Virtual resource putting method and device, storage medium and electronic equipment

Abstract

The application discloses a virtual resource putting method and device, a storage medium and an electronic device. The method comprises the following steps: obtaining a resource putting request, wherein the resource putting request is used for requesting to put virtual resources associated with a target application to a user account, the virtual resources are used for providing reference for adjusting target interaction data of the user account, and the target interaction data is data generated by the user account when performing a target type of interaction operation on the target application; in response to the resource putting request, obtaining target user characteristics corresponding to the user account; based on the target user characteristics, determining a target user group in which the user account is located from N user groups corresponding to the target type, wherein N is an integer greater than or equal to 1; and putting the virtual resources to the user account according to putting instruction information corresponding to the target user group. The application solves the technical problem of low accuracy of virtual resource putting.

Description

Technical Field

[0001] This invention relates to the field of computers, and more specifically, to a method, apparatus, storage medium, and electronic device for virtual resource deployment. Background Technology

[0002] In actual product operation, due to considerations such as distributing virtual resources or reducing user harassment, it is necessary to target specific eligible user groups with virtual resources. However, existing technologies often rely on the personal experience of data analysts to determine user group segmentation information. This method is heavily dependent on human experience, making it prone to errors. Furthermore, it fails to consider that segmented user groups may not be suited to different product optimization directions, thus failing to accurately distribute virtual resources to matching user groups and resulting in wasted virtual resources. In other words, existing technologies suffer from low accuracy in virtual resource distribution.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This invention provides a method, apparatus, storage medium, and electronic device for virtual resource deployment, in order to at least solve the technical problem of low accuracy in virtual resource deployment.

[0005] According to one aspect of the present invention, a virtual resource delivery method is provided, comprising: obtaining a resource delivery request, wherein the resource delivery request is used to request the delivery of virtual resources associated with a target application to a user account, the virtual resources being used to provide a reference for the user account to adjust target interaction data, the target interaction data being data generated by the user account when performing a target type interaction operation on the target application; responding to the resource delivery request and obtaining target user characteristics corresponding to the user account; based on the target user characteristics, determining the target user group to which the user account belongs from N user groups corresponding to the target type, wherein N is an integer greater than or equal to 1; and delivering the virtual resources to the user account according to delivery instruction information corresponding to the target user group.

[0006] According to another aspect of the present invention, a virtual resource delivery device is also provided, comprising: a first acquisition unit, configured to acquire a resource delivery request, wherein the resource delivery request is used to request the delivery of virtual resources associated with a target application to a user account, the virtual resources being used to provide a reference for the user account to adjust target interaction data, the target interaction data being data generated by the user account when performing a target type interaction operation on the target application; a second acquisition unit, configured to respond to the resource delivery request and acquire target user characteristics corresponding to the user account; a first determination unit, configured to determine the target user group to which the user account belongs from N user groups corresponding to the target type based on the target user characteristics, wherein N is an integer greater than or equal to 1; and a delivery unit, configured to deliver the virtual resources to the user account according to delivery instruction information corresponding to the target user group.

[0007] As an optional solution, it includes: a third acquisition unit, configured to acquire M first sample user accounts before the resource delivery request, wherein the first sample user accounts are accounts that have been delivered the virtual resources within a first time period, and M is an integer greater than 1; a fourth acquisition unit, configured to acquire M first sample user features corresponding to each of the M first sample user accounts before the resource delivery request; and a fifth acquisition unit, configured to acquire the N user groups using the M first sample user features before the resource delivery request.

[0008] As an optional solution, it includes: a sixth acquisition unit, configured to acquire P second sample user accounts and K third sample user accounts before the resource delivery request, wherein the second sample user accounts are accounts that received the virtual resources during the second time period, and the third sample user accounts are accounts that did not receive the virtual resources during the second time period, and K and P are both integers greater than 1; a seventh acquisition unit, configured to acquire P second sample user features corresponding to each of the P second sample user accounts and K third sample user features corresponding to each of the K third sample user accounts before the resource delivery request; and an eighth acquisition unit, configured to acquire the P second sample user features and K third sample user features corresponding to each of the P second sample user accounts before the resource delivery request. The adjustment values ​​generated when the user account and the third sample user account adjust the target interaction data during the second time period; the calculation unit is used to calculate and process the adjustment values ​​before obtaining the resource delivery request to obtain P target sample features, wherein the target sample features are used to represent the degree of matching between the second sample user account and the target interaction data; the second determination unit is used to determine N group features corresponding to each of the N user groups based on the P target sample features, the K third sample user features, and the P second sample user features before obtaining the resource delivery request; the ninth acquisition unit is used to acquire the N user groups using the N group features before obtaining the resource delivery request.

[0009] As an optional solution, the above-mentioned calculation unit includes: a repetition module, used to repeatedly execute the following steps until the above-mentioned P target sample features are obtained; a third determination module, used to determine the current second sample user account from the above-mentioned P second sample user accounts; a second acquisition module, used to acquire the first adjustment value generated when the above-mentioned current second sample user account adjusts the above-mentioned target interaction data during the above-mentioned second time period, and the second adjustment value generated when the reference user group associated with the current user group to which the above-mentioned current second sample user account belongs adjusts the above-mentioned target interaction data during the above-mentioned second time period, wherein the above-mentioned current user group is a user group determined for the above-mentioned current second sample user account based on the above-mentioned P second sample user features, and the above-mentioned reference user group is selected from the user group determined for the above-mentioned third sample user account based on the above-mentioned K third sample user features; a first calculation module, used to calculate and process the above-mentioned first adjustment value and the above-mentioned second adjustment value; and a third acquisition module, used to acquire the next second sample user account as the above-mentioned current second sample user account after calculating and obtaining the target sample features corresponding to the above-mentioned current second sample user account.

[0010] As an optional scheme, the above-mentioned calculation unit includes: a second calculation module, used to calculate the information divergence of each of the P second sample user features relative to the P target sample features, wherein the information divergence is used to represent the degree of correlation between features; and a fourth determination module, used to determine the N group features based on the multiple information divergences.

[0011] As an optional approach, when the second sample user features include both categorical features and continuous features, the second calculation module includes at least one of the following: a second calculation submodule, configured to calculate, respectively, the P first information divergences of each of the P second sample user features relative to the P target sample features, wherein the categorical features are used to determine the user group to which each of the second sample user accounts belongs; and a third calculation submodule, configured to calculate, respectively, the P second information divergences of each of the P second sample user features relative to the P target sample features, wherein the continuous features are used to represent the interaction data generated by the second sample user accounts during the second time period.

[0012] As an optional solution, the above-mentioned delivery unit includes at least one of the following: a first delivery module, used to deliver the target quantity of the virtual resources corresponding to the delivery instruction information to the user account; a second delivery module, used to deliver the virtual resources to the user account according to the delivery frequency corresponding to the delivery instruction information; and a third delivery module, used to deliver the virtual resources to the user account according to the delivery type corresponding to the delivery instruction information.

[0013] According to another aspect of the present invention, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer program, and the computer program is configured to execute the above-described virtual resource deployment method at runtime.

[0014] According to another aspect of the present invention, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the virtual resource deployment method described above through the computer program.

[0015] In this embodiment of the invention, a resource delivery request is obtained, wherein the resource delivery request is used to request the delivery of virtual resources associated with a target application to a user account. The virtual resources are used to provide a reference for the user account to adjust target interaction data. The target interaction data is the data generated by the user account when performing a target type interaction operation on the target application. In response to the resource delivery request, the target user characteristics corresponding to the user account are obtained. Based on the target user characteristics, the target user group to which the user account belongs is determined from N user groups corresponding to the target type, wherein N is an integer greater than or equal to 1. According to the delivery instruction information corresponding to the target user group, the virtual resources are delivered to the user account. The corresponding virtual resources are delivered in a targeted manner through the target interaction data, and the method of selecting the group to be delivered from the user group corresponding to the target type is used to make the virtual resources delivered to a specific user group in a specific direction, thereby achieving the technical objective of improving the matching degree between the delivered virtual resources and the user group, thereby achieving the technical effect of improving the accuracy of virtual resource delivery, and thus solving the technical problem of low accuracy of virtual resource delivery. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0017] Figure 1 This is a schematic diagram of an application environment for an optional virtual resource deployment method according to an embodiment of the present invention;

[0018] Figure 2 This is a schematic diagram of the flow of an optional virtual resource deployment method according to an embodiment of the present invention;

[0019] Figure 3 This is a schematic diagram of an optional virtual resource deployment method according to an embodiment of the present invention;

[0020] Figure 4 This is a schematic diagram of another optional virtual resource deployment method according to an embodiment of the present invention;

[0021] Figure 5 This is a schematic diagram of another optional virtual resource deployment method according to an embodiment of the present invention;

[0022] Figure 6 This is a schematic diagram of an optional virtual resource delivery device according to an embodiment of the present invention;

[0023] Figure 7 This is a schematic diagram of another optional virtual resource delivery device according to an embodiment of the present invention;

[0024] Figure 8 This is a schematic diagram of another optional virtual resource delivery device according to an embodiment of the present invention;

[0025] Figure 9 This is a schematic diagram of another optional virtual resource delivery device according to an embodiment of the present invention;

[0026] Figure 10 This is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] First, to facilitate understanding of the embodiments of the present invention, some terms or nouns involved in the present invention will be explained below:

[0030] Blockchain is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and cryptographic algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying platform, a platform product service layer, and an application service layer.

[0031] The underlying blockchain platform can include processing modules such as user management, basic services, smart contracts, and operational monitoring. The user management module is responsible for managing the identity information of all blockchain participants, including maintaining public and private key generation (account management), key management, and maintaining the correspondence between user real identities and blockchain addresses (access management). Furthermore, under authorization, it monitors and audits transactions of certain real identities and provides risk control rule configuration (risk control audit). The basic services module is deployed on all blockchain node devices to verify the validity of business requests. After consensus is reached on valid requests, they are recorded in storage. For a new business request, the basic services first perform interface adaptation parsing and authentication (interface adaptation), and then encrypt the business information through a consensus algorithm (consensus management). After encryption, the data is transmitted completely and consistently to the shared ledger (network communication) and recorded and stored. The smart contract module is responsible for contract registration, issuance, triggering, and execution. Developers can define contract logic using a programming language and publish it to the blockchain (contract registration). According to the contract terms, the key or other events are invoked to trigger execution and complete the contract logic. It also provides functions for contract upgrades and cancellations. The operation monitoring module is mainly responsible for deployment, configuration modification, contract settings, cloud adaptation, and real-time status visualization output during product release, such as alarms, monitoring network conditions, and monitoring the health status of node devices.

[0032] The platform's product service layer provides the basic capabilities and implementation frameworks for typical applications. Developers can leverage these basic capabilities, along with the specific characteristics of their business needs, to implement blockchain-based business logic. The application service layer provides blockchain-based application services to business stakeholders.

[0033] According to one aspect of the present invention, a virtual resource deployment method is provided. Optionally, as an optional implementation, the above-described virtual resource deployment method may be applied to, but is not limited to, [examples of other methods]. Figure 1 The environment shown may include, but is not limited to, user equipment 102, network 110, and server 112. The user equipment 102 may include, but is not limited to, a display 108, a processor 106, and a memory 104.

[0034] The specific process can be summarized in the following steps:

[0035] In step S102, user equipment 102 obtains a resource delivery request, wherein the resource delivery request is used to request the delivery of virtual resources to account 1;

[0036] In steps S104-S106, user equipment 102 sends a resource delivery request to server 112 via network 110;

[0037] In step S108, server 112 searches for the attribute / behavioral data of account 1 in database 114 and processes the attribute / behavioral data through processing engine 116 to obtain the user characteristics corresponding to account 1; further, processing engine 116 determines the target user group to which account 1 belongs based on the user characteristics corresponding to account 1, and searches for the corresponding delivery data of the target user group in database 114 to generate instruction information, wherein the instruction information is used to indicate the method of delivery of virtual resources, such as the delivery quantity, delivery frequency, etc.

[0038] In steps S110-S112, server 112 sends instruction information to user equipment 102 via network 110, displays the instruction information on display 108, and uses processor 106 in user equipment 102 to allocate virtual resources to account 1 according to the instruction information, and stores the instruction information and feedback information after allocation in memory 104.

[0039] remove Figure 1 Beyond the illustrated example, the above steps can be performed independently by user equipment 102. That is, user equipment 102 can perform steps such as acquiring user characteristics, determining target user groups, searching for delivery data, and generating instruction information, thereby reducing the processing load on the server. User equipment 102 includes, but is not limited to, handheld devices (such as mobile phones), laptops, desktop computers, and in-vehicle devices. This invention does not limit the specific implementation of user equipment 102.

[0040] Alternatively, as an alternative implementation method, such as Figure 2 As shown, the methods for deploying virtual resources include:

[0041] S202, Obtain resource delivery request, wherein the resource delivery request is used to request the delivery of virtual resources associated with the target application to the user account. The virtual resources are used to provide a reference for the user account to adjust the target interaction data. The target interaction data is the data generated when the user account performs a target type interaction operation on the target application.

[0042] S204, responding to the resource delivery request, obtain the target user characteristics corresponding to the user account;

[0043] S206, Based on the characteristics of the target user, determine the target user group to which the user account belongs from the N user groups corresponding to the target type, where N is an integer greater than or equal to 1;

[0044] S208, according to the delivery instructions corresponding to the target user group, deliver virtual resources to the user account.

[0045] Optionally, in this embodiment, the above-mentioned virtual resource delivery method can be applied, but is not limited to, in scenarios where user accounts are segmented and operated in a refined manner to improve the delivery efficiency and actual operational efficiency of virtual resources. For example, by combining the target type corresponding to specific business needs, the most matching target user group is selected for the user account to be delivered, and then virtual resources are delivered to the user account to be delivered in a targeted manner according to the resource delivery method corresponding to the target user group. This achieves refined user segmentation around specific business needs, makes the best use of virtual resources, reduces unnecessary waste of virtual resources, and improves the delivery efficiency of virtual resources.

[0046] Optionally, in this embodiment, the user account may be, but is not limited to, the account of the target application, or may be, but is not limited to, the account of other applications. For example, virtual resources of application A may be delivered to the account of application A, or virtual resources of application B may be delivered to the account of application A.

[0047] Optionally, in this embodiment, virtual resources may be, but are not limited to, virtual advertisements, virtual services, virtual currency, and other resources used to promote the target application. For example, advertising information corresponding to the target application may be delivered to a user account, or a virtual customer service corresponding to the target application may be provided to a user account, or an operation interface for virtual tasks may be provided to a user account, and after the user account completes the corresponding virtual task (such as logging into the target application), a corresponding amount of virtual currency may be transferred to the user account.

[0048] Optionally, in this embodiment, the target interaction data is the data generated when a user account performs a target type of interaction operation on the target application. The interaction operation can be, but is not limited to, various operation types, such as click type, like type, comment type, subscription type, reading type, virtual resource transfer type, etc. The target application in different application scenarios can flexibly select the target type corresponding to actual needs. For example, assuming the target application is a reading application, the target type can be, but is not limited to, determined as the reading type, thereby determining the virtual resources allocated to the user account based on the data generated when the user account performs a reading operation on the reading application. Similarly, assuming the target application is a shopping application, the target type can be, but is not limited to, determined as the resource transfer type, thereby determining the virtual resources allocated to the user account based on the data generated when the user account performs a resource transfer operation (such as consumption) on the shopping application.

[0049] Optionally, in this embodiment, the use of virtual resources to provide a reference for adjusting target interaction data for user accounts can be understood, but is not limited to, as the virtual resources can have a certain impact on the adjustment of target interaction data for user accounts, or play a role in promoting or guiding them. For example, the virtual resource is a target virtual task, and the target virtual task is used to guide the user account to complete the registration of the target application or to perform a certain number or frequency of operations in the target application. When the target virtual task is in a completed state, virtual items or virtual currency are transferred to the user account or the account associated with the user account in the target application, so as to promote the establishment of user account and improve the association relationship between the user account and the target application.

[0050] Optionally, in this embodiment, the user account's adjustment of the target interaction data may include, but is not limited to, at least one of the following: the user account increases the target interaction data, or the user account decreases the target interaction data. Specifically, when the target interaction data is positive interaction data (such as data triggered by interactive behaviors that benefit the target application, such as liking, commenting, tipping, and shopping), virtual resources are deployed to promote the user account's increase in the target interaction data; conversely, when the target interaction data is negative interaction data (such as data triggered by interactive behaviors that harm the target application, such as reporting, giving bad reviews, and uninstalling), virtual resources are deployed to promote the user account's decrease in the target interaction data.

[0051] Optionally, in this embodiment, the target user features may be used, but are not limited to, to represent the account characteristics of the user account, such as the user account's behavioral data, the user account's attribute information, etc. The behavioral data may include, but is not limited to, data generated by the user account's actions performed on the target application or other applications, such as resource transfer data, interactive operation data, etc.; the attribute information may include, but is not limited to, the user account's account attribute information, or the user attribute information associated with the user account, such as account level, user identity identifier, user gender, user age, etc.

[0052] Optionally, in this embodiment, the N user groups corresponding to the target type can be obtained in advance, but not limited to, before obtaining the resource delivery request, or can be understood as first obtaining the user group sets corresponding to different types, assigning a corresponding target tag to each user group, and then finding the target tag that matches the corresponding account characteristics in the user group set, thereby determining the N user groups corresponding to the target tag.

[0053] It should be noted that by targeting virtual resources through interactive data and selecting target groups from user groups corresponding to the target type, virtual resources are delivered to specific user groups in a specific direction. This improves the matching degree between targeted virtual resources and user groups, thereby achieving efficient delivery of virtual resources.

[0054] To further illustrate, the optional assumptions are as follows: Figure 3 As shown, firstly, a resource delivery request for account 1 is triggered at the virtual button "Targeted Resource Delivery" in client 302, as follows: Figure 3 As shown in (a); further responding to the resource delivery request, and upon obtaining the account user characteristics corresponding to account 1, determining the target user group to which account 1 belongs based on the account user characteristics, wherein the target user group may, but is not limited to, have a pre-assigned corresponding resource delivery strategy (delivery instruction information); furthermore, as Figure 3 As shown in (b), according to the resource delivery strategy corresponding to the target user group, virtual promotional resource 304 is delivered to account 1. Virtual promotional resource 304 is delivered by displaying it on the display interface of account 1. Specifically, a promotional resource box is displayed in the lower left corner of the corresponding display interface, and virtual promotional resource 304 is displayed in this box. This virtual promotional resource 304 is used to promote game A. Furthermore, users of account 1 can click the virtual button "Click to Enter" on the virtual promotional resource 304 to redirect the current display interface to the login / registration interface of game A (the target application), as shown below. Figure 3 As shown in (c); based on this, the promotion and operation of account 1 is completed by the targeted delivery of virtual resources. Since the virtual promotion resource 304 is determined based on the account characteristics corresponding to account 1, it can be understood that the matching degree between the virtual promotion resource 304 and account 1 is relatively high. As a result, account 1 has a relatively high probability of making the virtual promotion resource 304 effective, thereby increasing the user group of game A.

[0055] The embodiments provided in this application obtain a resource delivery request, wherein the resource delivery request is used to request the delivery of virtual resources associated with a target application to a user account. The virtual resources are used to provide a reference for the user account to adjust target interaction data, and the target interaction data is the data generated when the user account performs a target type interaction operation on the target application. In response to the resource delivery request, the target user characteristics corresponding to the user account are obtained. Based on the target user characteristics, the target user group to which the user account belongs is determined from N user groups corresponding to the target type, where N is an integer greater than or equal to 1. Virtual resources are delivered to the user account according to the delivery instruction information corresponding to the target user group. The corresponding virtual resources are delivered in a targeted manner through the target interaction data, and the method of selecting a group to be delivered from the user group corresponding to the target type is used to ensure that the virtual resources are delivered to a specific user group in a specific direction. This achieves the technical objective of improving the matching degree between the delivered virtual resources and the user group, thereby realizing the technical effect of improving the accuracy of virtual resource delivery.

[0056] As an optional approach, based on target user characteristics, the target user group to which the user account belongs is determined from N user groups corresponding to the target type, including:

[0057] S1, obtain the N group features corresponding to each user group in the N user groups;

[0058] S2, determine the target group feature from N group features, wherein the feature similarity between the target group feature and the target user feature is greater than or equal to the first threshold;

[0059] S3, determine the user group corresponding to the target group characteristics as the target user group.

[0060] Optionally, in this embodiment, the target user feature corresponding to the user account may be, but is not limited to, one (class) or multiple (classes). Specifically, when the target user feature corresponding to the user account is one (class), the target user feature may be compared with the N group features corresponding to each user group in the N user groups for feature similarity. Or, when the target user feature corresponding to the user account is multiple (classes), each (class) sub-feature of the target user feature may be compared with each (class) sub-feature of the N group features corresponding to each user group in the N user groups for feature similarity. Or, when the target user feature corresponding to the user account is multiple (classes), the multiple (classes) sub-features of the target user feature may be integrated into one (class) feature first, and then the integrated feature may be compared with the N group features corresponding to each user group in the N user groups for feature similarity.

[0061] Optionally, in this embodiment, feature similarity can be used, but is not limited to, to represent the similarity between at least two events, behaviors, or pieces of information. It can be, but is not limited to, being reflected by calculating the distance between features. For example, a small distance between features can be used, but is not limited to, to represent a large feature similarity; conversely, a large distance between features can be used, but is not limited to, to represent a small feature similarity. The distance between features can be, but is not limited to, at least one of the following: Minkowski distance, Manhattan distance, Euclidean distance, Chebyshev distance, cosine similarity, Hellinger distance (KL divergence), etc.

[0062] Optionally, in this embodiment, each of the N user groups corresponds to a group feature, and there may be, but is not limited to, a priority relationship between the group features;

[0063] To further illustrate, such as Figure 4 As shown, N user groups are displayed in list 402, where the first user group 404 corresponds to the first group feature, the second user group 406 corresponds to the second group feature, and the first group feature corresponding to the first user group 404 has a higher priority than the second group feature corresponding to the second user group 406. This can be understood as the first user group 404 having a higher priority than the second user group 406. Assuming that after feature matching, it is determined that the group where user account A belongs is the first user group 404 and the group where user account B belongs is the second user group 406, in the subsequent allocation of virtual resources, the virtual resources allocated to user account A may be, but are not limited to, better than the virtual resources allocated to user account B.

[0064] The embodiments provided in this application obtain N group features corresponding to each of the N user groups; determine the target group features from the N group features, wherein the feature similarity between the target group features and the target user features is greater than or equal to a first threshold; and determine the user group corresponding to the target group features as the target user group, thereby achieving the purpose of efficiently determining the user group to which a user account belongs by utilizing feature similarity, and realizing the effect of improving the efficiency of user group determination.

[0065] As an optional approach, the target group features are determined from N group features, including:

[0066] S1, when the target user features include at least two types of user features, obtain the calculated weight of each user feature in the target user features, wherein the calculated weight is associated with the target type;

[0067] S2, integrates and calculates the two types of user features based on the calculated weights to obtain the target features;

[0068] S3, identify the group features among N group features whose feature similarity to the target feature is greater than or equal to the second threshold.

[0069] Optionally, in this embodiment, the target user features may include, but are not limited to, at least two types of user features. For example, the target user features may include a first user feature and a second user feature, and the first user feature and the second user feature may have different feature types. Therefore, the first user feature and the second user feature may be calculated separately, and then, based on the calculation results of the first user feature and the second user feature, the first group feature and the second group feature with a feature similarity greater than or equal to a second threshold with the target feature may be determined from among N group features. Alternatively, the first user feature and the second user feature may be uniformly integrated and calculated, and the weights on which the integration and calculation are based may be, but are not limited to, pre-obtained calculation weights. Then, based on the calculation results of the first user feature and the second user feature, the group features with a feature similarity greater than or equal to a second threshold with the target feature may be determined from among N group features.

[0070] It should be noted that, when the target user features include one type of user feature, it is possible, but not limited to, directly determining the group features with a feature similarity greater than or equal to the target feature from among the N group features based on that one type of user feature; while when the target user features include at least two types of user features, it is possible, but not limited to, calculating the feature similarity between each type of user feature and the target feature separately, and taking the target feature corresponding to the lowest or highest feature similarity to determine the group features with a feature similarity greater than or equal to the target feature from among the N group features; or, following the method described above for determining the target group features from among the N group features, when the target user features include at least two types of user features, the at least two types of user features are integrated and calculated according to the calculation weight, and based on the calculation results, the group features with a feature similarity greater than or equal to the target feature are determined from among the N group features.

[0071] Through the embodiments provided in this application, when the target user features include at least two types of user features, the calculated weight of each user feature in the target user features is obtained, wherein the calculated weight is associated with the target type; the two types of user features are integrated and calculated based on the calculated weight to obtain the target feature; and the group features with a feature similarity to the target feature greater than or equal to a second threshold are determined among N group features, thereby achieving the purpose of comprehensively determining the group features through multiple methods and realizing the effect of improving the comprehensiveness of the group features.

[0072] As an optional approach, before obtaining the resource delivery request, the following steps are taken:

[0073] S1, obtain M first sample user accounts, where the first sample user accounts are the accounts that received virtual resources in the first time period, and M is an integer greater than 1;

[0074] S2, obtain the M first sample user features corresponding to each sample user account in the M first sample user accounts;

[0075] S3 uses the features of M first sample users to obtain N user groups.

[0076] Optionally, in this embodiment, M sample user accounts are randomly selected from the database, and then the same or different types of strategies or operational activities are deployed to the sample user accounts.

[0077] Furthermore, data from sample user accounts after the campaign is launched is collected, and preliminary data cleaning based on anomaly detection (such as filtering invalid or malicious users) is performed to calculate the optimization target metrics (target interaction data) before and after the campaign.

[0078] Furthermore, the feature construction of the above sample user account data can refer to the standard process of feature engineering;

[0079] Furthermore, based on user characteristics, the above sample user accounts are grouped. For example, the continuous features (such as continuous resource transfer features, continuous interaction execution features, etc.) corresponding to the above sample user accounts are binned into k equal parts (k can be between 3 and 10 depending on the number of features), and all users are divided into n user groups (n can be between 50 and 200 depending on the number of samples).

[0080] Furthermore, for each sample user account, the rate of change of its own target metric is calculated to construct user prediction labels;

[0081] Based on this, N user groups are identified using the constructed user prediction labels.

[0082] It should be noted that before obtaining resource delivery requests, it is necessary to construct sample user characteristics using the data corresponding to the collected sample user accounts, and obtain multiple corresponding user groups based on these sample user characteristics.

[0083] The embodiments provided in this application obtain M first sample user accounts, where the first sample user accounts are accounts that have been given virtual resources in a first time period, and M is an integer greater than 1; obtain M first sample user features corresponding to each of the M first sample user accounts; and use the M first sample user features to obtain N user groups, thereby achieving the purpose of automatically obtaining the corresponding user groups and improving the efficiency of obtaining user groups.

[0084] As an optional approach, before obtaining the resource delivery request, the following steps are taken:

[0085] S1. Obtain P second sample user accounts and K third sample user accounts, where the second sample user accounts are accounts that received virtual resources during the second time period, and the third sample user accounts are accounts that did not receive virtual resources during the second time period. K and P are both integers greater than 1.

[0086] S2, obtain the P second sample user features corresponding to each sample user account in the P second sample user accounts, and the K third sample user features corresponding to each sample user account in the K third sample user accounts;

[0087] S3, obtain the adjustment values ​​generated when the second sample user account and the third sample user account adjust the target interaction data during the second time period;

[0088] S4, calculate and process the adjustment value to obtain P target sample features, where the target sample features are used to represent the degree of matching between the second sample user account and the target interaction data;

[0089] S5. Based on P target sample features, K third sample user features, and P second sample user features, determine N group features corresponding to each user group in the N user groups.

[0090] S6 uses N group features to obtain N user groups.

[0091] Optionally, in this embodiment, the second sample user account and the third sample user account may be, but are not limited to, user accounts of different types, such as the second sample user account being a positive sample user account and the third sample user account being a negative sample user account, and the N user groups finally obtained may, but are not limited to, correspond to each of the second sample user accounts.

[0092] It should be noted that in actual work, the product manager's personal experience is often relied upon to determine the user groups to be targeted. The product manager will output some rules to extract user groups to lock in the target audience. From experience, the results of decision-making based on experience are often not ideal. Therefore, it is necessary to explore data-driven and automated methods that do not rely on human experience to complete this process, thereby improving operational efficiency and product effectiveness.

[0093] For specific examples, one option is to first determine the metrics (target interaction data) of the campaign optimization target. For different types of products and businesses, the corresponding optimization target metrics will be different, such as purchase frequency (e-commerce), reading time (information flow products), click-through rate (ads), etc.

[0094] Then, a group of random users (second sample user accounts) will be targeted with strategies or operational activities, while another group of random users with the same attributes (third sample user accounts) will not be targeted as a control group. The purpose of this stage is to prepare for data collection. The following pre-targeting strategies can be adopted according to the user base: experimental group (second sample user accounts): 1% of users will be randomly selected for targeting, and control group (third sample user accounts): 1% of users will not be targeted. The user ratio can be determined according to the user base. To control the bias of data modeling, it is recommended that the minimum sample size be 100,000.

[0095] Furthermore, data from the experimental and control groups were collected after deployment, and preliminary data cleaning based on anomaly detection (such as filtering invalid data and malicious users) was performed. The optimization target indicators (target interaction data) before and after deployment were calculated.

[0096] For feature construction of experimental and control group samples, the standard procedure of feature engineering can be referred to.

[0097] Furthermore, users in the experimental and control groups are grouped based on user characteristics. This step is to prepare for the subsequent construction of user tags. Continuous features are binned into k equal parts based on frequency (k can be between 3 and 10 depending on the number of features), and all users are divided into n user groups (n can be between 50 and 200 depending on the number of samples).

[0098] Further construct user prediction labels. For example, for each experimental group sample, calculate the rate of change of its own target metric and the rate of change of the target metric of the user group to which the control group belongs, and construct user prediction labels.

[0099] Based on this, N user groups are identified using the constructed user prediction labels.

[0100] The embodiments provided in this application obtain P second sample user accounts and K third sample user accounts, wherein the second sample user accounts are accounts that received virtual resources during a second time period, and the third sample user accounts are accounts that did not receive virtual resources during the second time period, and K and P are both integers greater than 1; obtain P second sample user features corresponding to each of the P second sample user accounts and K third sample user features corresponding to each of the K third sample user accounts; obtain the adjustment values ​​generated when the second sample user accounts and third sample user accounts adjust the target interaction data during the second time period; calculate and process the adjustment values ​​to obtain P target sample features, wherein the target sample features are used to represent the degree of matching between the second sample user accounts and the target interaction data; based on the P target sample features, K third sample user features, and P second sample user features, determine N group features corresponding to each of the N user groups; use the N group features to obtain N user groups, achieving the purpose of automatically obtaining the corresponding user groups and improving the efficiency of obtaining user groups.

[0101] As an optional approach, the adjustment values ​​are calculated to obtain P target sample features, including:

[0102] S1, Repeat the following steps until P target sample features are obtained:

[0103] S2, determine the current second sample user account from P second sample user accounts;

[0104] S3, obtain the first adjustment value generated when the current second sample user account adjusts the target interaction data in the second time period, and the second adjustment value generated when the reference user group associated with the current user group to which the current second sample user account belongs adjusts the target interaction data in the second time period, wherein the current user group is a user group determined for the current second sample user account based on P features of the second sample user, and the reference user group is selected from the user group determined for the third sample user account based on K features of the third sample user;

[0105] S4, calculate and process the first adjustment value and the second adjustment value;

[0106] S5, after calculating and obtaining the target sample features corresponding to the current second sample user account, obtain the next second sample user account as the current second sample user account.

[0107] Optionally, in this embodiment, the first adjustment value generated when the current second sample user account adjusts the target interaction data within the second time period can be, but is not limited to, understood as the change rate of a single target interaction data of a single second sample user account within the second time period;

[0108] Optionally, in this embodiment, the second adjustment value generated when the reference user group associated with the current user group where the current second sample user account is located adjusts the target interaction data within the second time period can be, but is not limited to, understood as the change rate of the overall target interaction data of each sample user account in the corresponding user group of the user group where the above single second sample user account is located within the second time period;

[0109] It should be noted that for each second sample user account, calculate the change rate of its own target interaction data and the change rate of the overall target interaction data of the user group to which the corresponding third sample user account belongs, so as to calculate and generate the corresponding target sample feature.

[0110] For further illustration, optionally, for example, assume that the target sample feature is p, the first adjustment value is a, and the second adjustment value is b. p can be, but is not limited to, [(a - b) / b], or [(a + b) / b], or [(a - b) / a], etc.

[0111] For further illustration, optionally, for example, assume that the target sample feature is k, the first adjustment value is a, and the second adjustment value is b. Then, it can be, but is not limited to, first calculate the first adjustment value and the second adjustment value. Assume the calculation result is p, and then determine the target sample feature k based on the comparison between the calculation result and the sensitivity coefficient Q. Specifically as follows:

[0112] Step S1, obtain the calculation result p through the calculation formula p = [(a - b) / b];

[0113] Step S2, compare the calculation result p with the sensitivity coefficient Q to obtain a comparison result. Among them, the sensitivity coefficient Q can be taken between 0.01 - 0.1 according to business needs;

[0114] Step S3, determine the target sample feature k according to the comparison result. For example, if p >= Q, the target sample feature k represents a positive user 1; if p <= -Q, the target sample feature k represents a negative user -1; if -Q < p < Q, the target sample feature k represents a user with no influence 0; or, according to business needs, the multi-classification problem can be simplified into a binary classification problem. For example, if p >= Q, the target sample feature k represents a positive user 1; if p <= -Q, the target sample feature k represents a negative user -1.

[0115] The embodiments provided in this application involve repeating the following steps until P target sample features are obtained: determining the current second sample user account from P second sample user accounts; obtaining the first adjustment value generated when the current second sample user account adjusts the target interaction data in the second time period, and the second adjustment value generated when the reference user group associated with the current user group of the current second sample user account adjusts the target interaction data in the second time period, wherein the current user group is a user group determined based on P second sample user features for the current second sample user account, and the reference user group is selected from the user group determined based on K third sample user features for the third sample user account; calculating and processing the first adjustment value and the second adjustment value; and obtaining the target sample features corresponding to the current second sample user account, and then obtaining the next second sample user account as the current second sample user account, thereby achieving the purpose of automatically completing the calculation and acquisition of target sample features and improving the efficiency of target sample feature acquisition.

[0116] As an optional approach, based on P target sample features, K third sample user features, and P second sample user features, N group features corresponding to each of the N user groups are determined, including:

[0117] S1, calculate the information divergence of each of the P second sample user features relative to the P target sample features, where the information divergence is used to represent the degree of correlation between features;

[0118] S2, determine N group features based on multiple information divergences.

[0119] Optionally, in this embodiment, the information divergence can be, but is not limited to, KL divergence. Specifically, assuming P(x) are two probability distributions on the random variable Q(x), then in the case of discrete and continuous random variables, the definition of KL divergence can be as shown in the following formula (1):

[0120]

[0121]

[0122] Furthermore, in data mining applications, KL divergence measures the distance between two random distributions. When two random distributions are identical, their KL divergence is zero; as the difference between the two random distributions increases, their KL divergence also increases. It is often used to measure the degree of chaos and separability of feature variables relative to the target variable. In classification problems and tree models, KL divergence is frequently used to discretize continuous features and divide them into split points. This is also an important concept in this patent's application of this idea to practical scenarios.

[0123] Optionally, in this embodiment, the multiple information divergences may be, but are not limited to, P information divergences or more than P information divergences. This can be understood as not limiting the number or content of information divergences to correspond one-to-one with the P target sample features.

[0124] It should be noted that, in order to improve the accuracy of group feature determination, data mining is carried out by means of information divergence to measure the distance between two random distributions, and then the P target sample features are divided into several user groups with hierarchical progressive relationships.

[0125] To further illustrate, an alternative approach is to calculate the KL divergence of each second sample user feature with respect to the target sample feature, and then further select the n features (e.g., 3-5) that have the greatest impact on the target sample feature. At the same time, based on the KL divergence, find the optimal k split point (e.g., 1-3) corresponding to each second sample user feature.

[0126] Furthermore, based on the filtering features and corresponding split points obtained after KL divergence calculation, the entire user base can be stratified to obtain N layers of user groups, with each layer corresponding to a specific priority (such as weight calculation, feature labels, etc.).

[0127] Through the embodiments provided in this application, each of the P second sample user features is calculated, and multiple information divergences are calculated relative to the P target sample features, wherein the information divergence is used to represent the degree of correlation between features; based on the multiple information divergences, N group features are determined, thereby achieving the goal of accurately determining the corresponding group features and improving the accuracy of group feature determination.

[0128] As an optional approach, when the second sample user features include both categorical and continuous features, the information divergence of each of the P second sample user features relative to the P target sample features is calculated, including at least one of the following:

[0129] S1, calculate the first information divergence of each classification feature in the P second sample user features relative to the P target sample features, where the classification features are used to determine the user group to which each second sample user account belongs.

[0130] S2, calculate the P second information divergences of each continuous feature among the P second sample user features relative to the P target sample features, where the continuous features are used to represent the interaction data generated by the second sample user accounts in the second time period.

[0131] Optionally, in this embodiment, the classification features may refer to, but are not limited to, features that can be used as reference information when performing classification operations, such as the attribute information of user accounts, gender to classify user accounts as male / female, age to classify user accounts as age groups, etc.

[0132] Optionally, in this embodiment, the continuous feature may, but is not limited to, represent multiple segments or multiple interactive data with a continuous relationship, wherein the continuous data may, but is not limited to, indicate that the time interval between the aforementioned multiple segments or multiple interactive data is less than or equal to a target interval threshold.

[0133] It should be noted that when calculating information divergence using only categorical features, the ranking information related to the categorical features can be determined based on the calculation results, but is not limited to this. Similarly, when calculating information divergence using only continuous features, the ranking information related to the continuous features can be determined based on the calculation results, but is not limited to this. However, when calculating information divergence by considering both categorical and continuous features, the maximum or minimum calculation result can be taken to determine the corresponding ranking information. Alternatively, when calculating information divergence by considering both categorical and continuous features, pre-determined calculation weights can be used to integrate the calculation of categorical and continuous features before calculating information divergence, and finally, the relevant ranking information can be determined based on the calculation results.

[0134] To illustrate further, one could first calculate the KL divergence of each categorical feature with respect to the target variable; then calculate the KL divergence of each continuous feature with respect to the target variable. Specifically, this could involve iterating through each value of a continuous feature as a split point, calculating the KL divergence for each value, and selecting the value with the lowest KL divergence as the split point. Further, for all features, determine the feature with the lowest KL divergence value as the first feature; then, based on the split of the first feature, remove features that have already appeared, and repeat this process w times (e.g., 3-5 times). Finally, after the execution completion condition is met, obtain the top n features and their corresponding split points.

[0135] Based on this, according to the filtering features and corresponding split points obtained after KL divergence calculation, the entire user base can be stratified to obtain N layers of user groups, with each layer of users corresponding to a specific priority.

[0136] Finally, in actual use, based on the results of user segmentation, the campaign is prioritized for high-priority user groups, and the volume is increased accordingly.

[0137] Through the embodiments provided in this application, each categorical feature among the P second sample user features is calculated with respect to the P target sample features, and P first information divergences are calculated, wherein the categorical features are used to determine the user group to which each second sample user account belongs; each continuous feature among the P second sample user features is calculated with respect to the P target sample features, wherein the continuous features are used to represent the interaction data generated by the second sample user account in the second time period, thereby achieving the purpose of using more comprehensive types of features to calculate the corresponding information divergences and realizing the effect of improving the comprehensiveness of information divergence calculation.

[0138] As an optional approach, virtual resources are delivered to user accounts according to the delivery instructions corresponding to the target user group, including at least one of the following:

[0139] S1, Deliver the target quantity of virtual resources corresponding to the delivery instruction information to the user account;

[0140] S2, deliver virtual resources to user accounts according to the delivery frequency corresponding to the delivery instruction information;

[0141] S3 delivers virtual resources to user accounts according to the delivery type corresponding to the delivery instruction information.

[0142] Optionally, in this embodiment, the delivery instruction information may be used, but is not limited to, to indicate the delivery method of virtual resources. For example, virtual resources may be delivered to user accounts at a fixed delivery frequency, and the number of virtual resources delivered each time may be changed in real time based on feedback data. If the feedback data does not meet the requirements, the delivery type of virtual resources may be changed.

[0143] It should be noted that the virtual resources are delivered to user accounts in accordance with the target quantity and / or delivery frequency and / or delivery type corresponding to the delivery instruction information.

[0144] To further illustrate, options include delivering virtual resources (such as advertisements) to target user accounts at a frequency of once per day, with the number of virtual resources (such as playback duration) delivered each time fixed at 5 seconds, and setting the delivery type of the virtual resources to occur during the waiting response process of the corresponding application running in the target user account.

[0145] The embodiments provided in this application deliver a target number of virtual resources corresponding to the delivery instruction information to a user account; deliver virtual resources to a user account according to the delivery frequency corresponding to the delivery instruction information; and deliver virtual resources to a user account according to the delivery type corresponding to the delivery instruction information. This achieves the purpose of flexibly configuring the delivery method of virtual resources and improves the flexibility of virtual resource delivery.

[0146] As an optional approach, for ease of understanding, the implementation of the above virtual resource delivery method is illustrated using a user operation scenario, as follows:

[0147] In actual operation, due to limitations in resource allocation or considerations to reduce user harassment, products need to target specific user groups that meet certain conditions to maximize the return on investment with limited resources. At this time, the business often has an optimization goal, such as increasing purchase frequency (e-commerce), increasing reading time (information flow products), increasing click-through rate (advertising), etc.

[0148] In practice, product managers often rely on their personal experience to determine the target user groups for advertising. They typically provide rules for identifying user groups to pinpoint the desired audience. However, experience shows that decisions based on experience are often unsatisfactory. Therefore, it's necessary to explore data-driven and automated methods that don't depend on human experience to complete this process, improving operational efficiency and product effectiveness. The implementation steps are as follows: Figure 5 As shown:

[0149] Step S502: Determine the metrics for the optimization goals. The corresponding optimization goals will vary depending on the product and business type, such as purchase frequency (e-commerce), reading time (information flow products), click-through rate (ads), etc.

[0150] Step S504: Strategies or operational activities are deployed to a subset of random users, while another subset of random users with the same attributes are not deployed as a control group. The purpose of this stage is to prepare for data collection. The following pre-deployment strategies can be adopted based on the user base: experimental group: 1% of users are randomly selected for deployment; control group: 1% of users are randomly selected and not deployed. The user ratio can be determined according to the user base. To control data modeling bias, a minimum sample size of 100,000 is recommended.

[0151] Step S506: Collect data from the experimental and control groups after deployment, perform preliminary data cleaning based on anomaly detection (such as filtering invalid data and malicious users), and calculate the optimization target indicators before and after deployment.

[0152] Step S508: Feature construction is performed on the experimental and control group samples, which can be referred to the standard procedure of feature engineering.

[0153] Step S510: Based on user characteristics, users in the experimental and control groups are grouped. The purpose of this step is to prepare for the subsequent construction of user tags. Continuous features are binned into k equal parts based on frequency (k can be between 3 and 10 depending on the number of features), and all users are divided into n user groups (n can be between 50 and 200 depending on the number of samples).

[0154] Step S512: For each experimental group sample, calculate the rate of change of its own target metric and the rate of change of the target metric of the user group to which the control group belongs, and construct user prediction labels. Specific steps can be found below:

[0155] Let p = (Change rate of a single user in the experimental group - Change rate of the user group to which the control group belongs) / Change rate of the user group to which the control group belongs;

[0156] 1 represents a positive user (p>=α),

[0157] -1 represents a negative user (p <= -α),

[0158] 0 represents no affected users (-α) <p<α),

[0159] α is the sensitivity coefficient, which can be set between 0.01 and 0.1 depending on business needs.

[0160] Based on business needs, the multi-class classification problem can be simplified into a binary classification problem:

[0161] 1 represents a positive user (p>0),

[0162] 0 represents a negative user (p<=0).

[0163] Step S514: By calculating the KL divergence of each feature variable with respect to the target variable, select the n features (3-5 recommended) that have the greatest impact on the target variable. At the same time, based on the KL divergence, find the optimal k-split points corresponding to each feature variable (1-3 recommended, see the following for details).

[0164] 1) Calculate the KL divergence of each categorical feature with respect to the target variable;

[0165] 2) Calculate the KL divergence of each continuous feature with respect to the target variable: traverse each value of the continuous feature as a split point, calculate the KL divergence for each value, and take the value with the lowest KL divergence as the split point.

[0166] 3) For all features, determine the feature with the lowest KL divergence value and use it as the first feature;

[0167] 4) Based on the division of the first feature, continue steps 1-3 (remove features that have appeared before), and execute them a total of n times (3-5 times is recommended);

[0168] 5) Obtain the features of the top n and the corresponding split points.

[0169] Step S516: Based on the filtering features and corresponding split points obtained after KL divergence calculation, the entire user base can be layered to obtain n layers of user groups, with each layer of users corresponding to a specific priority.

[0170] Step S518: Based on the results of user segmentation, prioritize the deployment to high-priority user groups and gradually increase the volume accordingly.

[0171] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0172] According to another aspect of the present invention, a virtual resource delivery apparatus for implementing the above-described virtual resource delivery method is also provided. For example... Figure 6 As shown, the device includes:

[0173] The first acquisition unit 602 is used to acquire a resource delivery request, wherein the resource delivery request is used to request the delivery of virtual resources associated with the target application to the user account, the virtual resources are used to provide a reference for the user account to adjust the target interaction data, and the target interaction data is the data generated when the user account performs a target type interaction operation on the target application;

[0174] The second acquisition unit 604 is used to respond to resource delivery requests and acquire the target user characteristics corresponding to the user account.

[0175] The first determining unit 606 is used to determine the target user group to which the user account belongs among N user groups corresponding to the target type based on the characteristics of the target user, where N is an integer greater than or equal to 1;

[0176] Delivery unit 608 is used to deliver virtual resources to user accounts according to the delivery instructions corresponding to the target user group.

[0177] Optionally, in this embodiment, the aforementioned virtual resource delivery device can be applied, but is not limited to, in scenarios where user accounts are segmented and operated in a refined manner to improve the delivery efficiency and actual operational efficiency of virtual resources. For example, by combining the target type corresponding to specific business needs, the device can select the most matching target user group for the user account to be delivered to, and then deliver virtual resources to the user account to be delivered to according to the resource delivery method corresponding to the target user group. This achieves refined user segmentation around specific business needs, makes the best use of virtual resources, reduces unnecessary waste of virtual resources, and thus improves the delivery efficiency of virtual resources.

[0178] Optionally, in this embodiment, the user account may be, but is not limited to, the account of the target application, or may be, but is not limited to, the account of other applications. For example, virtual resources of application A may be delivered to the account of application A, or virtual resources of application B may be delivered to the account of application A.

[0179] Optionally, in this embodiment, virtual resources may be, but are not limited to, virtual advertisements, virtual services, virtual currency, and other resources used to promote the target application. For example, advertising information corresponding to the target application may be delivered to a user account, or a virtual customer service corresponding to the target application may be provided to a user account, or an operation interface for virtual tasks may be provided to a user account, and after the user account completes the corresponding virtual task (such as logging into the target application), a corresponding amount of virtual currency may be transferred to the user account.

[0180] Optionally, in this embodiment, the target interaction data is the data generated when a user account performs a target type of interaction operation on the target application. The interaction operation can be, but is not limited to, various operation types, such as click type, like type, comment type, subscription type, reading type, virtual resource transfer type, etc. The target application in different application scenarios can flexibly select the target type corresponding to actual needs. For example, assuming the target application is a reading application, the target type can be, but is not limited to, determined as the reading type, thereby determining the virtual resources allocated to the user account based on the data generated when the user account performs a reading operation on the reading application. Similarly, assuming the target application is a shopping application, the target type can be, but is not limited to, determined as the resource transfer type, thereby determining the virtual resources allocated to the user account based on the data generated when the user account performs a resource transfer operation (such as consumption) on the shopping application.

[0181] Optionally, in this embodiment, the use of virtual resources to provide a reference for adjusting target interaction data for user accounts can be understood, but is not limited to, as the virtual resources can have a certain impact on the adjustment of target interaction data for user accounts, or play a role in promoting or guiding them. For example, the virtual resource is a target virtual task, and the target virtual task is used to guide the user account to complete the registration of the target application or to perform a certain number or frequency of operations in the target application. When the target virtual task is in a completed state, virtual items or virtual currency are transferred to the user account or the account associated with the user account in the target application, so as to promote the establishment of user account and improve the association relationship between the user account and the target application.

[0182] Optionally, in this embodiment, the user account's adjustment of the target interaction data may include, but is not limited to, at least one of the following: the user account increases the target interaction data, or the user account decreases the target interaction data. Specifically, when the target interaction data is positive interaction data (such as data triggered by interactive behaviors that benefit the target application, such as liking, commenting, tipping, and shopping), virtual resources are deployed to promote the user account's increase in the target interaction data; conversely, when the target interaction data is negative interaction data (such as data triggered by interactive behaviors that harm the target application, such as reporting, giving bad reviews, and uninstalling), virtual resources are deployed to promote the user account's decrease in the target interaction data.

[0183] Optionally, in this embodiment, the target user features may be used, but are not limited to, to represent the account characteristics of the user account, such as the user account's behavioral data, the user account's attribute information, etc. The behavioral data may include, but is not limited to, data generated by the user account's actions performed on the target application or other applications, such as resource transfer data, interactive operation data, etc.; the attribute information may include, but is not limited to, the user account's account attribute information, or the user attribute information associated with the user account, such as account level, user identity identifier, user gender, user age, etc.

[0184] Optionally, in this embodiment, the N user groups corresponding to the target type can be obtained in advance, but not limited to, before obtaining the resource delivery request, or can be understood as first obtaining the user group sets corresponding to different types, assigning a corresponding target tag to each user group, and then finding the target tag that matches the corresponding account characteristics in the user group set, thereby determining the N user groups corresponding to the target tag.

[0185] It should be noted that by targeting virtual resources through interactive data and selecting target groups from user groups corresponding to the target type, virtual resources are delivered to specific user groups in a specific direction. This improves the matching degree between targeted virtual resources and user groups, thereby achieving efficient delivery of virtual resources.

[0186] For specific implementation examples, please refer to the example shown in the virtual resource delivery device described above. These examples will not be repeated here.

[0187] The embodiments provided in this application obtain a resource delivery request, wherein the resource delivery request is used to request the delivery of virtual resources associated with a target application to a user account. The virtual resources are used to provide a reference for the user account to adjust target interaction data, and the target interaction data is the data generated when the user account performs a target type interaction operation on the target application. In response to the resource delivery request, the target user characteristics corresponding to the user account are obtained. Based on the target user characteristics, the target user group to which the user account belongs is determined from N user groups corresponding to the target type, where N is an integer greater than or equal to 1. Virtual resources are delivered to the user account according to the delivery instruction information corresponding to the target user group. The corresponding virtual resources are delivered in a targeted manner through the target interaction data, and the method of selecting a group to be delivered from the user group corresponding to the target type is used to ensure that the virtual resources are delivered to a specific user group in a specific direction. This achieves the technical objective of improving the matching degree between the delivered virtual resources and the user group, thereby realizing the technical effect of improving the accuracy of virtual resource delivery.

[0188] As an alternative solution, such as Figure 7 As shown, the first determining unit 606 includes:

[0189] The first acquisition module 702 is used to acquire N group features corresponding to each user group in the N user groups;

[0190] The first determining module 704 is used to determine the target group feature among N group features, wherein the feature similarity between the target group feature and the target user feature is greater than or equal to a first threshold.

[0191] The second determining module 706 is used to determine the user group corresponding to the target group characteristics as the target user group.

[0192] For specific implementation examples, please refer to the examples shown in the virtual resource deployment method above. These examples will not be repeated here.

[0193] As an optional solution, the first determining module 704 includes:

[0194] The acquisition submodule is used to acquire the calculated weight of each user feature in the target user features when the target user features include at least two types of user features, wherein the calculated weight is associated with the target type;

[0195] The first calculation submodule is used to integrate and calculate the two types of user features based on the calculation weights to obtain the target features;

[0196] The determination submodule is used to identify group features among N group features that have a feature similarity to the target feature greater than or equal to a second threshold.

[0197] For specific implementation examples, please refer to the examples shown in the virtual resource deployment method above. These examples will not be repeated here.

[0198] As an alternative solution, such as Figure 8 As shown, it includes:

[0199] The third acquisition unit 802 is used to acquire M first sample user accounts before acquiring the resource delivery request, wherein the first sample user accounts are accounts that have been delivered virtual resources in the first time period, and M is an integer greater than 1.

[0200] The fourth acquisition unit 804 is used to acquire the M first sample user features corresponding to each sample user account in the M first sample user accounts before acquiring the resource delivery request.

[0201] The fifth acquisition unit 806 is used to acquire N user groups using the characteristics of M first sample users before acquiring the resource delivery request.

[0202] For specific implementation examples, please refer to the examples shown in the virtual resource deployment method above. These examples will not be repeated here.

[0203] As an alternative solution, such as Figure 9 As shown, it includes:

[0204] The sixth acquisition unit 902 is used to acquire P second sample user accounts and K third sample user accounts before acquiring the resource delivery request. The second sample user accounts are accounts that have been delivered virtual resources in the second time period, and the third sample user accounts are accounts that have not been delivered virtual resources in the second time period. K and P are both integers greater than 1.

[0205] The seventh acquisition unit 904 is used to acquire, before acquiring the resource delivery request, the P second sample user features corresponding to each sample user account in the P second sample user accounts, and the K third sample user features corresponding to each sample user account in the K third sample user accounts.

[0206] The eighth acquisition unit 906 is used to acquire the adjustment values ​​generated by the second sample user account and the third sample user account when adjusting the target interaction data in the second time period before acquiring the resource delivery request.

[0207] The calculation unit 908 is used to calculate and process the adjustment value before obtaining the resource delivery request to obtain P target sample features, wherein the target sample features are used to represent the degree of matching between the second sample user account and the target interaction data.

[0208] The second determining unit 910 is used to determine, before obtaining the resource delivery request, N group features corresponding to each user group in the N user groups based on P target sample features, K third sample user features, and P second sample user features.

[0209] The ninth acquisition unit 912 is used to acquire N user groups using N group characteristics before acquiring resource delivery requests.

[0210] For specific implementation examples, please refer to the examples shown in the virtual resource deployment method above. These examples will not be repeated here.

[0211] As an optional solution, computing unit 908 includes:

[0212] The repeat module is used to repeatedly execute the following steps until P target sample features are obtained:

[0213] The third determination module is used to determine the current second sample user account from P second sample user accounts;

[0214] The second acquisition module is used to acquire the first adjustment value generated when the current second sample user account adjusts the target interaction data in the second time period, and the second adjustment value generated when the reference user group associated with the current user group to which the current second sample user account belongs adjusts the target interaction data in the second time period. The current user group is a user group determined for the current second sample user account based on P features of the current second sample user, and the reference user group is selected from the user group determined for the third sample user account based on K features of the third sample user.

[0215] The first calculation module is used to calculate and process the first adjustment value and the second adjustment value;

[0216] The third acquisition module is used to acquire the next second sample user account as the current second sample user account after calculating and obtaining the target sample features corresponding to the current second sample user account.

[0217] For specific implementation examples, please refer to the examples shown in the virtual resource deployment method above. These examples will not be repeated here.

[0218] As an optional solution, computing unit 908 includes:

[0219] The second calculation module is used to calculate the information divergence of each of the P second sample user features relative to the P target sample features, where the information divergence is used to represent the degree of correlation between features.

[0220] The fourth determination module is used to determine the characteristics of N groups based on multiple information divergences.

[0221] For specific implementation examples, please refer to the examples shown in the virtual resource deployment method above. These examples will not be repeated here.

[0222] As an optional approach, when the second sample user features include both categorical and continuous features, the second calculation module includes at least one of the following:

[0223] The second calculation submodule is used to calculate the first information divergence of each classification feature among the P second sample user features relative to the P target sample features, wherein the classification features are used to determine the user group to which each second sample user account belongs.

[0224] The third calculation submodule is used to calculate the P second information divergences of each continuous feature among the P second sample user features relative to the P target sample features, wherein the continuous features are used to represent the interaction data generated by the second sample user accounts in the second time period.

[0225] For specific implementation examples, please refer to the examples shown in the virtual resource deployment method above. These examples will not be repeated here.

[0226] As an optional solution, delivery unit 608 includes at least one of the following:

[0227] The first delivery module is used to deliver the target number of virtual resources corresponding to the delivery instruction information to user accounts;

[0228] The second delivery module is used to deliver virtual resources to user accounts according to the delivery frequency corresponding to the delivery instruction information;

[0229] The third delivery module is used to deliver virtual resources to user accounts according to the delivery type corresponding to the delivery instruction information.

[0230] For specific implementation examples, please refer to the examples shown in the virtual resource deployment method above. These examples will not be repeated here.

[0231] According to another aspect of the present invention, an electronic device for implementing the above-described virtual resource delivery method is also provided, such as... Figure 10 As shown, the electronic device includes a memory 1002 and a processor 1004. The memory 1002 stores a computer program, and the processor 1004 is configured to execute the steps of any of the above method embodiments via the computer program.

[0232] Optionally, in this embodiment, the aforementioned electronic device may be located in at least one of a plurality of network devices in a computer network.

[0233] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0234] S1, Obtain resource delivery request, wherein the resource delivery request is used to request the delivery of virtual resources associated with the target application to the user account. The virtual resources are used to provide a reference for the user account to adjust the target interaction data. The target interaction data is the data generated when the user account performs a target type interaction operation on the target application.

[0235] S2 responds to resource delivery requests and obtains the target user characteristics corresponding to the user account;

[0236] S3, based on the characteristics of the target user, determine the target user group to which the user account belongs from the N user groups corresponding to the target type, where N is an integer greater than or equal to 1;

[0237] S4 delivers virtual resources to user accounts according to the delivery instructions corresponding to the target user group.

[0238] Alternatively, as those skilled in the art will understand, Figure 10 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones (such as Android phones, iOS phones, etc.), tablets, PDAs, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 10 This does not limit the structure of the aforementioned electronic devices. For example, the electronic device may also include components that are more... Figure 10 The more or fewer components shown (such as network interfaces, etc.), or having the same Figure 10 The different configurations shown.

[0239] The memory 1002 can be used to store software programs and modules, such as the program instructions / modules corresponding to the virtual resource delivery method and apparatus in this embodiment of the invention. The processor 1004 executes various functional applications and data processing by running the software programs and modules stored in the memory 1002, thereby realizing the aforementioned virtual resource delivery method. The memory 1002 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 1002 may further include memory remotely located relative to the processor 1004, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. Specifically, the memory 1002 may be used, but is not limited to, to store information such as resource delivery requests, target user characteristics, target user groups, and delivery instruction information. As an example, such as... Figure 10 As shown, the memory 1002 may include, but is not limited to, the first acquisition unit 602, the second acquisition unit 604, the first determination unit 606, and the delivery unit 608 of the virtual resource delivery device. Furthermore, it may include, but is not limited to, other module units of the virtual resource delivery device, which will not be elaborated upon in this example.

[0240] Optionally, the transmission device 1006 described above is used to receive or send data via a network. Specific examples of the network described above may include wired networks and wireless networks. In one example, the transmission device 1006 includes a Network Interface Controller (NIC), which can be connected to other network devices and routers via a network cable to communicate with the Internet or a local area network. In another example, the transmission device 1006 is a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0241] In addition, the aforementioned electronic device also includes: a display 1008 for displaying information such as the resource delivery request, target user characteristics, target user group, and delivery instruction information; and a connection bus 1010 for connecting the various module components in the aforementioned electronic device.

[0242] In other embodiments, the aforementioned terminal device or server can be a node in a distributed system, wherein the distributed system can be a blockchain system, which is a distributed system formed by connecting multiple nodes through network communication. The nodes can form a peer-to-peer (P2P) network, and any form of computing device, such as a server, terminal, or other electronic device, can become a node in the blockchain system by joining this peer-to-peer network.

[0243] According to one aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions to cause the computer device to perform the described XX method, wherein the computer program is configured to perform the steps of any of the method embodiments described above when running.

[0244] Optionally, in this embodiment, the computer-readable storage medium described above may be configured to store a computer program for performing the following steps:

[0245] S1, Obtain resource delivery request, wherein the resource delivery request is used to request the delivery of virtual resources associated with the target application to the user account. The virtual resources are used to provide a reference for the user account to adjust the target interaction data. The target interaction data is the data generated when the user account performs a target type interaction operation on the target application.

[0246] S2 responds to resource delivery requests and obtains the target user characteristics corresponding to the user account;

[0247] S3, based on the characteristics of the target user, determine the target user group to which the user account belongs from the N user groups corresponding to the target type, where N is an integer greater than or equal to 1;

[0248] S4 delivers virtual resources to user accounts according to the delivery instructions corresponding to the target user group.

[0249] Optionally, in this embodiment, those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0250] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0251] If the integrated units in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in the aforementioned computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0252] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0253] In the several embodiments provided in this application, it should be understood that the disclosed client can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between units or modules, and may be electrical or other forms.

[0254] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0255] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0256] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for delivering virtual resources, characterized in that, include: Obtain a resource delivery request, wherein the resource delivery request is used to request the delivery of virtual resources associated with the target application to the user account, the virtual resources are used to provide a reference for the user account to adjust the target interaction data, and the target interaction data is the data generated by the user account when performing a target type interaction operation on the target application; In response to the resource delivery request, obtain the target user characteristics corresponding to the user account; Based on the target user characteristics, the target user group to which the user account belongs is determined from the N user groups corresponding to the target type, where N is an integer greater than or equal to 1; According to the delivery instructions corresponding to the target user group, the virtual resources are delivered to the user account; Before obtaining the resource delivery request, the following steps are included: Obtain P second sample user accounts and K third sample user accounts, wherein the second sample user accounts are accounts that were given the virtual resources during the second time period, and the third sample user accounts are accounts that were not given the virtual resources during the second time period, and K and P are both integers greater than 1; Obtain P second sample user features corresponding to each sample user account in the P second sample user accounts, and K third sample user features corresponding to each sample user account in the K third sample user accounts; The target interaction data of the second sample user account and the target interaction data of the third sample user account are obtained and adjusted during the second time period. The adjustment value is used to represent the amount of change of the target interaction data of the second sample user account and the amount of change of the target interaction data of the third sample user account during the second time period. The adjustment value is calculated to obtain P target sample features, wherein the target sample features are used to represent the degree of matching between the second sample user account and the target interaction data; The step of calculating and processing the adjustment value to obtain P target sample features includes: calculating the adjustment value of each second sample user account with the overall adjustment value of the user group to which the corresponding third sample user account belongs, and obtaining the calculation result; and determining the target sample features by comparing the calculation result with a preset threshold. Based on the P target sample features, the K third sample user features, and the P second sample user features, determine the N group features corresponding to each user group in the N user groups; The N user groups are obtained using the N group features.

2. The method according to claim 1, characterized in that, The step of determining the target user group to which the user account belongs from the N user groups corresponding to the target type based on the target user characteristics includes: Obtain N group features corresponding to each of the N user groups; Among the N group features, a target group feature is determined, wherein the feature similarity between the target group feature and the target user feature is greater than or equal to a first threshold. The user group corresponding to the target group characteristics is determined as the target user group.

3. The method according to claim 2, characterized in that, Determining the target group features from the N group features includes: When the target user features include at least two types of user features, the calculated weight of each user feature in the target user features is obtained, wherein the calculated weight is associated with the target type; The two types of user features are integrated and calculated based on the calculated weights to obtain the target features; Among the N group features, group features with a feature similarity to the target feature greater than or equal to a second threshold are identified.

4. The method according to any one of claims 1 to 3, characterized in that, Before obtaining the resource delivery request, the following steps are included: Obtain M first sample user accounts, where the first sample user accounts are accounts that were given the virtual resources within a first time period, and M is an integer greater than 1; Obtain the M first sample user features corresponding to each of the M first sample user accounts; The N user groups are obtained using the features of the M first sample users.

5. The method according to claim 1, characterized in that, The calculation and processing of the adjusted value to obtain P target sample features includes: Repeat the following steps until the P target sample features are obtained: The current second sample user account is determined from the P second sample user accounts; The method obtains a first adjustment value generated when the current second sample user account adjusts the target interaction data during the second time period, and a second adjustment value generated when a reference user group associated with the current user group to which the current second sample user account belongs adjusts the target interaction data during the second time period. The current user group is a user group determined based on the P features of the current second sample user account, and the reference user group is selected from the user groups determined based on the K features of the third sample user account. The first adjustment value is used to represent the rate of change of a single target interaction data of a single second sample user account during the second time period, and the second adjustment value is used to represent the rate of change of the overall target interaction data of each sample user account in the user group to which the single second sample user account belongs during the second time period. The first adjustment value and the second adjustment value are calculated and processed; If the target sample features corresponding to the current second sample user account are obtained through calculation, the next second sample user account is obtained as the current second sample user account.

6. The method according to claim 1, characterized in that, The step of determining N group features corresponding to each of the N user groups based on the P target sample features, the K third sample user features, and the P second sample user features includes: Calculate the correlation between each of the P second sample user features and each of the P target sample features to obtain multiple information divergences. The N group features are determined based on the multiple information divergences.

7. The method according to claim 6, characterized in that, When the second sample user features include categorical features and continuous features, the correlation between each of the P second sample user features and each of the P target sample features is calculated to obtain multiple information divergences, including at least one of the following: Calculate the correlation between each classification feature in the P second sample user features and each target sample feature in the P target sample features to obtain P first information divergences, wherein the classification features are used to determine the user group to which each second sample user account belongs; Calculate the correlation between each continuous feature in the P second sample user features and each target sample feature in the P target sample features to obtain P second information divergences, wherein the continuous features are used to represent the interaction data generated by the second sample user account in the second time period.

8. The method according to any one of claims 1 to 3, 4, or 5 to 7, characterized in that, The step of delivering the virtual resources to the user account according to the delivery instruction information corresponding to the target user group includes at least one of the following: Deliver the target quantity of the virtual resources corresponding to the delivery instruction information to the user account; The virtual resources are delivered to the user account according to the delivery frequency corresponding to the delivery instruction information; The virtual resources are delivered to the user account according to the delivery type corresponding to the delivery instruction information.

9. A virtual resource delivery device, characterized in that, include: The first acquisition unit is used to acquire a resource delivery request, wherein the resource delivery request is used to request the delivery of virtual resources associated with the target application to the user account, the virtual resources are used to provide a reference for the user account to adjust the target interaction data, and the target interaction data is the data generated by the user account when performing a target type interaction operation on the target application; The second acquisition unit is used to respond to the resource delivery request and acquire the target user characteristics corresponding to the user account. The first determining unit is used to determine the target user group to which the user account belongs from among the N user groups corresponding to the target type based on the target user characteristics, where N is an integer greater than or equal to 1; The delivery unit is used to deliver the virtual resources to the user account according to the delivery instruction information corresponding to the target user group; The sixth acquisition unit is used to acquire P second sample user accounts and K third sample user accounts before acquiring the resource delivery request, wherein the second sample user accounts are accounts that have been delivered the virtual resources during the second time period, and the third sample user accounts are accounts that have not been delivered the virtual resources during the second time period, and K and P are both integers greater than 1. The seventh acquisition unit is used to acquire, before acquiring the resource delivery request, P second sample user features corresponding to each sample user account in the P second sample user accounts, and K third sample user features corresponding to each sample user account in the K third sample user accounts. The eighth acquisition unit is used to acquire the target interaction data of the second sample user account and the target interaction data of the third sample user account before acquiring the resource delivery request, and the adjustment value generated when the target interaction data of the second sample user account is adjusted during the second time period, wherein the adjustment value is used to represent the amount of change of the target interaction data of the second sample user account and the amount of change of the target interaction data of the third sample user account during the second time period. The calculation unit is used to calculate and process the adjustment value before obtaining the resource delivery request to obtain P target sample features, wherein the target sample features are used to represent the degree of matching between the second sample user account and the target interaction data; The calculation unit is further configured to calculate the adjustment value of each second sample user account and the overall adjustment value of the user group to which the corresponding third sample user account belongs, to obtain a calculation result; and to determine the target sample features by comparing the calculation result with a preset threshold. The second determining unit is used to determine, before obtaining the resource delivery request, N group features corresponding to each user group in the N user groups, based on the P target sample features, the K third sample user features, and the P second sample user features. The ninth acquisition unit is used to acquire the N user groups using the N group characteristics before acquiring the resource delivery request.

10. The apparatus according to claim 9, characterized in that, The first determining unit includes: The first acquisition module is used to acquire N group features corresponding to each of the N user groups; The first determining module is used to determine the target group feature among the N group features, wherein the feature similarity between the target group feature and the target user feature is greater than or equal to a first threshold. The second determining module is used to determine the user group corresponding to the target group feature as the target user group.

11. The apparatus according to claim 10, characterized in that, The first determining module includes: The acquisition submodule is used to acquire the calculated weight of each user feature in the target user features when the target user features include at least two types of user features, wherein the calculated weight is associated with the target type; The first calculation submodule is used to integrate and calculate the two types of user features based on the calculation weights to obtain the target features; A determination submodule is used to identify, among the N group features, group features whose feature similarity to the target feature is greater than or equal to a second threshold.

12. The apparatus according to any one of claims 9 to 11, characterized in that, include: The third acquisition unit is used to acquire M first sample user accounts before acquiring the resource delivery request, wherein the first sample user accounts are accounts that have been delivered the virtual resources in the first time period, and M is an integer greater than 1. The fourth acquisition unit is used to acquire M first sample user features corresponding to each sample user account in the M first sample user accounts before acquiring the resource delivery request; The fifth acquisition unit is used to acquire the N user groups using the characteristics of the M first sample users before acquiring the resource delivery request.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the method described in any one of claims 1 to 8.

14. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the method described in any one of claims 1 to 8 through the computer program.

Images