until convergence.

[0102] Obtain the advertising delivery plan configuration data from the standardized transmission unit message, and use the historical user exposure data, historical advertising resource time-sharing consumption report data, and historical user quality score data as performance data. Encode the advertising delivery plan configuration data and the performance data into a numerical vector.

[0103] In the time-segmented user quality and consumption relationship advertising plan performance data model, actions to adjust the delivery strategy are defined. These actions include changing the delivery time, increasing bids, decreasing bids, and changing the target audience attributes and geographic targeting data.

[0104] Q-learning is a model-free reinforcement learning algorithm used to solve Markov Decision Process (MDP) problems. Its goal is to enable an agent to learn an optimal policy through interaction with its environment, thereby maximizing cumulative reward. The core idea of ​​Q-learning is to evaluate the long-term value of taking an action in a given state by continuously updating a function called the Q-value. The goal of the Q-value function is to find the optimal policy, that is, to choose the action that maximizes the Q-value in each state. The core of Q-learning is using the Bellman equation to update the Q-value.

[0105] In a Markov Decision Process (MDP), a state is the set of states of the environment, representing the different situations in which the agent is situated. An action is the set of actions the agent can take in each state. A reward is the immediate feedback returned by the environment after the agent performs an action. A transition probability is the probability of transitioning to the next state after taking an action in a given state.

[0106] In this embodiment, the step of training the time-segmented user quality and consumption relationship advertising campaign performance data model until convergence includes:

[0107] The data model for the relationship between user quality and spending across different time periods in the advertising campaign performance is set up to update the Q-value using the Bellman equation: Where Q(s,a) represents the expected cumulative reward that may be obtained after taking action a in state s, α is the learning rate, r is the immediate reward, γ is the discount factor, s is the current state, a is the current action, s′ is the next state, and a′ is the next action. It is to choose the action that maximizes the Q value in the next state s′;

[0108] When training the data model of advertising campaign performance based on the relationship between user quality and consumption in different time periods, the Q value Q(s,a) is initialized to zero. The current state s is observed, and an action a is selected according to the current delivery strategy. The action a is executed, and the immediate reward r and the next state s′ are observed. The Q value is updated using the Bellman equation, and the state is transferred to s′. The above steps are repeated until the Q value converges. The selection of an action a according to the current delivery strategy includes: setting the current delivery strategy to an ∈-greedy strategy, using the ∈-greedy strategy to select an action, that is, randomly selecting an action with a probability of ∈, and selecting the current optimal action with a probability of 1-∈.

[0109] like Figure 4 As shown, Figure 4 A logic diagram for optimizing the delivery strategy.

[0110] In this embodiment, the step of obtaining the corresponding advertising resource delivery strategy based on the advertising delivery plan configuration data in the standardized transmission unit message using the time-segmented user quality and consumption relationship advertising plan effect data model includes:

[0111] The advertising campaign performance data model based on the time-segmented user quality and consumption relationship is used to adjust the bid of the advertising resources in real time according to the delivery strategy.

[0112] Obtain real-time user exposure data and real-time time-based consumption reports of advertising resources;

[0113] The advertising plan performance data model is adjusted in real time based on the real-time user exposure data and the time-sharing consumption report data of the real-time advertising resources to reflect the relationship between user quality and consumption in different time periods.

[0114] The revised data model of advertising campaign performance based on the relationship between user quality and consumption in different time periods is used to re-form the corresponding advertising resource delivery strategy.

[0115] By creating validation rules based on a data model of the relationship between user quality and consumption in different time periods for advertising campaign performance, the system can verify the advertising resource placement plans of agencies in real time and assist agencies in making real-time adjustments, saving agencies time operating in the media backend and enabling adjustments anytime, anywhere.

[0116] In this embodiment, the step of real-time correction of the advertising plan performance data model based on the real-time user exposure data and the time-sharing consumption report data of the real-time advertising resources includes:

[0117] Obtain the hyperparameters of the advertising plan performance data model that shows the relationship between user quality and consumption across different time periods. The hyperparameters include the learning rate, discount factor, and network structure.

[0118] The performance of the time-segmented user quality and consumption relationship advertising campaign performance data model is evaluated using a test set or online A / B testing. The model is then optimized by adjusting the hyperparameters.

[0119] First, initialize the Q-value table (Q-learning).

[0120] Secondly, the loop (at each time step) works as follows: Observe the state: Obtain the current ad delivery configuration and performance data. Select an action: Select an action based on the current strategy (e.g., ∈-greedy strategy). Execute the action: Adjust the ad delivery configuration. Observe the reward and new state: Obtain new ad performance data and state. Store the experience: Save the experience (state, action, reward, new state). Update the Q-value: Update the Q-value using the Bellman equation.

[0121] Finally, the termination condition is either reaching the predetermined number of training steps or achieving the expected advertising effect. Through reinforcement learning models, advertising strategies can be dynamically adjusted to maximize the effectiveness of advertising resource allocation.

[0122] In this embodiment, the step of optimizing the delivery strategy modification method based on the comparison results includes:

[0123] Analyze the optimal click-through rate, conversion rate, cost per conversion, and return on investment among the comparison results. If the value of the second performance indicator is greater than the value of the second historical performance indicator of the historical target advertising resources executed according to their corresponding delivery strategies, it is determined to be positive feedback; otherwise, it is determined to be negative feedback.

[0124] When the probability of positive feedback is greater than a preset probability threshold, the system is set to not provide feedback and to receive confirmation information by suggesting correction data. The system automatically corrects the advertising time period, bid, target audience attributes, and geographic targeting data of the target advertising resource to form a corrected advertising strategy, and then executes the target advertising resource according to the corrected advertising strategy.

[0125] The preset probability threshold is preferably 90%. Based on positive and negative feedback, if accepting the suggested data correction results in a worse effect, the model will continue to be optimized and modified. If accepting the suggested data correction results in a better effect, it means that the suggested data correction is effective. When the probability of positive feedback reaches an execution rate of over 90%, it is no longer necessary to confirm the modification content. Instead, the system directly modifies the parameters corresponding to the target delivery strategy, achieving unattended automatic processing.

[0126] The method for analyzing the optimal click-through rate, conversion rate, cost per conversion, and return on investment from the comparison results is as follows.

[0127] Click-through rate (CTR): CTR = Clicks / Impressions; where Clicks is the number of clicks and Impressions is the number of impressions;

[0128] Conversion Rate (CVR): CVR = Conversions / ClicksCVR; where Conversions is the number of conversions and ClicksCVR is the number of clicks.

[0129] Cost per conversion (CPA): CPA = Cost / Conversions; where Cost is the investment cost and Conversions is the number of conversions.

[0130] Return on Investment (ROI): ROI = (Revenue - Cost) / Cost, where Revenue is the investment income and Cost is the investment cost.

[0131] In the aforementioned advertising resource delivery method, when there is failure data in the execution result of the corresponding delivery strategy of the advertising resource, suggested correction data is fed back to the media to correct the difference data of the target advertising resource failing to execute the target delivery strategy. Confirmation information is received, and it is determined whether to agree to modify the difference data of the target advertising resource to the suggested correction data. If agreed, the corrected advertising resource is executed according to the target delivery strategy; if disagreed, the target advertising resource is executed according to the corrected delivery strategy. The method of modifying advertising resources and delivery strategies is optimized based on the comparison results of the execution effect index values ​​and historical data. This not only allows for timely adjustment of advertising resources and / or delivery strategy content to improve resource delivery efficiency, but also optimizes the adjustment and modification methods and reduces the time spent confirming correction information.

[0132] It should be understood that, although Figures 2-4 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figures 2-4 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0133] In one embodiment, such as Figure 5As shown, an advertising resource delivery device 10 is provided, including: a data receiving module 1, a delivery strategy execution statistics module 2, an invalid data correction module 3, a data correction interaction module 4, an advertising modification and optimization module 5, and a strategy modification and optimization module 6.

[0134] The data receiving module 1 is used to receive the advertising resources to be delivered and the delivery strategy selected for the corresponding advertising resources, add the advertising resources to the advertising resource delivery list in sequence, and record the delivery strategy corresponding to each advertising resource in the advertising resource delivery list.

[0135] The delivery strategy execution statistics module 2 is used to execute the corresponding delivery strategy for each advertising resource in the order of the advertising resource delivery list, obtain the execution result of each advertising resource, and record the execution result in the advertising resource delivery list.

[0136] The failure data correction module 3 is used to statistically analyze the failure data of the target advertising resources in the execution results, analyze the difference data of the failure of the target advertising resources in the execution of the target advertising strategy, obtain suggested correction data for correcting the difference data, and provide feedback.

[0137] The data correction interaction module 4 is used to receive confirmation information and determine whether to agree to modify the difference data of the target advertising resource to the suggested correction data.

[0138] The advertising modification and optimization module 5 is used to respond to the agreement to modify the difference data of the target advertising resource to the suggested correction data, then obtain the returned corrected advertising resource, execute the corrected advertising resource according to the target delivery strategy and obtain the first execution effect index value, compare the first execution effect index value with the first historical execution effect index value of historical advertising resources executed according to the target delivery strategy, and optimize the advertising resource modification method based on the comparison result.

[0139] The strategy modification and optimization module 6 is used to respond to disagreement with modifying the difference data of the target advertising resource to the suggested correction data, then modify the target delivery strategy according to the target advertising resource to form a modified delivery strategy, execute the target advertising resource according to the modified delivery strategy and obtain the second execution effect index value, compare the second execution effect index value with the second historical execution effect index value of the historical target advertising resource executed according to its corresponding delivery strategy, and optimize the delivery strategy modification method according to the comparison result.

[0140] In this embodiment, the steps of sequentially executing the corresponding delivery strategy for each advertising resource according to the advertising resource delivery list, obtaining the execution result for each advertising resource, and recording the execution result in the advertising resource delivery list include:

[0141] According to the advertising resource placement list, obtain the data of each advertising resource and its corresponding placement strategy, and determine whether the data of the advertising resource and / or the placement strategy has changed;

[0142] In response to changes in the data of the advertising resource and / or the delivery strategy, the advertising resource executes the delivery strategy, and the execution result is recorded in the advertising resource delivery list;

[0143] If the data of the advertising resource and the delivery strategy have not changed, it is determined whether the advertising resource has result data after executing the delivery strategy. If the result data exists, the advertising resource does not execute the delivery strategy. If it does not exist, the advertising resource executes the delivery strategy, and the execution result is recorded in the advertising resource delivery list.

[0144] In this embodiment, the steps of receiving the advertising resources to be delivered and the delivery strategy selected for the corresponding advertising resources, adding the advertising resources to the advertising resource delivery list in sequence, and recording the delivery strategy corresponding to each advertising resource in the advertising resource delivery list include:

[0145] Receive advertising resources to be delivered, parse the advertising resources to obtain advertising structure data, the advertising structure data including advertising content and advertising delivery plan configuration data;

[0146] The advertising structure data is converted into data transmission unit messages, and the data transmission unit messages are standardized to form standardized transmission unit messages.

[0147] Add the primary key ID of the object table in the standardized transmission unit message to the advertising resource delivery list in the order of receipt;

[0148] The advertising placement strategy corresponding to the advertising resource is obtained based on the advertising placement plan configuration data in the standardized transmission unit message. The advertising placement strategy corresponding to the advertising resource is recorded in the advertising resource placement list. The placement strategy includes advertising placement time period, bid, target audience attributes and geographic targeting data.

[0149] After the corresponding delivery strategy is executed in response to the advertising resource, the number of executions and the execution result are recorded in the advertising resource delivery list.

[0150] In this embodiment, the step of obtaining the delivery strategy corresponding to the advertising resource based on the advertising delivery plan configuration data in the standardized transmission unit message, and recording the delivery strategy corresponding to the advertising resource in the advertising resource delivery list includes:

[0151] Obtain historical user exposure data, historical ad resource time-based consumption report data, and historical user quality score data;

[0152] Based on the historical user exposure data, historical advertising resource time-sharing consumption report data, and historical user quality score data, construct a data model of advertising plan performance based on the relationship between time-sharing user quality and consumption.

[0153] Using the time-segmented user quality and consumption relationship advertising plan performance data model, the corresponding advertising resource delivery strategy is obtained based on the advertising delivery plan configuration data in the standardized transmission unit message;

[0154] Set a strategy name and version number for the delivery strategy, and record the strategy name and version number of the delivery strategy in the ad resource delivery list.

[0155] In this embodiment, the step of constructing a time-segmented user quality and consumption relationship advertising plan performance data model based on the historical user exposure data, historical advertising resource time-segmented consumption report data, and historical user quality score data includes:

[0156] A data model of advertising campaign performance based on the relationship between user quality and consumption in different time periods is constructed using the Q-Learning algorithm, and the model is trained until convergence.

[0157] Obtain the advertising delivery plan configuration data from the standardized transmission unit message, and use the historical user exposure data, historical advertising resource time-sharing consumption report data, and historical user quality score data as performance data. Encode the advertising delivery plan configuration data and the performance data into a numerical vector.

[0158] In the time-segmented user quality and consumption relationship advertising plan performance data model, actions to adjust the delivery strategy are defined. These actions include changing the delivery time, increasing bids, decreasing bids, and changing the target audience attributes and geographic targeting data.

[0159] In this embodiment, the step of training the time-segmented user quality and consumption relationship advertising campaign performance data model until convergence includes:

[0160] The data model for the relationship between user quality and spending across different time periods in the advertising campaign performance is set up to update the Q-value using the Bellman equation: Where Q(s,a) represents the expected cumulative reward that may be obtained after taking action a in state s, α is the learning rate, r is the immediate reward, γ is the discount factor, s is the current state, a is the current action, s′ is the next state, and a′ is the next action. It is to choose the action that maximizes the Q value in the next state s′;

[0161] When training the data model of advertising campaign performance based on the relationship between user quality and consumption in different time periods, the Q value Q(s,a) is initialized to zero. The current state s is observed, and an action a is selected according to the current delivery strategy. The action a is executed, and the immediate reward r and the next state s′ are observed. The Q value is updated using the Bellman equation, and the state is transferred to s′. The above steps are repeated until the Q value converges. The selection of an action a according to the current delivery strategy includes: setting the current delivery strategy to an ∈-greedy strategy, using the ∈-greedy strategy to select an action, that is, randomly selecting an action with a probability of ∈, and selecting the current optimal action with a probability of 1-∈.

[0162] In this embodiment, the step of obtaining the corresponding advertising resource delivery strategy based on the advertising delivery plan configuration data in the standardized transmission unit message using the time-segmented user quality and consumption relationship advertising plan effect data model includes:

[0163] The advertising campaign performance data model based on the time-segmented user quality and consumption relationship is used to adjust the bid of the advertising resources in real time according to the delivery strategy.

[0164] Obtain real-time user exposure data and real-time time-based consumption reports of advertising resources;

[0165] The advertising plan performance data model is adjusted in real time based on the real-time user exposure data and the time-sharing consumption report data of the real-time advertising resources to reflect the relationship between user quality and consumption in different time periods.

[0166] The revised data model of advertising campaign performance based on the relationship between user quality and consumption in different time periods is used to re-form the corresponding advertising resource delivery strategy.

[0167] In this embodiment, the step of real-time correction of the advertising plan performance data model based on the real-time user exposure data and the time-sharing consumption report data of the real-time advertising resources includes:

[0168] Obtain the hyperparameters of the advertising plan performance data model that shows the relationship between user quality and consumption across different time periods. The hyperparameters include the learning rate, discount factor, and network structure.

[0169] The performance of the time-segmented user quality and consumption relationship advertising campaign performance data model is evaluated using a test set or online A / B testing. The model is then optimized by adjusting the hyperparameters.

[0170] In this embodiment, the step of optimizing the delivery strategy modification method based on the comparison results includes:

[0171] Analyze the optimal click-through rate, conversion rate, cost per conversion, and return on investment among the comparison results. If the value of the second performance indicator is greater than the value of the second historical performance indicator of the historical target advertising resources executed according to their corresponding delivery strategies, it is determined to be positive feedback; otherwise, it is determined to be negative feedback.

[0172] When the probability of positive feedback is greater than a preset probability threshold, the system is set to not provide feedback and to receive confirmation information by suggesting correction data. The system automatically corrects the advertising time period, bid, target audience attributes, and geographic targeting data of the target advertising resource to form a corrected advertising strategy, and then executes the target advertising resource according to the corrected advertising strategy.

[0173] In the aforementioned advertising resource delivery device, when there is failure data in the execution result of the corresponding delivery strategy of the advertising resource, suggested correction data is fed back to the media end to correct the difference data of the target advertising resource failing to execute the target delivery strategy. Confirmation information is received, and it is determined whether to agree to modify the difference data of the target advertising resource to the suggested correction data. If agreed, the corrected advertising resource is executed according to the target delivery strategy; if disagreed, the target advertising resource is executed according to the corrected delivery strategy. The method of modifying advertising resources and delivery strategies is optimized based on the comparison results of the execution effect index value and historical data. This not only allows for timely adjustment of advertising resources and / or delivery strategy content to improve resource delivery efficiency, but also optimizes the adjustment and modification method and reduces the time spent confirming correction information.

[0174] Specific limitations regarding the advertising resource delivery device can be found in the limitations on advertising resource delivery methods described above, and will not be repeated here. Each module in the aforementioned advertising resource delivery device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0175] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0176] Receive the advertising resources to be delivered and the delivery strategy selected for the corresponding advertising resources, add the advertising resources to the advertising resource delivery list in sequence, and record the delivery strategy corresponding to each advertising resource in the advertising resource delivery list;

[0177] According to the advertising resource placement list, execute the corresponding placement strategy for each advertising resource in sequence, obtain the execution result of each advertising resource, and record the execution result in the advertising resource placement list;

[0178] The execution results include statistics on failure data of the target advertising resources in executing the target delivery strategy, analysis of the difference data of the failure of the target advertising resources in executing the target delivery strategy, acquisition of suggested correction data for correcting the difference data, and feedback.

[0179] Upon receiving confirmation information, determine whether to agree to modify the difference data of the target advertising resource to the suggested correction data;

[0180] In response to agreeing to modify the difference data of the target advertising resource to the suggested correction data, the corrected advertising resource is obtained, the corrected advertising resource is executed according to the target delivery strategy and the first execution performance index value is obtained, the first execution performance index value is compared with the first historical execution performance index value of the historical advertising resources executed according to the target delivery strategy, and the advertising resource modification method is optimized based on the comparison result.

[0181] In response to disagreement with modifying the difference data of the target advertising resource to the suggested correction data, the target delivery strategy is modified according to the target advertising resource to form a modified delivery strategy. The target advertising resource is executed according to the modified delivery strategy and a second performance indicator value is obtained. The second performance indicator value is compared with the second historical performance indicator value of the target advertising resource executed according to its corresponding delivery strategy in the past. The delivery strategy modification method is optimized according to the comparison result.

[0182] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0183] The steps of sequentially executing the corresponding delivery strategy for each advertising resource according to the advertising resource delivery list, obtaining the execution result for each advertising resource, and recording the execution result in the advertising resource delivery list include:

[0184] According to the advertising resource placement list, obtain the data of each advertising resource and its corresponding placement strategy, and determine whether the data of the advertising resource and / or the placement strategy has changed;

[0185] In response to changes in the data of the advertising resource and / or the delivery strategy, the advertising resource executes the delivery strategy, and the execution result is recorded in the advertising resource delivery list;

[0186] If the data of the advertising resource and the delivery strategy have not changed, it is determined whether the advertising resource has result data after executing the delivery strategy. If the result data exists, the advertising resource does not execute the delivery strategy. If it does not exist, the advertising resource executes the delivery strategy, and the execution result is recorded in the advertising resource delivery list.

[0187] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0188] The steps of receiving the advertising resources to be delivered and the delivery strategy selected for the corresponding advertising resources, adding the advertising resources to the advertising resource delivery list in sequence, and recording the delivery strategy corresponding to each advertising resource in the advertising resource delivery list include:

[0189] Receive advertising resources to be delivered, parse the advertising resources to obtain advertising structure data, the advertising structure data including advertising content and advertising delivery plan configuration data;

[0190] The advertising structure data is converted into data transmission unit messages, and the data transmission unit messages are standardized to form standardized transmission unit messages.

[0191] Add the primary key ID of the object table in the standardized transmission unit message to the advertising resource delivery list in the order of receipt;

[0192] The advertising placement strategy corresponding to the advertising resource is obtained based on the advertising placement plan configuration data in the standardized transmission unit message. The advertising placement strategy corresponding to the advertising resource is recorded in the advertising resource placement list. The placement strategy includes advertising placement time period, bid, target audience attributes and geographic targeting data.

[0193] After the corresponding delivery strategy is executed in response to the advertising resource, the number of executions and the execution result are recorded in the advertising resource delivery list.

[0194] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0195] The step of obtaining the delivery strategy corresponding to the advertising resource based on the advertising delivery plan configuration data in the standardized transmission unit message, and recording the delivery strategy corresponding to the advertising resource in the advertising resource delivery list includes:

[0196] Obtain historical user exposure data, historical ad resource time-based consumption report data, and historical user quality score data;

[0197] Based on the historical user exposure data, historical advertising resource time-sharing consumption report data, and historical user quality score data, construct a data model of advertising plan performance based on the relationship between time-sharing user quality and consumption.

[0198] Using the time-segmented user quality and consumption relationship advertising plan performance data model, the corresponding advertising resource delivery strategy is obtained based on the advertising delivery plan configuration data in the standardized transmission unit message;

[0199] Set a strategy name and version number for the delivery strategy, and record the strategy name and version number of the delivery strategy in the ad resource delivery list.

[0200] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0201] The steps of constructing a time-segmented user quality and consumption relationship advertising plan performance data model based on the historical user exposure data, historical advertising resource time-segmented consumption report data, and historical user quality score data include:

[0202] A data model of advertising campaign performance based on the relationship between user quality and consumption in different time periods is constructed using the Q-Learning algorithm, and the model is trained until convergence.

[0203] Obtain the advertising delivery plan configuration data from the standardized transmission unit message, and use the historical user exposure data, historical advertising resource time-sharing consumption report data, and historical user quality score data as performance data. Encode the advertising delivery plan configuration data and the performance data into a numerical vector.

[0204] In the time-segmented user quality and consumption relationship advertising plan performance data model, actions to adjust the delivery strategy are defined. These actions include changing the delivery time, increasing bids, decreasing bids, and changing the target audience attributes and geographic targeting data.

[0205] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0206] The steps for training the time-segmented user quality and consumption relationship advertising campaign performance data model until convergence include:

[0207] The data model for the relationship between user quality and spending across different time periods in the advertising campaign performance is set up to update the Q-value using the Bellman equation: Where Q(s,a) represents the expected cumulative reward that may be obtained after taking action a in state s, α is the learning rate, r is the immediate reward, γ is the discount factor, s is the current state, a is the current action, s′ is the next state, and a′ is the next action. It is to choose the action that maximizes the Q value in the next state s′;

[0208] When training the data model of advertising campaign performance based on the relationship between user quality and consumption in different time periods, the Q value Q(s,a) is initialized to zero. The current state s is observed, and an action a is selected according to the current delivery strategy. The action a is executed, and the immediate reward r and the next state s′ are observed. The Q value is updated using the Bellman equation, and the state is transferred to s′. The above steps are repeated until the Q value converges. The selection of an action a according to the current delivery strategy includes: setting the current delivery strategy to an ∈-greedy strategy, using the ∈-greedy strategy to select an action, that is, randomly selecting an action with a probability of ∈, and selecting the current optimal action with a probability of 1-∈.

[0209] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0210] The step of obtaining the corresponding advertising resource delivery strategy based on the advertising delivery plan configuration data in the standardized transmission unit message using the time-segmented user quality and consumption relationship advertising plan performance data model includes:

[0211] The advertising campaign performance data model based on the time-segmented user quality and consumption relationship is used to adjust the bid of the advertising resources in real time according to the delivery strategy.

[0212] Obtain real-time user exposure data and real-time time-based consumption reports of advertising resources;

[0213] The advertising plan performance data model is adjusted in real time based on the real-time user exposure data and the time-sharing consumption report data of the real-time advertising resources to reflect the relationship between user quality and consumption in different time periods.

[0214] The revised data model of advertising campaign performance based on the relationship between user quality and consumption in different time periods is used to re-form the corresponding advertising resource delivery strategy.

[0215] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0216] The step of real-time correction of the advertising plan performance data model based on the real-time user exposure data and the time-sharing consumption report data of the real-time advertising resources includes:

[0217] Obtain the hyperparameters of the advertising plan performance data model that shows the relationship between user quality and consumption across different time periods. The hyperparameters include the learning rate, discount factor, and network structure.

[0218] The performance of the time-segmented user quality and consumption relationship advertising campaign performance data model is evaluated using a test set or online A / B testing. The model is then optimized by adjusting the hyperparameters.

[0219] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0220] The steps for optimizing the delivery strategy based on the comparison results include:

[0221] Analyze the optimal click-through rate, conversion rate, cost per conversion, and return on investment among the comparison results. If the value of the second performance indicator is greater than the value of the second historical performance indicator of the historical target advertising resources executed according to their corresponding delivery strategies, it is determined to be positive feedback; otherwise, it is determined to be negative feedback.

[0222] When the probability of positive feedback is greater than a preset probability threshold, the system is set to not provide feedback and to receive confirmation information by suggesting correction data. The system automatically corrects the advertising time period, bid, target audience attributes, and geographic targeting data of the target advertising resource to form a corrected advertising strategy, and then executes the target advertising resource according to the corrected advertising strategy.

[0223] For specific limitations on the steps implemented when a computer program is executed by a processor, please refer to the limitations on the methods of advertising resource placement mentioned above, which will not be repeated here.

[0224] In one embodiment, a computer device is provided, which may be a resource delivery terminal, and its internal structure diagram may be as follows: Figure 6 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system, computer programs, and the database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores advertising resource delivery data. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements an advertising resource delivery method.

[0225] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0226] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps:

[0227] Receive the advertising resources to be delivered and the delivery strategy selected for the corresponding advertising resources, add the advertising resources to the advertising resource delivery list in sequence, and record the delivery strategy corresponding to each advertising resource in the advertising resource delivery list;

[0228] According to the advertising resource placement list, execute the corresponding placement strategy for each advertising resource in sequence, obtain the execution result of each advertising resource, and record the execution result in the advertising resource placement list;

[0229] The execution results include statistics on failure data of the target advertising resources in executing the target delivery strategy, analysis of the difference data of the failure of the target advertising resources in executing the target delivery strategy, acquisition of suggested correction data for correcting the difference data, and feedback.

[0230] Upon receiving confirmation information, determine whether to agree to modify the difference data of the target advertising resource to the suggested correction data;

[0231] In response to agreeing to modify the difference data of the target advertising resource to the suggested correction data, the corrected advertising resource is obtained, the corrected advertising resource is executed according to the target delivery strategy and the first execution performance index value is obtained, the first execution performance index value is compared with the first historical execution performance index value of the historical advertising resources executed according to the target delivery strategy, and the advertising resource modification method is optimized based on the comparison result.

[0232] In response to disagreement with modifying the difference data of the target advertising resource to the suggested correction data, the target delivery strategy is modified according to the target advertising resource to form a modified delivery strategy. The target advertising resource is executed according to the modified delivery strategy and a second performance indicator value is obtained. The second performance indicator value is compared with the second historical performance indicator value of the target advertising resource executed according to its corresponding delivery strategy in the past. The delivery strategy modification method is optimized according to the comparison result.

[0233] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0234] The steps of sequentially executing the corresponding delivery strategy for each advertising resource according to the advertising resource delivery list, obtaining the execution result for each advertising resource, and recording the execution result in the advertising resource delivery list include:

[0235] According to the advertising resource placement list, obtain the data of each advertising resource and its corresponding placement strategy, and determine whether the data of the advertising resource and / or the placement strategy has changed;

[0236] In response to changes in the data of the advertising resource and / or the delivery strategy, the advertising resource executes the delivery strategy, and the execution result is recorded in the advertising resource delivery list;

[0237] If the data of the advertising resource and the delivery strategy have not changed, it is determined whether the advertising resource has result data after executing the delivery strategy. If the result data exists, the advertising resource does not execute the delivery strategy. If it does not exist, the advertising resource executes the delivery strategy, and the execution result is recorded in the advertising resource delivery list.

[0238] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0239] The steps of receiving the advertising resources to be delivered and the delivery strategy selected for the corresponding advertising resources, adding the advertising resources to the advertising resource delivery list in sequence, and recording the delivery strategy corresponding to each advertising resource in the advertising resource delivery list include:

[0240] Receive advertising resources to be delivered, parse the advertising resources to obtain advertising structure data, the advertising structure data including advertising content and advertising delivery plan configuration data;

[0241] The advertising structure data is converted into data transmission unit messages, and the data transmission unit messages are standardized to form standardized transmission unit messages.

[0242] Add the primary key ID of the object table in the standardized transmission unit message to the advertising resource delivery list in the order of receipt;

[0243] The advertising placement strategy corresponding to the advertising resource is obtained based on the advertising placement plan configuration data in the standardized transmission unit message. The advertising placement strategy corresponding to the advertising resource is recorded in the advertising resource placement list. The placement strategy includes advertising placement time period, bid, target audience attributes and geographic targeting data.

[0244] After the corresponding delivery strategy is executed in response to the advertising resource, the number of executions and the execution result are recorded in the advertising resource delivery list.

[0245] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0246] The step of obtaining the delivery strategy corresponding to the advertising resource based on the advertising delivery plan configuration data in the standardized transmission unit message, and recording the delivery strategy corresponding to the advertising resource in the advertising resource delivery list includes:

[0247] Obtain historical user exposure data, historical ad resource time-based consumption report data, and historical user quality score data;

[0248] Based on the historical user exposure data, historical advertising resource time-sharing consumption report data, and historical user quality score data, construct a data model of advertising plan performance based on the relationship between time-sharing user quality and consumption.

[0249] Using the time-segmented user quality and consumption relationship advertising plan performance data model, the corresponding advertising resource delivery strategy is obtained based on the advertising delivery plan configuration data in the standardized transmission unit message;

[0250] Set a strategy name and version number for the delivery strategy, and record the strategy name and version number of the delivery strategy in the ad resource delivery list.

[0251] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0252] The steps of constructing a time-segmented user quality and consumption relationship advertising plan performance data model based on the historical user exposure data, historical advertising resource time-segmented consumption report data, and historical user quality score data include:

[0253] A data model of advertising campaign performance based on the relationship between user quality and consumption in different time periods is constructed using the Q-Learning algorithm, and the model is trained until convergence.

[0254] Obtain the advertising delivery plan configuration data from the standardized transmission unit message, and use the historical user exposure data, historical advertising resource time-sharing consumption report data, and historical user quality score data as performance data. Encode the advertising delivery plan configuration data and the performance data into a numerical vector.

[0255] In the time-segmented user quality and consumption relationship advertising plan performance data model, actions to adjust the delivery strategy are defined. These actions include changing the delivery time, increasing bids, decreasing bids, and changing the target audience attributes and geographic targeting data.

[0256] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0257] The steps for training the time-segmented user quality and consumption relationship advertising campaign performance data model until convergence include:

[0258] The data model for the relationship between user quality and spending across different time periods in the advertising campaign performance is set up to update the Q-value using the Bellman equation: Where Q(s,a) represents the expected cumulative reward that may be obtained after taking action a in state s, α is the learning rate, r is the immediate reward, γ is the discount factor, s is the current state, a is the current action, s′ is the next state, and a′ is the next action. It is to choose the action that maximizes the Q value in the next state s′;

[0259] When training the data model of advertising campaign performance based on the relationship between user quality and consumption in different time periods, the Q value Q(s,a) is initialized to zero. The current state s is observed, and an action a is selected according to the current delivery strategy. The action a is executed, and the immediate reward r and the next state s′ are observed. The Q value is updated using the Bellman equation, and the state is transferred to s′. The above steps are repeated until the Q value converges. The selection of an action a according to the current delivery strategy includes: setting the current delivery strategy to an ∈-greedy strategy, using the ∈-greedy strategy to select an action, that is, randomly selecting an action with a probability of ∈, and selecting the current optimal action with a probability of 1-∈.

[0260] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0261] The step of obtaining the corresponding advertising resource delivery strategy based on the advertising delivery plan configuration data in the standardized transmission unit message using the time-segmented user quality and consumption relationship advertising plan performance data model includes:

[0262] The advertising campaign performance data model based on the time-segmented user quality and consumption relationship is used to adjust the bid of the advertising resources in real time according to the delivery strategy.

[0263] Obtain real-time user exposure data and real-time time-based consumption reports of advertising resources;

[0264] The advertising plan performance data model is adjusted in real time based on the real-time user exposure data and the time-sharing consumption report data of the real-time advertising resources to reflect the relationship between user quality and consumption in different time periods.

[0265] The revised data model of advertising campaign performance based on the relationship between user quality and consumption in different time periods is used to re-form the corresponding advertising resource delivery strategy.

[0266] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0267] The step of real-time correction of the advertising plan performance data model based on the real-time user exposure data and the time-sharing consumption report data of the real-time advertising resources includes:

[0268] Obtain the hyperparameters of the advertising plan performance data model that shows the relationship between user quality and consumption across different time periods. The hyperparameters include the learning rate, discount factor, and network structure.

[0269] The performance of the time-segmented user quality and consumption relationship advertising campaign performance data model is evaluated using a test set or online A / B testing. The model is then optimized by adjusting the hyperparameters.

[0270] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0271] The steps for optimizing the delivery strategy based on the comparison results include:

[0272] Analyze the optimal click-through rate, conversion rate, cost per conversion, and return on investment among the comparison results. If the value of the second performance indicator is greater than the value of the second historical performance indicator of the historical target advertising resources executed according to their corresponding delivery strategies, it is determined to be positive feedback; otherwise, it is determined to be negative feedback.

[0273] When the probability of positive feedback is greater than a preset probability threshold, the system is set to not provide feedback and to receive confirmation information by suggesting correction data. The system automatically corrects the advertising time period, bid, target audience attributes, and geographic targeting data of the target advertising resource to form a corrected advertising strategy, and then executes the target advertising resource according to the corrected advertising strategy.

[0274] For specific limitations on the steps a processor takes when executing a computer program, please refer to the limitations on the methods for placing advertising resources mentioned above, which will not be repeated here.

[0275] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0276] Receive the advertising resources to be delivered and the delivery strategy selected for the corresponding advertising resources, add the advertising resources to the advertising resource delivery list in sequence, and record the delivery strategy corresponding to each advertising resource in the advertising resource delivery list;

[0277] According to the advertising resource placement list, execute the corresponding placement strategy for each advertising resource in sequence, obtain the execution result of each advertising resource, and record the execution result in the advertising resource placement list;

[0278] The execution results include statistics on failure data of the target advertising resources in executing the target delivery strategy, analysis of the difference data of the failure of the target advertising resources in executing the target delivery strategy, acquisition of suggested correction data for correcting the difference data, and feedback.

[0279] Upon receiving confirmation information, determine whether to agree to modify the difference data of the target advertising resource to the suggested correction data;

[0280] In response to agreeing to modify the difference data of the target advertising resource to the suggested correction data, the corrected advertising resource is obtained, the corrected advertising resource is executed according to the target delivery strategy and the first execution performance index value is obtained, the first execution performance index value is compared with the first historical execution performance index value of the historical advertising resources executed according to the target delivery strategy, and the advertising resource modification method is optimized based on the comparison result.

[0281] In response to disagreement with modifying the difference data of the target advertising resource to the suggested correction data, the target delivery strategy is modified according to the target advertising resource to form a modified delivery strategy. The target advertising resource is executed according to the modified delivery strategy and a second performance indicator value is obtained. The second performance indicator value is compared with the second historical performance indicator value of the target advertising resource executed according to its corresponding delivery strategy in the past. The delivery strategy modification method is optimized according to the comparison result.

[0282] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0283] The steps of sequentially executing the corresponding delivery strategy for each advertising resource according to the advertising resource delivery list, obtaining the execution result for each advertising resource, and recording the execution result in the advertising resource delivery list include:

[0284] According to the advertising resource placement list, obtain the data of each advertising resource and its corresponding placement strategy, and determine whether the data of the advertising resource and / or the placement strategy has changed;

[0285] In response to changes in the data of the advertising resource and / or the delivery strategy, the advertising resource executes the delivery strategy, and the execution result is recorded in the advertising resource delivery list;

[0286] If the data of the advertising resource and the delivery strategy have not changed, it is determined whether the advertising resource has result data after executing the delivery strategy. If the result data exists, the advertising resource does not execute the delivery strategy. If it does not exist, the advertising resource executes the delivery strategy, and the execution result is recorded in the advertising resource delivery list.

[0287] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0288] The steps of receiving the advertising resources to be delivered and the delivery strategy selected for the corresponding advertising resources, adding the advertising resources to the advertising resource delivery list in sequence, and recording the delivery strategy corresponding to each advertising resource in the advertising resource delivery list include:

[0289] Receive advertising resources to be delivered, parse the advertising resources to obtain advertising structure data, the advertising structure data including advertising content and advertising delivery plan configuration data;

[0290] The advertising structure data is converted into data transmission unit messages, and the data transmission unit messages are standardized to form standardized transmission unit messages.

[0291] Add the primary key ID of the object table in the standardized transmission unit message to the advertising resource delivery list in the order of receipt;

[0292] The advertising placement strategy corresponding to the advertising resource is obtained based on the advertising placement plan configuration data in the standardized transmission unit message. The advertising placement strategy corresponding to the advertising resource is recorded in the advertising resource placement list. The placement strategy includes advertising placement time period, bid, target audience attributes and geographic targeting data.

[0293] After the corresponding delivery strategy is executed in response to the advertising resource, the number of executions and the execution result are recorded in the advertising resource delivery list.

[0294] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0295] The step of obtaining the delivery strategy corresponding to the advertising resource based on the advertising delivery plan configuration data in the standardized transmission unit message, and recording the delivery strategy corresponding to the advertising resource in the advertising resource delivery list includes:

[0296] Obtain historical user exposure data, historical ad resource time-based consumption report data, and historical user quality score data;

[0297] Based on the historical user exposure data, historical advertising resource time-sharing consumption report data, and historical user quality score data, construct a data model of advertising plan performance based on the relationship between time-sharing user quality and consumption.

[0298] Using the time-segmented user quality and consumption relationship advertising plan performance data model, the corresponding advertising resource delivery strategy is obtained based on the advertising delivery plan configuration data in the standardized transmission unit message;

[0299] Set a strategy name and version number for the delivery strategy, and record the strategy name and version number of the delivery strategy in the ad resource delivery list.

[0300] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0301] The steps of constructing a time-segmented user quality and consumption relationship advertising plan performance data model based on the historical user exposure data, historical advertising resource time-segmented consumption report data, and historical user quality score data include:

[0302] A data model of advertising campaign performance based on the relationship between user quality and consumption in different time periods is constructed using the Q-Learning algorithm, and the model is trained until convergence.

[0303] Obtain the advertising delivery plan configuration data from the standardized transmission unit message, and use the historical user exposure data, historical advertising resource time-sharing consumption report data, and historical user quality score data as performance data. Encode the advertising delivery plan configuration data and the performance data into a numerical vector.

[0304] In the time-segmented user quality and consumption relationship advertising plan performance data model, actions to adjust the delivery strategy are defined. These actions include changing the delivery time, increasing bids, decreasing bids, and changing the target audience attributes and geographic targeting data.

[0305] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0306] The steps for training the time-segmented user quality and consumption relationship advertising campaign performance data model until convergence include:

[0307] The data model for the relationship between user quality and spending across different time periods in the advertising campaign performance is set up to update the Q-value using the Bellman equation: Where Q(s,a) represents the expected cumulative reward that may be obtained after taking action a in state s, α is the learning rate, r is the immediate reward, γ is the discount factor, s is the current state, a is the current action, s′ is the next state, and a′ is the next action. It is to choose the action that maximizes the Q value in the next state s′;

[0308] When training the data model of advertising campaign performance based on the relationship between user quality and consumption in different time periods, the Q value Q(s,a) is initialized to zero. The current state s is observed, and an action a is selected according to the current delivery strategy. The action a is executed, and the immediate reward r and the next state s′ are observed. The Q value is updated using the Bellman equation, and the state is transferred to s′. The above steps are repeated until the Q value converges. The selection of an action a according to the current delivery strategy includes: setting the current delivery strategy to an ∈-greedy strategy, using the ∈-greedy strategy to select an action, that is, randomly selecting an action with a probability of ∈, and selecting the current optimal action with a probability of 1-∈.

[0309] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0310] The step of obtaining the corresponding advertising resource delivery strategy based on the advertising delivery plan configuration data in the standardized transmission unit message using the time-segmented user quality and consumption relationship advertising plan performance data model includes:

[0311] The advertising campaign performance data model based on the time-segmented user quality and consumption relationship is used to adjust the bid of the advertising resources in real time according to the delivery strategy.

[0312] Obtain real-time user exposure data and real-time time-based consumption reports of advertising resources;

[0313] The advertising plan performance data model is adjusted in real time based on the real-time user exposure data and the time-sharing consumption report data of the real-time advertising resources to reflect the relationship between user quality and consumption in different time periods.

[0314] The revised data model of advertising campaign performance based on the relationship between user quality and consumption in different time periods is used to re-form the corresponding advertising resource delivery strategy.

[0315] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0316] The step of real-time correction of the advertising plan performance data model based on the real-time user exposure data and the time-sharing consumption report data of the real-time advertising resources includes:

[0317] Obtain the hyperparameters of the advertising plan performance data model that shows the relationship between user quality and consumption across different time periods. The hyperparameters include the learning rate, discount factor, and network structure.

[0318] The performance of the time-segmented user quality and consumption relationship advertising campaign performance data model is evaluated using a test set or online A / B testing. The model is then optimized by adjusting the hyperparameters.

[0319] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0320] The steps for optimizing the delivery strategy based on the comparison results include:

[0321] Analyze the optimal click-through rate, conversion rate, cost per conversion, and return on investment among the comparison results. If the value of the second performance indicator is greater than the value of the second historical performance indicator of the historical target advertising resources executed according to their corresponding delivery strategies, it is determined to be positive feedback; otherwise, it is determined to be negative feedback.

[0322] When the probability of positive feedback is greater than a preset probability threshold, the system is set to not provide feedback and to receive confirmation information by suggesting correction data. The system automatically corrects the advertising time period, bid, target audience attributes, and geographic targeting data of the target advertising resource to form a corrected advertising strategy, and then executes the target advertising resource according to the corrected advertising strategy.

[0323] For specific limitations on the steps implemented when a computer program is executed by a processor, please refer to the limitations on the methods of advertising resource placement mentioned above, which will not be repeated here.

[0324] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0325] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0326] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for placing advertising resources, characterized in that, include: Receive the advertising resources to be delivered and the delivery strategy selected for the corresponding advertising resources, add the advertising resources to the advertising resource delivery list in sequence, and record the delivery strategy corresponding to each advertising resource in the advertising resource delivery list; According to the advertising resource placement list, execute the corresponding placement strategy for each advertising resource in sequence, obtain the execution result of each advertising resource, and record the execution result in the advertising resource placement list; The execution results include statistics on failure data of the target advertising resources in executing the target delivery strategy, analysis of the difference data of the failure of the target advertising resources in executing the target delivery strategy, acquisition of suggested correction data for correcting the difference data, and feedback. Upon receiving confirmation information, determine whether to agree to modify the difference data of the target advertising resource to the suggested correction data; In response to agreeing to modify the difference data of the target advertising resource to the suggested correction data, the corrected advertising resource is obtained, the corrected advertising resource is executed according to the target delivery strategy and the first execution performance index value is obtained, the first execution performance index value is compared with the first historical execution performance index value of the historical advertising resources executed according to the target delivery strategy, and the advertising resource modification method is optimized based on the comparison result. In response to disagreement with modifying the difference data of the target advertising resource to the suggested correction data, the target delivery strategy is modified according to the target advertising resource to form a modified delivery strategy. The target advertising resource is executed according to the modified delivery strategy and a second performance indicator value is obtained. The second performance indicator value is compared with the second historical performance indicator value of the target advertising resource executed according to its corresponding delivery strategy in the past. The delivery strategy modification method is optimized according to the comparison result.

2. The advertising resource placement method according to claim 1, characterized in that, The steps of sequentially executing the corresponding delivery strategy for each advertising resource according to the advertising resource delivery list, obtaining the execution result for each advertising resource, and recording the execution result in the advertising resource delivery list include: According to the advertising resource placement list, obtain the data of each advertising resource and its corresponding placement strategy, and determine whether the data of the advertising resource and / or the placement strategy has changed; In response to changes in the data of the advertising resource and / or the delivery strategy, the advertising resource executes the delivery strategy, and the execution result is recorded in the advertising resource delivery list; If the data of the advertising resource and the delivery strategy have not changed, it is determined whether the advertising resource has result data after executing the delivery strategy. If it does, the advertising resource does not execute the delivery strategy; if it does not, the advertising resource executes the delivery strategy, and the execution result is recorded in the advertising resource delivery list.

3. The advertising resource placement method according to claim 1, characterized in that, The steps of receiving the advertising resources to be delivered and the delivery strategy selected for the corresponding advertising resources, adding the advertising resources to the advertising resource delivery list in sequence, and recording the delivery strategy corresponding to each advertising resource in the advertising resource delivery list include: Receive advertising resources to be delivered, parse the advertising resources to obtain advertising structure data, the advertising structure data including advertising content and advertising delivery plan configuration data; The advertising structure data is converted into data transmission unit messages, and the data transmission unit messages are standardized to form standardized transmission unit messages. Add the primary key ID of the object table in the standardized transmission unit message to the advertising resource delivery list in the order of receipt; The advertising placement strategy corresponding to the advertising resource is obtained based on the advertising placement plan configuration data in the standardized transmission unit message. The advertising placement strategy corresponding to the advertising resource is recorded in the advertising resource placement list. The placement strategy includes advertising placement time period, bid, target audience attributes and geographic targeting data. After the corresponding delivery strategy is executed in response to the advertising resource, the number of executions and the execution result are recorded in the advertising resource delivery list.

4. The advertising resource placement method according to claim 3, characterized in that, The step of obtaining the delivery strategy corresponding to the advertising resource based on the advertising delivery plan configuration data in the standardized transmission unit message, and recording the delivery strategy corresponding to the advertising resource in the advertising resource delivery list includes: Obtain historical user exposure data, historical ad resource time-based consumption report data, and historical user quality score data; Based on the historical user exposure data, historical advertising resource time-sharing consumption report data, and historical user quality score data, construct a data model of advertising plan effectiveness based on the relationship between time-sharing user quality and consumption; Using the time-segmented user quality and consumption relationship advertising plan performance data model, the corresponding advertising resource delivery strategy is obtained based on the advertising delivery plan configuration data in the standardized transmission unit message; Set a strategy name and version number for the delivery strategy, and record the strategy name and version number of the delivery strategy in the ad resource delivery list.

5. The advertising resource placement method according to claim 4, characterized in that, The steps of constructing a time-segmented user quality and consumption relationship advertising plan performance data model based on the historical user exposure data, historical advertising resource time-segmented consumption report data, and historical user quality score data include: A data model of advertising campaign performance based on the relationship between user quality and consumption in different time periods is constructed using the Q-learning algorithm, and the model is trained until it converges. Obtain the advertising delivery plan configuration data from the standardized transmission unit message, and use the historical user exposure data, historical advertising resource time-sharing consumption report data, and historical user quality score data as performance data. Encode the advertising delivery plan configuration data and the performance data into a numerical vector. In the time-segmented user quality and consumption relationship advertising plan performance data model, actions to adjust the delivery strategy are defined. These actions include changing the delivery time, increasing bids, decreasing bids, and changing the target audience attributes and geographic targeting data.

6. The advertising resource placement method according to claim 5, characterized in that, The steps for training the time-segmented user quality and consumption relationship advertising campaign performance data model until convergence include: The data model for the relationship between user quality and spending across different time periods in the advertising campaign performance is set up to update the Q-value using the Bellman equation: The Q value Q ( s , a ) indicates the state s Take action below a Then, the expected value of the cumulative rewards that may be obtained in the future. α It's the learning rate. r It's an instant reward. γ It is a discount factor. s This is the current state. a s is the current action, and s′ is the next state. a ′ is the next action. It is to choose the action that maximizes the Q value in the next state s′; When training the data model of the relationship between user quality and consumption in the time-segmented advertising campaign performance, the Q-value is initialized. Q ( s , a If the value is zero, observe the current state. s Select an action based on the current delivery strategy. a Execute actions a Observe the instant rewards r Given the next state s′, update the Q value using the Bellman equation, transition the state to s′, and repeat the above steps until the Q value converges.

7. The advertising resource placement method according to claim 4, characterized in that, The step of obtaining the corresponding advertising resource delivery strategy based on the advertising delivery plan configuration data in the standardized transmission unit message using the time-segmented user quality and consumption relationship advertising plan performance data model includes: The advertising campaign performance data model based on the time-segmented user quality and consumption relationship is used to adjust the bid of the advertising resources in real time according to the delivery strategy. Obtain real-time user exposure data and real-time time-based consumption reports of advertising resources; The advertising plan performance data model is adjusted in real time based on the real-time user exposure data and the time-sharing consumption report data of the real-time advertising resources to reflect the relationship between user quality and consumption in different time periods. The revised data model of advertising campaign performance based on the relationship between user quality and consumption in different time periods is used to re-form the corresponding advertising resource delivery strategy.

8. The advertising resource placement method according to claim 7, characterized in that, The step of real-time correction of the advertising plan performance data model based on the real-time user exposure data and the time-sharing consumption report data of the real-time advertising resources includes: Obtain the hyperparameters of the advertising plan performance data model that shows the relationship between user quality and consumption across different time periods. The hyperparameters include the learning rate, discount factor, and network structure. The performance of the time-segmented user quality and consumption relationship advertising campaign performance data model is evaluated using a test set or online A / B testing. The model is then optimized by adjusting the hyperparameters.

9. The advertising resource placement method according to claim 1, characterized in that, The steps for optimizing the delivery strategy based on the comparison results include: Analyze the optimal click-through rate, conversion rate, cost per conversion, and return on investment among the comparison results. If the value of the second performance indicator is greater than the value of the second historical performance indicator of the historical target advertising resources executed according to their corresponding delivery strategies, it is determined to be positive feedback; otherwise, it is determined to be negative feedback. When the probability of positive feedback is greater than a preset probability threshold, the system is set to not provide feedback and to receive confirmation information by suggesting correction data. The system automatically corrects the advertising time period, bid, target audience attributes, and geographic targeting data of the target advertising resource to form a corrected advertising strategy, and then executes the target advertising resource according to the corrected advertising strategy.

10. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 9.

Images