Model training and resource delivery configuration method and device for resource delivery configuration

Abstract

The embodiments of the present invention provide a model training and resource delivery configuration method and device for resource delivery configuration, which obtains material data, resource location data, user data, and policy data. S1: Based on the material data, resource location data, and user data, multiple prediction configuration strategies are obtained through the model to be trained. S2: The prediction configuration strategy is selected, and the target configuration strategy corresponding to the target resource location and target user in the selected prediction configuration strategy is searched from the policy data. S3: The selected prediction configuration strategy is compared with the target configuration strategy. S4: Based on the comparison result of the selected prediction configuration strategy and the target configuration strategy, the model parameters of the model to be trained are adjusted. S1 to S4 are repeated until a preset iteration end condition is met, and the model parameters that meet the preset iteration end condition are used as the model parameters of the model to be trained, thereby obtaining a trained model. This achieves more refined resource delivery configuration.

Description

Technical Field

[0001] The present invention relates to the field of Internet application technology, and in particular to a model training and resource delivery configuration method and device for resource delivery configuration. Background Art

[0002] With the growing number of Internet user groups, refined operations for different user groups have become an important development direction of Internet operations, and resource allocation is a key link in refined operations.

[0003] Resource delivery can be understood as: displaying promotional information as resource content on resource positions for a set user group during a set delivery time period. For example, promotional information can be related to Internet products such as games, websites, and platforms. These promotional information to be delivered can also be called materials.

[0004] The configuration of resource allocation is an important process in the resource allocation process, and achieving refined resource allocation has always been a difficult problem in this process. Summary of the Invention

[0005] The purpose of the embodiments of the present invention is to provide a model training and resource allocation method and device for resource allocation, so as to achieve more refined resource allocation. The specific technical solution is as follows:

[0006] In a first aspect of the present invention, a model training method for resource deployment configuration is provided, comprising:

[0007] Acquire material data, resource location data, user data, and policy data, wherein the policy data stores a correspondence between multiple resource locations, multiple users, and multiple target historical configuration policies;

[0008] S1, based on the material data, the resource location data, and the user data, a plurality of prediction configuration strategies are obtained through a to-be-trained model, each prediction configuration strategy being used to represent a strategy for displaying a target material to a target user at a target resource location;

[0009] S2, selecting a predicted configuration strategy, and searching the strategy data for a target configuration strategy corresponding to the target resource location and target user in the selected predicted configuration strategy, wherein the target configuration strategy is a configuration strategy whose benefits meet a preset benefit condition among the historical configuration strategies;

[0010] S3, comparing the selected prediction configuration strategy with the target configuration strategy;

[0011] S4, adjusting the model parameters of the to-be-trained model based on a comparison result between the selected prediction configuration strategy and the target configuration strategy;

[0012] Repeat S1 to S4 until the preset iteration end condition is met, and use the model parameters that meet the preset iteration end condition as the model parameters of the model to be trained to obtain a trained model.

[0013] Optionally, obtaining the policy data includes:

[0014] Obtain pre-built policy data; the policy data is constructed in the following manner:

[0015] Obtain historical configuration strategies for displaying materials to multiple users at multiple resource locations over a historical period, as well as the corresponding revenue for each historical configuration strategy.

[0016] Find historical configuration policies for the same target resource location and the same target user;

[0017] A configuration strategy whose benefit satisfies a preset benefit condition among historical configuration strategies for the same target resource location and the same target user is selected as the target configuration strategy corresponding to the target resource location and the target user.

[0018] Optionally, selecting a configuration strategy whose benefit satisfies a preset benefit condition from historical configuration strategies for the same target resource location and the same target user as the target configuration strategy corresponding to the target resource location and the target user includes:

[0019] A historical configuration strategy with the highest benefit among historical configuration strategies for the same target resource location and the same target user is selected as the target configuration strategy corresponding to the target resource location and the target user.

[0020] Optionally, selecting a configuration strategy whose benefit satisfies a preset benefit condition from historical configuration strategies for the same target resource location and the same target user as the target configuration strategy corresponding to the target resource location and the target user includes:

[0021] Compare the benefits corresponding to each historical configuration strategy found for the same target resource location and the same target user with the preset benefits;

[0022] If the benefit corresponding to a historical configuration strategy exceeds the preset benefit, the historical configuration strategy is used as the target configuration strategy corresponding to the target resource position and the target user; or, if the benefit corresponding to a historical configuration strategy does not exceed the preset benefit, the historical configuration strategy is used as the target configuration strategy corresponding to the target resource position and the target user.

[0023] Optionally, obtaining the benefits corresponding to each historical configuration strategy includes:

[0024] Assign preset parameters to the historical configuration strategy based on the revenue type; and calculate the revenue of displaying materials to users at the resource location based on the preset parameters.

[0025] Optionally, adjusting the model parameters of the to-be-trained model based on the comparison result between the selected prediction configuration strategy and the target configuration strategy includes:

[0026] Based on the difference between the selected prediction configuration strategy and the target configuration strategy, the model parameters of the to-be-trained model are adjusted.

[0027] In a second aspect of the present invention, a resource allocation method is provided, comprising:

[0028] Obtain the materials, resource locations, and users to be delivered;

[0029] The material to be delivered, the resource position and the user are input into a pre-trained model for resource delivery configuration, and a configuration strategy for displaying the material to the user at the resource position is obtained, so that resource delivery is performed based on the configuration strategy, wherein the model for resource delivery configuration is trained based on any of the model training methods for resource delivery configuration described in the first aspect above.

[0030] In a third aspect of the present invention, a model training device for resource allocation is provided, comprising:

[0031] A first acquisition module is used to acquire material data, resource location data, user data and policy data, wherein the policy data stores a correspondence between multiple resource locations, multiple users and multiple target historical configuration policies;

[0032] The training module is used to perform the following steps: S1, based on the material data, the resource position data and the user data, a plurality of prediction configuration strategies are obtained through the model to be trained, each prediction configuration strategy is used to represent a strategy for displaying the target material to the target user at the target resource position; S2, selecting a prediction configuration strategy, and searching the strategy data for a target configuration strategy corresponding to the target resource position and the target user in the selected prediction configuration strategy, the target configuration strategy being a configuration strategy in the historical configuration strategy whose benefits meet the preset benefit conditions; S3, comparing the selected prediction configuration strategy with the target configuration strategy; S4, adjusting the model parameters of the model to be trained based on the comparison result between the selected prediction configuration strategy and the target configuration strategy; repeating S1 to S4 until the preset iteration end condition is met, and using the model parameters that meet the preset iteration end condition as the model parameters of the model to be trained to obtain a trained model.

[0033] In a fourth aspect of the present invention, a resource allocation device is provided, comprising:

[0034] The second acquisition module is used to obtain the materials, resource locations and users to be delivered;

[0035] A determination module is used to input the material to be delivered, the resource position and the user into a pre-trained model for resource delivery configuration, and obtain a configuration strategy for displaying the material to the user at the resource position, so that resource delivery is performed based on the configuration strategy, wherein the model for resource delivery configuration is trained based on any of the model training methods for resource delivery configuration described in the first aspect above.

[0036] In a fifth aspect of the present invention, an electronic device is provided, comprising a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0037] Memory for storing computer programs;

[0038] The processor is configured to implement the method steps described in any one of the first aspect or the second aspect when executing the program stored in the memory.

[0039] In another aspect of the implementation of the present invention, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, it implements any of the above-mentioned model training methods or resource delivery configuration methods for resource delivery configuration.

[0040] In another aspect of the implementation of the present invention, a computer program product containing instructions is also provided, which, when run on a computer, enables the computer to execute any of the above-mentioned model training methods or resource delivery configuration methods for resource delivery configuration.

[0041] In an embodiment of the present invention, by acquiring material data, resource location data, user data, and policy data, the policy data stores the correspondence between multiple resource locations, multiple users, and multiple target historical configuration strategies; and repeatedly performing the following steps S1 to S4: S1, based on the material data, resource location data, and user data, a plurality of prediction configuration strategies are obtained through the model to be trained, each prediction configuration strategy being used to represent a strategy for displaying target material to a target user at a target resource location; S2, selecting a prediction configuration strategy, and searching the policy data for a target configuration strategy corresponding to the target resource location and target user in the selected prediction configuration strategy, the target configuration strategy being a configuration strategy in the historical configuration strategy whose benefits meet a preset benefit condition; S3, comparing the selected prediction configuration strategy with the target configuration strategy; S4, adjusting the model parameters of the model to be trained based on the comparison result between the selected prediction configuration strategy and the target configuration strategy; when a preset iteration end condition is met, the model parameters that meet the preset iteration end condition are used as the model parameters of the model to be trained, thereby obtaining a trained model. In this way, during the resource delivery process, resource delivery can be configured using the trained model for resource delivery configuration.

[0042] The predicted configuration strategy output by the model to be trained is obtained based on the material data, resource location data, and user data, and the target configuration strategy that meets the preset benefit conditions can be understood as the true value. In the process of training the model for resource delivery configuration, the model parameters of the model to be trained are adjusted based on the comparison results of the predicted configuration strategy output by the model to be trained and the target configuration strategy that meets the preset benefit conditions. This allows the trained model to obtain a configuration strategy based on the material data, resource location data, and user data, and the target configuration strategy as the true value can guide the configuration strategy output by the model to meet the benefit conditions. In this way, in the resource delivery process, using the trained model for resource delivery configuration to configure resource delivery can achieve more refined resource delivery configuration. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for describing the embodiments or the prior art.

[0044] Figure 1 Flowchart of a model training method for resource placement configuration in an embodiment of the present invention;

[0045] Figure 2 A flowchart of pre-building policy data in an embodiment of the present invention;

[0046] Figure 3 Schematic diagram of the application of the model training method for resource deployment configuration in an embodiment of the present invention;

[0047] Figure 4 This is a flow chart of a resource placement configuration method according to an embodiment of the present invention;

[0048] Figure 5 A flowchart of optimizing a model for resource placement configuration in an embodiment of the present invention;

[0049] Figure 6 Schematic diagram of the structure of a model training device for resource deployment configuration in an embodiment of the present invention;

[0050] Figure 7 This is a schematic diagram of the structure of a resource placement configuration device according to an embodiment of the present invention;

[0051] Figure 8 Schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The technical solutions in the embodiments of the present invention will be described below with reference to the accompanying drawings in the embodiments of the present invention.

[0053] Simply put, the configuration of resource delivery is to determine how to deliver resources. It can also be understood as establishing the relationship between resource locations, users, and materials.

[0054] In the embodiment of the present invention, by learning the configuration strategies in the historical delivery process, the model learns the resources and users to determine the materials to be delivered to them. In this way, the model can be used to configure the resource delivery in the future.

[0055] The following describes in detail the model training process, which involves learning the configuration strategies during historical delivery processes so that the model can determine the materials to be delivered to resource locations and users.

[0056] Figure 1 Flowchart of the model training method for resource placement configuration provided by the embodiment of the present invention, refer to Figure 1 The model training method for resource placement configuration provided by an embodiment of the present invention includes:

[0057] S101, acquiring material data, resource location data, user data, and policy data, wherein the policy data stores correspondences between multiple resource locations, multiple users, and multiple target historical configuration policies;

[0058] S1, based on the material data, resource location data and user data, a plurality of prediction configuration strategies are obtained through the to-be-trained model, each prediction configuration strategy being used to represent a strategy for displaying a target material to a target user at a target resource location;

[0059] S2, selecting a predicted configuration strategy, and searching the strategy data for a target configuration strategy corresponding to the target resource location and target user in the selected predicted configuration strategy, wherein the target configuration strategy is a configuration strategy whose benefits meet a preset benefit condition among the historical configuration strategies;

[0060] S3, compare the selected predicted configuration strategy and the target configuration strategy;

[0061] S4, adjusting the model parameters of the to-be-trained model based on the comparison result between the selected prediction configuration strategy and the target configuration strategy;

[0062] Repeat S1 to S4 until a preset iteration end condition is met, and then perform S102: use the model parameters that meet the preset iteration end condition as the model parameters of the model to be trained to obtain a trained model.

[0063] In an embodiment of the present invention, the prediction configuration strategy output by the model to be trained is obtained based on the material data, resource location data, and user data, and the target configuration strategy that meets the preset profit conditions can be understood as a true value. In the process of training the model for resource delivery configuration, the model parameters of the model to be trained are adjusted based on the comparison results of the prediction configuration strategy output by the model to be trained and the target configuration strategy that meets the preset profit conditions. This allows the trained model to obtain a configuration strategy based on the material data, resource location data, and user data, and the target configuration strategy as a true value can guide the configuration strategy output by the model to meet the profit conditions. In this way, in the resource delivery process, a more refined resource delivery configuration can be achieved by using the trained model for resource delivery configuration to configure resource delivery.

[0064] Moreover, compared with manual operations, using a trained model for resource allocation to configure resource allocation can also lower the configuration threshold and simplify the resource allocation configuration process.

[0065] The preset iteration end conditions may include the number of iterations reaching a preset number, the model accuracy reaching a preset accuracy, etc., wherein the preset number and preset accuracy can be determined based on actual needs or experience, such as 1000, 2000, 3000 times, etc., and the preset accuracy can be 0.1, 0.01, 0.001, etc.

[0066] Executing S1 to S4 once can be considered an iteration, or comparing the predicted configuration strategy output by the model with the target configuration strategy once can be considered an iteration. Model accuracy can be represented by the difference between the predicted configuration strategy output by the model and the target configuration strategy corresponding to the predicted configuration strategy.

[0067] For the multiple prediction configuration strategies obtained in S1, S2 can select each prediction configuration strategy in turn and execute S3 and S4 respectively. Alternatively, multiple prediction configuration strategies can be randomly selected and S3 and S4 can be executed for each selected prediction configuration strategy. Alternatively, one prediction configuration strategy can be randomly selected and S3 and S4 can be executed for the selected prediction configuration strategy.

[0068] In S4, the model parameters of the to-be-trained model may be adjusted based on the difference between the selected prediction configuration strategy and the target configuration strategy.

[0069] The specific process of adjusting model parameters can refer to the model parameter adjustment methods in related technologies. Specifically, the selected prediction configuration strategy and target configuration strategy can be vectorized, and a loss function for the vectorized prediction configuration strategy and target configuration strategy can be calculated. The difference between the prediction configuration strategy and the target configuration strategy can be expressed based on the loss function.

[0070] In addition to the configuration process load, the configuration of resource delivery through manual operations often relies on the knowledge and experience of the operators, which has a high threshold. If the operators do not have a high level of knowledge and experience, the configured resource delivery strategy may not attract users well, which will result in a low conversion rate of the delivered resources and lower overall returns.

[0071] In an embodiment of the present invention, the configuration of resource delivery through the trained model for resource delivery configuration does not need to rely on the knowledge reserves and experience of the operator, and the configuration threshold is low. The trained model obtains the configuration strategy based on the material data, resource position data and user data, and takes into account the relationship between the material, resource position and user. The configuration strategy obtained by using the above-mentioned trained model for resource delivery configuration can also be more attractive to users, improve the conversion rate of delivered resources, and enhance the overall benefits of resource delivery.

[0072] In S101 , the material data includes a plurality of materials, and the materials can also be understood as resources to be released. For example, the materials can specifically be promotional information to be released, such as information related to Internet products such as games, websites, and platforms.

[0073] The resource bit data may include a plurality of resource bits and information of the plurality of resource bits.

[0074] Resource locations, such as the startup page or splash screen of an application (Application, App), banner ad space or interstitial ad space on a web page, marketing space, cash register, etc.

[0075] Resource location information can be understood as all information related to the resource location, such as the resource location name, size, platform, and other information.

[0076] User data may include user profiles of multiple users, wherein the user profiles include information of at least one dimension, and the at least one dimension includes at least one of the following dimensions: user attributes and user behavior.

[0077] User attributes may include the time when the user joined the membership, and user behavior may include user preferences, such as whether the user likes comedy movies, etc.

[0078] The dimensions of user portraits can be divided from different focus points, and different focus points can be set according to different levels to make more detailed portrait descriptions of the population and conduct more comprehensive analysis and classification.

[0079] The policy data stores the correspondence between multiple resource locations, multiple users, and multiple target historical configuration policies.

[0080] Wherein, obtaining the policy data can be achieved by obtaining the pre-built policy data. Figure 2 , the policy data can be constructed as follows:

[0081] S201 , obtaining historical configuration strategies for displaying materials to multiple users at multiple resource locations within a historical period, and obtaining revenue corresponding to each historical configuration strategy.

[0082] Profit can be determined through a variety of evaluation indicators, such as click-through rate, checkout counter entry rate, order conversion rate, etc.

[0083] It can be understood that revenue includes one or more of the following revenue types: click-through rate, checkout counter entry rate, and order conversion rate.

[0084] When multiple types of returns are included, to facilitate comparison between different types of returns, one possible implementation method for obtaining the returns corresponding to each historical configuration strategy may include:

[0085] Assign preset parameters to the historical configuration strategy based on the revenue type; and calculate the revenue of displaying materials to users at the resource location based on the preset parameters.

[0086] You can preset parameters for different income types. After obtaining the income type corresponding to the historical configuration strategy, you can assign preset parameters to the historical configuration strategy based on the income type. The preset parameters can be determined based on needs or experience.

[0087] S202, searching for historical configuration policies for the same target resource location and the same target user;

[0088] S203 : Selecting a configuration strategy whose benefit satisfies a preset benefit condition from historical configuration strategies for the same target resource location and the same target user as the target configuration strategy corresponding to the target resource location and the target user.

[0089] Figure 2 The process shown can also be understood as a process of processing multiple historical configuration strategies for recommending materials to users at resource locations within a historical period.

[0090] Target users can be selected based on user profiles in the above user data. Each user can be divided from multiple dimensions and labeled accordingly. In this way, in the process of selecting target users, selection can be made based on labels. For example, if the marketing party hopes to divide different types of users who are interested in different types of video content and recommend corresponding materials to each, then users who are interested in the same type of video content are considered to be a type of target users. Users whose user profiles indicate that they are interested in this type of video content can be selected from multiple users as target users of this type. Users of this type can be labeled with the same user ID or user label. Users labeled with the same user ID or user label are all the same target users.

[0091] In an optional embodiment, the historical configuration strategy with the highest benefit among the historical configuration strategies for the same target resource location and the same target user is selected as the target configuration strategy corresponding to the target resource location and the target user.

[0092] As shown in Table 1 below, six historical configuration policies are obtained: historical configuration policy 1, historical configuration policy 2, historical configuration policy 3, historical configuration policy 4, historical configuration policy 5, and historical configuration policy 6.

[0093] Table 1

[0094]

[0095] The number of the multiple historical configuration policies obtained may be hundreds, thousands, or tens of thousands, etc. The example here is only for the convenience of explanation.

[0096] For the historical configuration strategies for displaying materials to multiple users at multiple resource locations within the historical time period obtained in Table 1, as well as the corresponding benefits of each historical configuration strategy, we search for historical configuration strategies for the same target resource location and the same target user. The results are as follows:

[0097] For the same target resource location: location 1 and the same target user: the user with the user tag of user tag 1, the historical configuration policies include three: historical configuration policy 1, historical configuration policy 2, and historical configuration policy 3.

[0098] For the same target resource location: location 2 and the same target user: the historical configuration of the user with the user tag being user tag 2 includes 1: historical configuration policy 4.

[0099] For the same target resource location: location 3 and the same target user: the historical configuration policy for the user with the user tag of user tag 3 includes 1: historical configuration policy 5.

[0100] For the same target resource location: location 4 and the same target user: the historical configuration policy for the user with the user tag of user tag 4 includes 1: historical configuration policy 6.

[0101] For the historical configuration policies for the same target resource position: position 2 and the same target user: user tag with user tag 2, the historical configuration policies for the same target resource position: position 3 and the same target user: user tag with user tag 3, and the historical configuration policies for the same target resource position: position 4 and the same target user: user tag with user tag 4, each policy only includes one policy, and the policy with the highest benefit can only be that policy. Therefore, this policy is directly used as the target configuration policy corresponding to the target resource position and target user. That is, historical configuration policy 4 is used as the target configuration policy for the target resource position: position 2 and the target user: user tag with user tag 2; historical configuration policy 5 is used as the target configuration policy for the target resource position: position 3 and the target user: user tag with user tag 3; and historical configuration policy 6 is used as the target configuration policy for the target resource position: position 4 and the target user: user tag with user tag 4.

[0102] For the target resource position: position 1 and the target user: the user with the user tag of user tag 1, there are three historical configuration strategies: historical configuration strategy 1, historical configuration strategy 2, and historical configuration strategy 3. The benefits of these three strategies are compared, and historical configuration strategy 3 with the highest benefit is selected as the target configuration strategy corresponding to the target resource position: position 1 and the target user: the user tag of user tag 1.

[0103] In one case, the same configuration strategy may be displayed multiple times. This means that the same material is shown to the same user group in the same resource slot. This situation can be understood as the target material being recommended to the target user in the target resource slot multiple times in the past.

[0104] In this case, the historical recommendation materials obtained in multiple historical configuration strategies for the same target resource location and the same target user are also the same.

[0105] In one possible implementation, each historical configuration strategy with the same historical recommendation material for the same target resource location and the same target user can be treated as a separate historical configuration strategy and put together with other historical recommendation materials with different historical recommendation materials for the same target resource location and the same target user.

[0106] In another possible implementation, each historical configuration strategy that historically recommended the same material for the same target resource location and target user can be integrated, and the benefits of these historical configuration strategies can be integrated accordingly. Specifically, if the target material was recommended to the target user at the target resource location multiple times within a historical period, a preset ratio can be allocated to each recommendation; and based on the preset ratio allocated to each recommendation, the benefits of recommending the target material to the target user at the target resource location can be calculated as the benefits of the historical configuration strategy that includes the association between the target resource location, target user, and target material.

[0107] In an embodiment of the present invention, the historical configuration strategy with the highest profit among the historical configuration strategies for the same target resource position and the same designated user can be selected as the target historical configuration strategy corresponding to the target resource position and the target user, and based on the comparison result of the predicted configuration strategy output by the model to be trained and the target configuration strategy that meets the preset profit conditions, the model parameters of the model to be trained are adjusted so that the model learns how to obtain the target material that meets the profit conditions for the target resource position and the target user, so that the configuration strategy obtained by using the model can better attract users. Furthermore, resource allocation based on the configuration strategy obtained by using the model can improve the conversion rate of allocated resources and increase profits.

[0108] In another optional embodiment, the benefits corresponding to each historical configuration strategy found for the same target resource location and the same target user are compared with the preset benefits respectively; if the benefits corresponding to a historical configuration strategy exceed the preset benefits, the historical configuration strategy is used as the target configuration strategy corresponding to the target resource location and the target user; or, if the benefits corresponding to a historical configuration strategy do not exceed the preset benefits, the historical configuration strategy is used as the target configuration strategy corresponding to the target resource location and the target user.

[0109] Among them, the preset income can be determined based on actual needs or experience.

[0110] If the returns corresponding to a historical allocation strategy exceed the preset returns, the historical allocation strategy can also be understood as a positive target allocation strategy.

[0111] In this case, the model parameters of the model to be trained are adjusted in the expectation that the correspondence between the resource position, user, and configuration policy indicated by the predicted configuration policy is the same as the correspondence between the resource position, user, and configuration policy indicated by the target configuration policy; or, the model parameters are adjusted so that the correspondence between the resource position, user, and configuration policy indicated by the predicted configuration policy output by the model is infinitely close to the correspondence between the resource position, user, and configuration policy indicated by the target configuration policy.

[0112] If the return corresponding to a historical allocation strategy does not exceed the preset return, the historical allocation strategy can also be understood as a negative target allocation strategy.

[0113] In this case, the model parameters are adjusted so that the corresponding relationship between the resource position, user, and configuration policy indicated by the predicted configuration policy is different from the corresponding relationship between the resource position, user, and configuration policy indicated by the target configuration policy.

[0114] In embodiments of the present invention, feature extraction can be performed on the material data, resource bit data, user data, and policy data to obtain feature data corresponding to the material data, resource bit data, user data, and policy data, respectively. The feature extraction method can be selected based on actual needs, for example, one-hot encoding. In one implementation, feature extraction can specifically be performed by feature embedding.

[0115] In S1, based on the material data, resource location data, and user data, a plurality of prediction configuration strategies are obtained through the to-be-trained model. This may include: feature data corresponding to the material data, resource location data, user data, and strategy data, respectively. Specifically, the feature data corresponding to the material data, resource location data, user data, and strategy data, respectively, may be input into the to-be-trained model, and the to-be-trained model will output the plurality of prediction configuration strategies.

[0116] In one implementation, the model to be trained may include a low-order feature processing module and a high-order feature processing module.

[0117] Low-order feature processing modules can include multi-head self-attention mechanisms (Multi-head SelfAttention); high-order feature processing modules can include deep neural networks (DNN) and deep residual networks (ResNet).

[0118] In S1, the feature data corresponding to the material data, resource location data, user data and strategy data are respectively input into the model to be trained. The low-order feature processing module and the high-order feature processing module included in the model to be trained obtain low-order processing results and high-order processing results respectively; the low-order processing results and the high-order processing results are cascaded, and the prediction configuration strategy is output based on the cascaded results.

[0119] For example: based on the feature data corresponding to the material library, resource location library, and crowd template library, the low-order feature processing module and the high-order feature processing module in the model to be trained are used to obtain low-order processing results and high-order processing results respectively; the low-order processing results and the high-order processing results are cascaded, and the prediction configuration strategy is output based on the cascaded results.

[0120] Among them, the low-order feature processing module is used to process low-order features, and the high-order feature processing module is used to process high-order features. In the embodiment of the present invention, low-order features refer to features with fewer bits after feature embedding, and high-order features refer to features with more bits after feature embedding. For example, a bit threshold can be preset. If the number of bits obtained by feature embedding is less than the preset bit threshold, the feature data obtained by feature embedding is a low-order feature. If the number of bits obtained by feature embedding is not less than the preset bit threshold, the feature data obtained by feature embedding is a high-order feature.

[0121] The cascade may be a weighted sum or the like.

[0122] In an optional embodiment, material data may be maintained through a material library, resource location data may be maintained through a resource location library, user data may be maintained through a crowd template library, and policy data may be maintained through a policy library.

[0123] In the embodiment of the present invention, a material library, a resource location library, a crowd template library and a strategy library may be pre-built, and the pre-built material library, resource location library, crowd template library and strategy library may be acquired in S101.

[0124] The material library may include a bottom material library and a variable material library.

[0125] The underlying material library can be understood as the materials provided by the marketer that do not change with different users, and the variable material library can be understood as the materials that change with different users.

[0126] In one possible implementation method, the texts, pictures, links and other forms of materials in the historical material library are added as the underlying material library, and the data such as delivery with an order and red envelopes are added as the variable material library.

[0127] In the embodiment of the present invention, the materials such as pictures, links, texts, red envelopes contained in the material library can be managed to achieve full life cycle management from material production to material uploading, use and destruction.

[0128] The Crowd Template Library includes user portraits from multiple users.

[0129] Specific groups of people can be selected based on user attributes, behaviors and other tags. In the configuration background, specific groups of people can be quickly selected through the group template library. The group template library can improve operational efficiency and achieve rapid selection.

[0130] The resource library, also known as the location library or location material library, can contain information about multiple resource locations, such as the resource location name, size, platform, etc. The resource library allows front-end resource locations to be managed in the background.

[0131] Strategy library: For single or batch locations (resource positions), implement material association configuration for specified groups of people and locations.

[0132] You can crawl multiple historical configuration strategies for recommending materials to users at resource locations over a historical period of time and collect them into a strategy library.

[0133] In one possible implementation, a policy library that includes multiple historical configuration policies for recommending materials to users at resource locations within a historical period can be referred to as an initial policy library. In an embodiment of the present invention, the data in the initial policy library can be processed so that the processed data can be directly used in the model training process; or, the data in the initial policy library can be processed in the model training process, wherein the processing of the data in the initial policy library refers to the above Figure 2 The method shown.

[0134] The following combination Figure 3 , an example is given of an embodiment of the present invention, in which a configuration strategy in a historical delivery process is learned to determine the material to be delivered to a resource position and a user.

[0135] The embodiments of the present invention can be applied to marketing system scenarios, mainly including:

[0136] One-hot feature domain embedding, feature embedding, intelligent algorithm and output layer.

[0137] One-hot feature domain embedding can also be understood as data collection, including: material library, resource location library (also called location library), crowd template library and strategy library.

[0138] This process can also be called material library production and crowd portrait description.

[0139] Material library production: add texts, pictures, links and other forms of materials in the historical material library as the underlying material library, add data such as delivery with orders and red envelopes as the variable material library, and add data such as marketing positions and cash registers as the location material library.

[0140] Crowd portrait description: Make a more detailed portrait description of the crowd, set user portraits with different focuses according to different levels, and conduct more comprehensive analysis and classification.

[0141] Feature embedding, that is, encoding the collected data.

[0142] Intelligent algorithm recommendation: One-hot encodes the heterogeneous data of the material library and the crowd, converts high-order sparse features into low-order dense features to form the original data set; performs computational analysis of feature interactions to recommend more suitable materials to different groups of people.

[0143] Output layer: Based on the feature data corresponding to the material library, resource location library, and crowd template library, the low-order feature processing module and high-order feature processing module in the model to be trained are used to obtain low-order processing results and high-order processing results respectively; the low-order processing results and the high-order processing results are cascaded, and the prediction configuration strategy is output based on the cascaded results.

[0144] The algorithm continues to optimize learning based on the optimal goal. Specifically, the configuration strategy with the same historical configuration strategy for the same target resource location and the same target user, whose benefits meet the preset benefit conditions, is selected as the target configuration strategy for the target resource location and target user. This target configuration strategy can be understood as the optimal goal.

[0145] Obtain material data, resource position data, user data and policy data, obtain multiple prediction configuration strategies based on the material data, resource position data and user data through the model to be trained, select the prediction configuration strategy, and search the policy data for the target configuration strategy corresponding to the target resource position and target user in the selected prediction configuration strategy, compare the selected prediction configuration strategy with the target configuration strategy, and adjust the model parameters of the model to be trained based on the comparison result of the selected prediction configuration strategy and the target configuration strategy until the preset iteration end condition is met, and use the model parameters that meet the preset iteration end condition as the model parameters of the model to be trained to obtain a trained model.

[0146] Effect analysis: Set different indicators, including click-through rate, checkout counter entry rate, order conversion rate, etc.; set different indicators at different marketing nodes to achieve different focus recommendations and achieve more reasonable intelligent traffic delivery.

[0147] Strategies and materials are complex to configure, rely on high-threshold prior knowledge, and are difficult to close. When left to the algorithms and maximizing goals, they can intelligently generate global traffic strategies to avoid traffic loss.

[0148] Compared with the existing technology, the strategy configuration process requires manual operation, is repetitive and tedious, and has a large number of material types; it often relies on the knowledge reserve of operations and has a high threshold; once the configured strategy does not cover the global traffic, it will cause part of the data traffic to be directly lost, and the closed loop is difficult. The embodiment of the present invention proposes a traffic intelligent delivery method based on global benefits, which simplifies the configuration, lowers the threshold, breaks down information barriers, and improves the overall rate of return.

[0149] Among them, based on global benefits, it can be understood as providing a more appropriate recommendation strategy to better attract users, obtain benefits from users in a more comprehensive dimension, and improve overall benefits.

[0150] In the embodiment of the present invention, multiple materials are managed in a unified manner, and an intelligent recommendation algorithm is used to display different strategies for users with different focuses at different resource locations to avoid traffic loss.

[0151] The above embodiment illustrates how, by learning from historical deployment configuration strategies, the model can determine the material to be delivered to resource locations and users. This allows for subsequent resource delivery configuration using the model. The following describes the process of configuring resource delivery using the model in accordance with an embodiment of the present invention.

[0152] Reference Figure 4 , an embodiment of the present invention provides a resource delivery configuration method, which may include:

[0153] S401, obtaining the materials, resource locations and users to be delivered;

[0154] S402: Input the materials, resource locations and users to be delivered into a pre-trained model for resource delivery configuration to obtain a configuration strategy for displaying materials to users at the resource locations, so that resources are delivered based on the configuration strategy. The model for resource delivery configuration is trained based on the model training method for resource delivery configuration in the above-mentioned embodiment.

[0155] In one implementation, after receiving a user-triggered request, resource placement is configured to recommend the content indicated by the strategy to the user, i.e., display the content to the user in the resource slot according to the recommendation strategy. For example, a user opening the homepage of an app can be considered to have triggered a request.

[0156] Moreover, after deploying resources using the resource deployment strategy configured by the model, the deployment data such as revenue can be recovered, and the model can be further optimized based on the recovered deployment data. Figure 5 As shown, this may include:

[0157] S501, collecting delivery data, where the delivery data includes the benefits of the configuration strategy after resources are delivered based on the configuration strategy;

[0158] S502: Optimize the model for resource delivery configuration based on the delivery data.

[0159] Specifically, the material library, strategy library, crowd template library, and resource location library can be updated based on the delivery data. The specific optimization process is similar to the model training process.

[0160] In an embodiment of the present invention, after resource allocation is performed using the resource allocation strategy configured by the model, the allocation data such as revenue can be recovered, and then the model for resource allocation configuration obtained through the above training can be further optimized based on the recovered allocation data. In this way, the accuracy of the model can be further improved, making the accuracy of resource allocation based on the model for resource allocation configuration higher.

[0161] In this embodiment of the present invention, the intelligent recommendation algorithm leverages big data from historical placement strategies and placement strategies for specific locations and demographics to achieve the optimal placement strategy for each marketing position, based on operational optimization goals. Furthermore, after placement, the data is recycled, and the algorithm continues learning and iterating. This cycle of continuous optimization ultimately achieves greater returns. This represents a significant leap from "manually tedious and complex" to "intelligent recommendation and iterative optimization."

[0162] Corresponding to the model training method for resource placement configuration provided in the above embodiment, the embodiment of the present invention also provides a model training device for resource placement configuration, such as Figure 6 Shown, including:

[0163] The first acquisition module 601 is used to acquire material data, resource location data, user data and policy data, where the policy data stores the correspondence between multiple resource locations, multiple users and multiple target historical configuration policies;

[0164] The training module 602 is used to perform the following steps: S1, based on the material data, resource position data and user data, a plurality of prediction configuration strategies are obtained through the model to be trained, each prediction configuration strategy is used to represent a strategy for displaying the target material to the target user at the target resource position; S2, selecting the prediction configuration strategy, and searching the strategy data for the target configuration strategy corresponding to the target resource position and target user in the selected prediction configuration strategy, the target configuration strategy being the configuration strategy in the historical configuration strategy whose benefits meet the preset benefit conditions; S3, comparing the selected prediction configuration strategy and the target configuration strategy; S4, adjusting the model parameters of the model to be trained based on the comparison result of the selected prediction configuration strategy and the target configuration strategy; repeating S1 to S4 until the preset iteration end condition is met, and using the model parameters that meet the preset iteration end condition as the model parameters of the model to be trained to obtain a trained model.

[0165] The first acquisition module 601 is specifically used to: obtain pre-constructed policy data; wherein the policy data is constructed in the following manner: obtaining historical configuration strategies for displaying materials to multiple users at multiple resource locations within a historical period, and obtaining the benefits corresponding to each historical configuration strategy; searching for historical configuration strategies for the same target resource location and the same target user; selecting a configuration strategy for the same target resource location and the same target user whose benefits meet a preset benefit condition from the historical configuration strategies as the target configuration strategy corresponding to the target resource location and the target user.

[0166] The training module 602 is specifically configured to select the historical configuration strategy with the highest benefit among the historical configuration strategies for the same target resource location and the same target user as the target configuration strategy corresponding to the target resource location and the target user.

[0167] Training module 602 is specifically used to compare the benefits corresponding to each historical configuration strategy found for the same target resource location and the same target user with the preset benefits; if the benefit corresponding to a historical configuration strategy exceeds the preset benefit, the historical configuration strategy is used as the target configuration strategy corresponding to the target resource location and the target user; or, if the benefit corresponding to a historical configuration strategy does not exceed the preset benefit, the historical configuration strategy is used as the target configuration strategy corresponding to the target resource location and the target user.

[0168] The training module 602 is specifically configured to allocate preset parameters to the historical configuration strategy according to the revenue type; and calculate the revenue of displaying the material to the user at the resource position based on the preset parameters.

[0169] The training module 602 is specifically configured to adjust the model parameters of the to-be-trained model based on the difference between the selected prediction configuration strategy and the target configuration strategy.

[0170] Corresponding to the resource placement configuration method provided in the above embodiment, the embodiment of the present invention also provides a resource placement configuration device, such as Figure 7 Shown, including:

[0171] The second acquisition module 701 is used to obtain the materials, resource locations and users to be delivered;

[0172] Determination module 702 is used to input the materials, resource positions and users to be delivered into a pre-trained model for resource delivery configuration, and obtain a configuration strategy for displaying materials to users at the resource positions, so that resources can be delivered based on the configuration strategy. The model for resource delivery configuration is trained based on the model training method for resource delivery configuration in the above-mentioned embodiment.

[0173] The embodiment of the present invention further provides an electronic device, such as Figure 8 As shown, it includes a processor 801, a communication interface 802, a memory 803 and a communication bus 804, wherein the processor 801, the communication interface 802, and the memory 803 communicate with each other through the communication bus 804;

[0174] Memory 803, used for storing computer programs;

[0175] The processor 801 is used to implement the method steps of the above-mentioned model training method or resource delivery configuration method when executing the program stored in the memory 803.

[0176] The communication bus mentioned in the terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or only one type of bus.

[0177] The communication interface is used for communication between the above terminal and other devices.

[0178] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor.

[0179] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0180] In another embodiment provided by the present invention, a computer-readable storage medium is also provided, in which a computer program is stored. When the computer program is executed by a processor, it implements the model training method or resource delivery configuration method for resource delivery configuration described in any of the above embodiments.

[0181] In another embodiment provided by the present invention, a computer program product containing instructions is also provided. When the computer is run on the computer, the computer executes the model training method or resource delivery configuration method for any of the above embodiments.

[0182] In the above embodiments, all or part of the embodiments can be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be magnetic media (e.g., floppy disk, hard disk, tape), optical media (e.g., DVD), or semiconductor media (e.g., solid-state disk (SSD)).

[0183] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0184] Each embodiment in this specification is described in a related manner. Similar portions between embodiments can be referenced to each other. Each embodiment focuses on the differences between other embodiments. In particular, the device, electronic device, computer-readable storage medium, and computer program product embodiments are generally similar to the method embodiments, so their descriptions are relatively simple. For related portions, reference can be made to the descriptions of the method embodiments.

[0185] The above description is only a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention are included in the scope of protection of the present invention.

Claims

1. A model training method for resource deployment configuration, characterized in that: include: Acquire material data, resource location data, user data, and policy data, wherein the policy data stores a correspondence between multiple resource locations, multiple users, and multiple target historical configuration policies; S1, based on the material data, the resource location data, and the user data, a plurality of prediction configuration strategies are obtained through a to-be-trained model, each prediction configuration strategy being used to represent a strategy for displaying a target material to a target user at a target resource location; S2, selecting a predicted configuration strategy, and searching the strategy data for a target configuration strategy corresponding to the target resource location and target user in the selected predicted configuration strategy, wherein the target configuration strategy is a configuration strategy whose benefits meet a preset benefit condition among the historical configuration strategies; S3, comparing the selected prediction configuration strategy with the target configuration strategy; S4, adjusting the model parameters of the to-be-trained model based on a comparison result between the selected prediction configuration strategy and the target configuration strategy; Repeat S1 to S4 until the preset iteration end condition is met, and use the model parameters that meet the preset iteration end condition as the model parameters of the model to be trained to obtain a trained model.

2. The method according to claim 1, characterized in that Obtaining the policy data includes: Obtain pre-built policy data; the policy data is constructed in the following manner: Obtain historical configuration strategies for displaying materials to multiple users at multiple resource locations over a historical period, as well as the corresponding revenue for each historical configuration strategy. Find historical configuration policies for the same target resource location and the same target user; A configuration strategy whose benefit satisfies a preset benefit condition among historical configuration strategies for the same target resource location and the same target user is selected as the target configuration strategy corresponding to the target resource location and the target user.

3. The method according to claim 2, characterized in that The selecting, from historical configuration strategies for the same target resource location and the same target user, a configuration strategy whose benefits satisfy a preset benefit condition as the target configuration strategy corresponding to the target resource location and the target user includes: A historical configuration strategy with the highest benefit among historical configuration strategies for the same target resource location and the same target user is selected as the target configuration strategy corresponding to the target resource location and the target user.

4. The method according to claim 2, characterized in that The selecting, from historical configuration strategies for the same target resource location and the same target user, a configuration strategy whose benefits satisfy a preset benefit condition as the target configuration strategy corresponding to the target resource location and the target user includes: Compare the benefits corresponding to each historical configuration strategy found for the same target resource location and the same target user with the preset benefits; If the benefit corresponding to a historical configuration strategy exceeds the preset benefit, the historical configuration strategy is used as the target configuration strategy corresponding to the target resource position and the target user; or, if the benefit corresponding to a historical configuration strategy does not exceed the preset benefit, the historical configuration strategy is used as the target configuration strategy corresponding to the target resource position and the target user.

5. The method according to claim 2, characterized in that The acquisition of the benefits corresponding to each historical configuration strategy includes: Assign preset parameters to the historical configuration strategy based on the revenue type; and calculate the revenue of displaying materials to users at the resource location based on the preset parameters.

6. The method according to any one of claims 1 to 5, characterized in that The adjusting the model parameters of the to-be-trained model based on the comparison result of the selected prediction configuration strategy and the target configuration strategy includes: Based on the difference between the selected prediction configuration strategy and the target configuration strategy, the model parameters of the to-be-trained model are adjusted.

7. A resource placement configuration method, characterized in that: include: Obtain the materials, resource locations, and users to be delivered; The material to be delivered, the resource position and the user are input into a pre-trained model for resource delivery configuration, and a configuration strategy for displaying the material to the user at the resource position is obtained, so that resource delivery is performed based on the configuration strategy, wherein the model for resource delivery configuration is trained based on the model training method for resource delivery configuration described in any one of claims 1 to 6 above.

8. A model training device for resource deployment configuration, characterized in that: include: A first acquisition module is used to acquire material data, resource location data, user data and policy data, wherein the policy data stores a correspondence between multiple resource locations, multiple users and multiple target historical configuration policies; The training module is used to perform the following steps: S1, based on the material data, the resource position data and the user data, a plurality of prediction configuration strategies are obtained through the model to be trained, each prediction configuration strategy is used to represent a strategy for displaying the target material to the target user at the target resource position; S2, selecting a prediction configuration strategy, and searching the strategy data for a target configuration strategy corresponding to the target resource position and the target user in the selected prediction configuration strategy, the target configuration strategy being a configuration strategy in the historical configuration strategy whose benefits meet the preset benefit conditions; S3, comparing the selected prediction configuration strategy with the target configuration strategy; S4, adjusting the model parameters of the model to be trained based on the comparison result between the selected prediction configuration strategy and the target configuration strategy; repeating S1 to S4 until the preset iteration end condition is met, and using the model parameters that meet the preset iteration end condition as the model parameters of the model to be trained to obtain a trained model.

9. A resource placement configuration device, characterized in that: include: The second acquisition module is used to obtain the materials, resource locations and users to be delivered; A determination module is used to input the material to be delivered, the resource position and the user into a pre-trained model for resource delivery configuration, and obtain a configuration strategy for displaying the material to the user at the resource position, so that resource delivery is performed based on the configuration strategy, wherein the model for resource delivery configuration is trained based on the model training method for resource delivery configuration described in any one of claims 1 to 6 above.

10. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory for storing computer programs; A processor, configured to implement the method steps described in any one of claims 1 to 7 when executing a program stored in a memory.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps according to any one of claims 1 to 7 are implemented.

Images