Virtual resource allocation method, device, equipment and storage medium

Abstract

The embodiments of the present application disclose a virtual resource allocation method, apparatus, device, and storage medium. The method includes: obtaining a target dual variable corresponding to the current visiting user based on target attribute information of the current visiting user so that the corresponding dual function of the optimization problem obtains a first target value; the optimization problem is used to decide the virtual resources allocated to the user; the target dual variable is predicted based on historical time series data within a first historical time period; the historical time series data includes a historical dual variable sequence; the historical dual variable sequence includes multiple historical dual variables within the first historical time period that are related to the virtual resource allocation within the second historical time period and are arranged in chronological order; allocating target virtual resources to the current visiting user based on the target dual variable and target-related parameters of the current visiting user under at least one virtual resource; accurately grasping the user's virtual resource allocation trend through time series prediction, and improving the accuracy of virtual resource allocation.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a virtual resource allocation method, apparatus, device and storage medium. Background Art

[0002] In the field of marketing, optimizing resource allocation to maximize revenue has always been a key focus for businesses. Traditional online operations research solutions primarily employ linear programming models, leveraging dual solutions asynchronously to achieve online allocation of benefits. However, in practical applications, this approach has gradually exposed a series of problems. In particular, faced with complex and volatile market environments and user demands, linear programming models struggle to cope with multiple constraints, resulting in a complex and inefficient solution process. Summary of the Invention

[0003] The embodiments of the present application provide a virtual resource allocation method, apparatus, device, and storage medium. Through time series prediction, the target dual variables required for future virtual resource allocation are predicted in advance based on historical time series data within a first historical time period. The above-mentioned historical time series data includes a historical dual variable sequence, that is, the historical time series data records the virtual resource allocation situation and the corresponding dual variable values within a past period of time (the first historical time period), accurately grasps user needs and virtual resource allocation trends, provides strong support for current resource allocation, helps to improve the predictability and flexibility of virtual resource allocation, avoids the problem of problem solution deviation caused by the asynchronous use of dual solutions assuming the consistent distribution of adjacent samples in related technologies, resulting in efficiency loss, and improves the accuracy and maximization effect of operational solutions in the virtual resource allocation process. The above-mentioned technical solutions are as follows:

[0004] In a first aspect, an embodiment of the present application provides a virtual resource allocation method, comprising:

[0005] A target dual variable corresponding to the currently visiting user is obtained based on the target attribute information of the currently visiting user; the target dual variable is an independent variable that enables the dual function corresponding to the optimization problem to obtain a first target value; the optimization problem is used to decide on the virtual resources allocated to the user; the target dual variable is predicted based on historical time series data within a first historical time period; the first historical time period includes multiple different second historical time periods, the historical time series data includes a historical dual variable sequence, and the historical dual variable sequence includes multiple historical dual variables related to the virtual resource allocation within the second historical time period, which are arranged in chronological order;

[0006] A target virtual resource is allocated to the current visiting user based on the target dual variable and the target-related parameters of the current visiting user under at least one virtual resource.

[0007] In a possible implementation, the method further includes:

[0008] Obtain historical time series data within the first historical time period;

[0009] Predicting a future dual variable sequence based on the historical time series data; the future dual variable sequence includes predicted dual variables that enable a dual function corresponding to a corresponding optimization problem to obtain a first objective value within a plurality of different future time periods; the time interval corresponding to the future time period is equal to the time interval corresponding to the second historical time period;

[0010] The above future dual variable sequence is stored in the database.

[0011] In one possible implementation, the historical time series data also includes at least one of the following data: a historical virtual resource cost sequence, a historical time feature sequence, and a historical traffic sequence within the first historical time period; obtaining the historical time series data within the first historical time period includes: obtaining historical data within the first historical time period; the historical data includes multiple historical dual variables and other relevant historical data related to the virtual resource allocation within the second historical time period; the other relevant historical data include at least one of the following: multiple historical virtual resource costs, historical time information, and historical traffic information corresponding to each of the second historical time periods; and preprocessing the historical data to obtain the historical time series data.

[0012] In a possible implementation, before predicting the future dual variable sequence based on the historical time series data, the method further includes: obtaining a target time series prediction request; the target time series prediction request carries a time series prediction constraint, and the time series prediction constraint includes that the total cost of virtual resources allocated to users in multiple different future time periods does not exceed a preset total cost; the method predicting the future dual variable sequence based on the historical time series data includes: responding to the target time series prediction request, predicting the future dual variable sequence based on the time series prediction constraint and the historical time series data.

[0013] In one possible implementation, the time series prediction constraint condition includes that the total cost of virtual resources allocated to users under the target constraint dimension in multiple different future time periods does not exceed a preset total cost; the target constraint dimension includes at least one of the following: a target user group, a target user access scenario;

[0014] The above-mentioned prediction of the future dual variable sequence based on the above-mentioned historical time series data includes:

[0015] In response to the target time series prediction request, the future dual variable sequence under the target constraint dimension is predicted based on the time series prediction constraints and the historical time series data under the target constraint dimension.

[0016] In one possible implementation, the above-mentioned prediction of the future dual variable sequence based on the above-mentioned historical time series data includes: inputting the above-mentioned historical time series data into a time series prediction model, and outputting the future dual variable sequence; the above-mentioned time series prediction model is trained based on sample time series data in the second time period of the dual variable sequence in multiple known first time periods; the time interval corresponding to the above-mentioned first time period is equal to the time interval corresponding to the above-mentioned second time period, and the above-mentioned first time period is the time period after the above-mentioned second time period.

[0017] In a possible implementation, the above-mentioned acquisition of historical time series data within the first historical time period includes: regularly acquiring historical time series data of historical visiting users belonging to the same constraint dimension within the first historical time period at preset time intervals; the above-mentioned constraint dimension includes user groups and / or user access scenarios; the above-mentioned historical time series data is updated as the above-mentioned first historical time period is updated; the above-mentioned prediction of future dual variable sequences based on the above-mentioned historical time series data includes: predicting the future dual variable sequences of the above-mentioned historical visiting users under the corresponding historical constraint dimensions based on the above-mentioned historical time series data of the historical visiting users belonging to the same constraint dimension; the above-mentioned storage of the above-mentioned future dual variable sequences in a database includes: associating the above-mentioned future dual variable sequences with the historical constraint dimension identifiers corresponding to the above-mentioned historical visiting users and storing them in the database.

[0018] In a possible implementation, the above-mentioned acquisition of the target dual variable corresponding to the current visiting user based on the target attribute information of the current visiting user includes: determining the target group to which the current visiting user belongs based on the target attribute information of the current visiting user; querying in the above-mentioned database based on the target group identifier corresponding to the above-mentioned target group and / or the target access scenario identifier corresponding to the above-mentioned current visiting user to obtain the target future dual variable sequence corresponding to the above-mentioned current visiting user; determining the target dual variable corresponding to the above-mentioned current visiting user based on the current access time of the above-mentioned current visiting user and the above-mentioned target future dual variable sequence.

[0019] In a possible implementation, the target virtual resource is allocated to the current visiting user based on the target dual variable and the target-related parameters of the current visiting user under at least one virtual resource, including: searching for the second target value on the decision optimization function corresponding to the dual function based on the target dual variable, the target-related parameters of the current visiting user under at least one virtual resource and the target virtual resource cost and at least one virtual resource type to obtain the target virtual resource type; the target virtual resource type is the virtual resource type corresponding to the second target value of the decision optimization function in the at least one virtual resource type when the current visiting user and the target dual variable are known; and the corresponding target virtual resource is allocated to the current visiting user according to the target virtual resource type.

[0020] In a possible implementation, before allocating the target virtual resource to the current access user based on the target dual variable and the target-related parameter of the current access user under at least one virtual resource, the method further includes:

[0021] Using machine learning technology, the target-related parameters of the current visiting user under at least one virtual resource are calculated based on the target user characteristics of the current visiting user; the target user characteristics include at least one of the following: target attribute information, target transaction frequency, historical virtual resource allocation and related parameter information.

[0022] In one possible implementation, the above method also includes: constructing the above optimization problem based on the relevant parameters of the user under at least one virtual resource, and the decision variable indicating whether to allocate a virtual resource to the above user; the constraints of the above optimization problem include that each user is only allocated one virtual resource, and the total cost of the virtual resources allocated to at least one user does not exceed the preset total cost; based on the constraints of the above optimization problem, converting the above optimization problem into a dual problem to obtain the above dual function.

[0023] In a second aspect, an embodiment of the present application provides a method for allocating virtual resources, the method comprising:

[0024] Acquire the target virtual resource allocated to the current access user according to the virtual resource allocation method provided in the first aspect or any possible implementation manner of the first aspect; and display the target virtual resource.

[0025] In a third aspect, an embodiment of the present application provides a virtual resource allocation device, the virtual resource allocation device comprising:

[0026] An acquisition module is configured to acquire a target dual variable corresponding to the currently visiting user based on the target attribute information of the currently visiting user; the target dual variable is an independent variable that enables the dual function corresponding to the optimization problem to obtain a first target value; the optimization problem is used to determine the virtual resources allocated to the user; the target dual variable is predicted based on historical time series data within a first historical time period; the first historical time period includes multiple different second historical time periods, the historical time series data includes a historical dual variable sequence, and the historical dual variable sequence includes multiple historical dual variables related to the virtual resource allocation within the second historical time period, arranged in chronological order;

[0027] The virtual resource allocation module is configured to allocate target virtual resources to the current visiting user based on the target dual variable and target-related parameters of the current visiting user under at least one virtual resource.

[0028] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory; the processor is connected to the memory; the memory is used to store executable program code; the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the first aspect of the embodiment of the present application or any possible implementation method of the first aspect or the method provided by the second aspect.

[0029] In a fifth aspect, an embodiment of the present application provides a computer storage medium, which stores multiple instructions, and the above instructions are suitable for being loaded by a processor and executing the method steps provided in the first aspect of the embodiment of the present application or any possible implementation of the first aspect or the second aspect.

[0030] In one or more embodiments of the present application, on the one hand, based on the target attribute information of the currently visiting user, the target dual variable corresponding to the currently visiting user is obtained, and by deeply mining the user attribute information, the user characteristics are accurately located, providing a scientific basis for subsequent virtual resource allocation, which helps to improve the pertinence and effectiveness of virtual resource allocation; on the other hand, by introducing dual variables and optimization problems, the virtual resources allocated to the user are decided by the optimization problem, that is, the virtual resource allocation is optimized to maximize the user-related parameters, improve user experience and satisfaction, enhance user stickiness, and lay the foundation for long-term development, and the complex virtual resource allocation problem is converted into a solvable mathematical function (dual function). Quasi-solution prediction enables the dual function to obtain the target dual variable of the first target value, which facilitates the realization of automated and intelligent decision-making, avoids the limitations of manual decision-making, and significantly improves the efficiency and accuracy of resource allocation; thirdly, through time series prediction, the target dual variable required for future virtual resource allocation is predicted in advance based on the historical time series data in the first historical time period. The above-mentioned first historical time period includes multiple different second historical time periods, and the above-mentioned historical time series data includes a historical dual variable sequence, that is, the historical data records the virtual resource allocation situation and the corresponding dual variable values in the past period of time (the first historical time period). By analyzing and mining these data, it can be found that the virtual resource allocation and the dual variable are related. The relationship and rules between variables can be accurately grasped to provide a useful reference for future virtual resource allocation, that is, to provide strong support for current resource allocation, which is helpful to improve the predictability and flexibility of virtual resource allocation, avoid the problem of efficiency loss caused by the asynchronous use of dual solutions by assuming that adjacent samples are distributed uniformly in related technologies, and improve the accuracy and maximization effect of operational solutions in the process of virtual resource allocation; fourthly, accurate virtual resource allocation can be achieved based on the target dual variables corresponding to the current visiting user and their target-related parameters, forming a "data-decision-feedback" closed loop. For example, if the target-related parameters corresponding to the current visiting user are low, the dynamic Dynamically adjust its virtual resource allocation strategy (such as increasing the denomination of coupons or issuing points for high-frequency usage scenarios, etc.) to stimulate current visiting users to generate transaction behaviors and improve relevant parameters; at the same time, the essence of solving the dual problem is to optimize the allocation of virtual resources from a global perspective. Therefore, virtual resources are allocated to the current visiting user based on the user's individual related parameters (target related parameters) under at least one virtual resource and the target dual variable corresponding to the current visiting user obtained by solving the dual function. This takes into account both group efficiency and individual needs, avoids excessive concentration or waste of virtual resources, and achieves a balance between global optimization and personalization corresponding to virtual resource allocation, thereby improving virtual resource utilization and overall operational efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0032] Figure 1 A schematic diagram of the architecture of a virtual resource allocation system provided by an exemplary embodiment of the present application;

[0033] Figure 2 A flowchart of a virtual resource allocation method provided by an exemplary embodiment of the present application;

[0034] Figure 3 A schematic diagram of a construction process of a dual function provided by an exemplary embodiment of the present application;

[0035] Figure 4 A schematic diagram of an implementation flow of an operations research solution in a virtual resource allocation scenario provided by an exemplary embodiment of the present application;

[0036] Figure 5 A schematic diagram of an implementation flow of operations research solution in another virtual resource allocation scenario provided by an exemplary embodiment of the present application;

[0037] Figure 6 A schematic structural diagram of a virtual resource allocation device provided by an exemplary embodiment of the present application;

[0038] Figure 7 A schematic structural diagram of an electronic device provided as an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0039] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application.

[0040] In this specification, claims, and the accompanying drawings, the terms "first," "second," "third," and so on are used to distinguish between different items, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0041] Please refer to the following Figure 1 , which is a schematic diagram of the architecture of a virtual resource allocation system provided by an exemplary embodiment of the present application. Figure 1 As shown, the virtual resource allocation system may include: a terminal 110 and a server 120. Among them:

[0042] Terminal 110 includes one or more user terminals corresponding to users. A corresponding user version application can be installed on terminal 110. The application can register and log in to the user's corresponding account. Users can use the corresponding terminal 110 to conduct online transactions, access, claim, and redeem virtual resources, etc., based on the user version application. The corresponding target access operations and target attribute information are sent to server 120.

[0043] It can be understood that the above-mentioned terminal 110 can be a mobile phone, a tablet computer, a desktop, a laptop, a notebook computer, an ultra-mobile personal computer (UMPC), a handheld computer, a netbook, a personal digital assistant (PDA), a wearable electronic device, etc., and the embodiments of the present application are not limited to this.

[0044] Server 120 may be the server corresponding to the user version application used by the user for online transactions on terminal 110, and is used to provide services such as resource allocation after the user logs in and accesses the user version application. Server 120 may be a hardware server, a virtual server, a cloud server, etc., and is not limited in this embodiment of the present application.

[0045] Specifically, the server 120 can first obtain the target dual variable corresponding to the current visiting user based on the target attribute information of the current visiting user. The target dual variable is the independent variable that enables the dual function corresponding to the optimization problem to obtain the first target value. The optimization problem is used to decide the virtual resources allocated to the user. The target dual variable is predicted based on the historical time series data in the first historical time period. The first historical time period includes multiple different second historical time periods. The historical time series data includes a historical dual variable sequence. The historical dual variable sequence includes multiple historical dual variables related to the virtual resource allocation in the second historical time period arranged in chronological order; then, based on the target dual variable and the target-related parameters of the current visiting user under at least one virtual resource, the target virtual resource is allocated to the current visiting user.

[0046] The network can be, but is not limited to, a medium that provides a communication link between terminal 110 and server 120, or the Internet, which includes network devices and transmission media. The transmission media can be wired links, such as, but not limited to, coaxial cables, optical fibers, and digital subscriber lines (DSL), or wireless links, such as, but not limited to, wireless Fidelity (WIFI), Bluetooth, and mobile device networks.

[0047] Understandably, Figure 1 The number of terminals 110 and servers 120 in the virtual resource allocation system shown is for example only. In a specific implementation, the virtual resource allocation system may include any number of terminals 110 and servers 120, and this embodiment of the present application does not specifically limit this. For example, but not limited to, the terminal 110 may be a user terminal cluster consisting of multiple user terminals, and the server 120 may be a server cluster consisting of multiple servers.

[0048] Next, combine Figure 1 , introduces a virtual resource allocation method provided by the embodiment of this application. For details, please refer to Figure 2 , which is a flow chart of a virtual resource allocation method provided by an exemplary embodiment of the present application. Figure 2 As shown, the virtual resource allocation method includes the following steps:

[0049] S201, based on the target attribute information of the currently visiting user, obtain the target dual variable corresponding to the currently visiting user. The target dual variable is the independent variable that enables the dual function corresponding to the optimization problem to obtain the first target value. The optimization problem is used to decide the virtual resources allocated to the user. The target dual variable is predicted based on the historical time series data in the first historical time period.

[0050] Specifically, the above-mentioned current accessing user may be, but is not limited to, a user who is currently accessing the target application, and the above-mentioned target application may be, but is not limited to, an application used for online transactions such as shopping and financial management. The above-mentioned target application may be a separate online transaction software installed on the terminal, or it may be a small program integrated into other software, etc., and the embodiments of this specification do not limit this. The above-mentioned target attribute information includes data features related to the currently accessing user, such as, but not limited to, basic information such as the current accessing user's occupation, place of origin, historical transaction records, etc. This information is used to distinguish the group category to which the currently accessing user belongs. The above-mentioned group category can be divided according to basic attributes such as the user's age group, occupation, or location, and can also be divided according to the user's transaction preferences or transaction habits, such as the green food transaction group (i.e., users who like to buy green food online), etc., which can be set according to actual needs, and the embodiments of this specification do not limit this.

[0051] The goal of the aforementioned optimization problem is to determine how to allocate virtual resources to users currently accessing the target application so that all user-related parameters meet pre-set conditions, such as, but not limited to, maximizing or minimizing the sum of all user-related parameters or ensuring consistency across all user-related parameters. These parameters may include, but are not limited to, virtual resource redemption rates, access rates, transaction volumes, and other parameters related to the virtual resources, and can be set based on actual needs. The redemption rate can be the ratio of user usage or conversion of allocated virtual resources, i.e., virtual resource utilization or conversion rate, or the rate of increase in user conversion rate (e.g., but not limited to, order placement probability) after allocating virtual resources, though this specification is not limiting in this regard. A greater sum of user redemption rates indicates a higher total transaction rate for users in the target application, meaning a greater sum of corresponding benefits generated by users after allocating virtual resources. These virtual resources may be, but are not limited to, subsidies, coupons, or virtual points, and the corresponding virtual resource quantity may be, but is not limited to, subsidy amounts, coupon denominations, or virtual points, though this specification is not limiting in this regard.

[0052] The dual function corresponds to the function in the original optimization problem. It provides a different perspective on the original optimization problem, and solving the dual function is often more efficient than directly solving the original optimization problem. Dual variables are variables corresponding to the variables in the original optimization problem and are used to construct the dual problem. Solving the dual function for the dual variables in the dual problem yields the target solution to the original optimization problem.

[0053] Optionally, the target dual variable corresponding to the above-mentioned currently visiting user can be an independent variable value for enabling the dual function corresponding to the optimization problem under the target group and / or target access scenario corresponding to the current visiting user to obtain a first target value (such as but not limited to a minimum value or a maximum value or a preset value, etc.). The optimization problem under the target group corresponding to the above-mentioned currently visiting user is used to decide the virtual resources allocated to each user in the target group, so as to achieve that the relevant parameters of all users corresponding to the target group meet preset conditions, such as but not limited to maximizing or minimizing the sum of relevant parameters of all users corresponding to the target group or unifying relevant parameters of all users, etc.; the optimization problem under the target access scenario corresponding to the above-mentioned currently visiting user is used The virtual resources allocated to each user in the target access scenario are determined so that all user-related parameters in the target access scenario meet preset conditions, such as, but not limited to, maximizing or minimizing the sum of all user-related parameters in the target access scenario, or unifying all user-related parameters. The optimization problem corresponding to the target group and the target access scenario for the current access user is used to determine the virtual resources allocated to each user in the target group in the target access scenario so that all user-related parameters corresponding to the target group in the target access scenario meet preset conditions, such as, but not limited to, maximizing or minimizing the sum of all user-related parameters corresponding to the target group in the target access scenario, or unifying all user-related parameters. The target groups can be, but are not limited to, group classification based on target attribute information such as basic user information (such as, but not limited to, region, consumption preferences, etc.) or transaction habits (such as high consumption, low consumption, etc.) of the current access user, and can include, for example, but not limited to, a young user group, an elderly user group, a user group in region A, a user group in region B, a high-spending group, etc.

[0054] The first historical time period includes multiple different second historical time periods, which are non-overlapping and continuous. The first historical time period is the time period before the current access time. Different current time periods correspond to different time ranges of the historical time series data used for target dual variable prediction, i.e., the first historical time period. For example, but not limited to, when the current time period is T, the first historical time period should be the time period before T, i.e., the (T-1) time period. When the current time period is (T+1), the first historical time period should be the time period before (T+1), i.e., the T time period. The current time period and the first historical time period each have the same length. The current time period includes multiple current time subsegments of equal length (i.e., time intervals) that are continuous and non-overlapping. The time intervals corresponding to these current time subsegments are equal to the time intervals corresponding to the second historical time periods.

[0055] Optionally, the target dual variable corresponding to the currently visiting user can be, but is not limited to, first predicting a future dual variable sequence corresponding to a future time period (i.e., the current time period) based on historical time series data within the first historical time period, and then querying from the future dual variable sequence based on the current time sub-segment (i.e., the future time sub-segment) to which the current access time belongs, that is, the target dual variable can be the future dual variable corresponding to the current time sub-segment (i.e., the future time sub-segment) in the future dual variable sequence.

[0056] Optionally, the target dual variable corresponding to the above-mentioned currently visiting user can also be, but is not limited to, first predicting the future dual variable sequence corresponding to the future time period (i.e., the current time period) based on the historical time series data in the first historical time period, and then performing weighted summation on multiple future dual variables in the future dual variable sequence based on the current time sub-segment (i.e., the future time sub-segment) to which the current access time belongs.

[0057] Optionally, the target dual variable corresponding to the currently accessing user may also be obtained by, but is not limited to, first predicting a future dual variable sequence corresponding to a future time period (i.e., the current time period) based on historical time series data within a first historical time period, and then searching for a first target value (such as, but not limited to, a minimum value, a maximum value, or a preset value) on the dual function corresponding to the optimization problem based on multiple future dual variables in the future dual variable sequence. Alternatively, the target dual variable may be obtained by searching for the first target value on the dual function corresponding to the optimization problem based on multiple future dual variables in the future dual variable sequence, target-related parameters and target virtual resource cost for the currently accessing user for at least one virtual resource, and at least one virtual resource type. Specifically, the target dual variable is the future dual variable in the future dual variable sequence that causes the dual function corresponding to the optimization problem in the current time period to achieve the first target value. Target-related parameters may include, but are not limited to, a target write-off rate, target access rate, or target transaction volume for the currently accessing user for at least one virtual resource.

[0058] Optionally, the target dual variable corresponding to the currently visiting user can also be, but is not limited to, directly predicted based on the historical time series data in the first historical time period, and the independent variable that enables the dual function corresponding to the optimization problem to obtain the first target value in the future time period (i.e., the current time period).

[0059] The above-mentioned historical time series data includes a historical dual variable sequence, and the above-mentioned historical dual variable sequence includes a plurality of historical dual variables related to the virtual resource allocation in the second historical time period, which are arranged in chronological order.

[0060] Optionally, the historical time series data may also include, but is not limited to, at least one of the following: a historical virtual resource cost sequence, a historical time feature sequence, and a historical traffic sequence within the first historical time period. The historical virtual resource cost sequence may include, but is not limited to, the historical virtual resource cost allocated to at least one historical access user within multiple second historical time periods arranged in chronological order (i.e., the total virtual resource cost allocated to all historical access users within the second historical time period). The historical time feature sequence refers to a sequence consisting of a series of time feature values extracted from each second historical time period within the first historical time period. These time features are typically used to predict future trends or behaviors, and include, for example, but not limited to, timestamps, periodic features (e.g., hourly, daily, weekly, monthly, etc.), and special time attribute features (e.g., weekends, holidays, Singles' Day, etc.). The historical traffic sequence may reflect the consumption rate of historical virtual resource costs within each second historical time period, and may include, for example, but not limited to, the historical access traffic corresponding to each of the multiple second historical time periods.

[0061] Optionally, the above-mentioned historical time series data may also include, but is not limited to, a historical dual intermediate function sequence, wherein the above-mentioned historical dual intermediate function sequence is composed of a plurality of historical dual intermediate functions arranged in chronological order within the second historical time period, and the above-mentioned historical dual intermediate function may be, but is not limited to, composed of historical dual variables corresponding to the second historical time period, historical related parameters of historical visiting users under at least one virtual resource, and virtual resource costs, for example, but not limited to, ,in, is the dual intermediate function within the time period t, Refers to the relevant parameters corresponding to the allocation of virtual resource j to access user i. Refers to the dual variable corresponding to the user i who visited during the t period, It refers to the virtual resource cost corresponding to access user i when virtual resource j is allocated. j is greater than or equal to 1 and less than or equal to the total number of preset virtual resource types. C refers to the total number of users.

[0062] Optionally, the above-mentioned historical dual variable can be an independent variable that enables the dual function corresponding to the optimization problem in the second historical time period to obtain the first target value, or it can be the dual variable actually used when allocating virtual resources in the second historical time period, or it can be the historical target dual variable that enables the dual function corresponding to the optimization problem in the first historical time period to obtain the first target value, which is discretized according to a preset time step (for example, but not limited to 0.005, 0.006, etc.) and the above-mentioned historical target dual variable is located in the above-mentioned historical dual variable sequence, etc. The embodiments of this specification do not limit this.

[0063] Optionally, the target dual variable corresponding to the above-mentioned currently accessed user can also be, but is not limited to, first predicting the future dual intermediate function sequence in the future time period (i.e., the current time period) based on the historical dual intermediate function sequence in the first historical time period, and discretizing the historical target dual variable in the first historical time period that enables the dual function corresponding to the optimization problem to obtain the first target value according to a preset time step (for example, but not limited to 0.005, 0.006, etc.) to obtain multiple historical discrete dual variables, and then determining the target dual intermediate function corresponding to the future time sub-segment to which the current access time belongs in the future dual intermediate function sequence, and determining the target dual function corresponding to the optimization problem in the future time sub-segment to which the current access time belongs based on the target dual intermediate function and the total cost of the target virtual resources corresponding to the future time sub-segment to which the current access time belongs, and finally, searching for the first target value on the above-mentioned target dual function based on multiple historical discrete dual variables.

[0064] The at least one virtual resource mentioned above may refer to a virtual resource corresponding to at least one virtual resource quantity under the same type of virtual resources, such as, but not limited to, a coupon for a 5 yuan discount on purchases over 30 yuan, a coupon for a 6 yuan discount on purchases over 30 yuan, etc., or may refer to a virtual resource corresponding to a certain virtual resource quantity under at least one type of virtual resources, such as, but not limited to, a 3 yuan subsidy, a coupon for a 7 yuan discount on purchases over 30 yuan, a coupon for a 3 yuan discount on purchases over 30 yuan, etc. The relevant parameters of a historical visiting user under at least one virtual resource refer to the utilization rate or conversion rate of various virtual resources corresponding to the historical visiting user when various virtual resources are allocated. The virtual resource cost of a historical visiting user under at least one virtual resource refers to the cost of allocating a certain virtual resource to the historical visiting user. The total historical virtual resource cost corresponding to the second historical time period mentioned above refers to the total cost budget value pre-set for allocating virtual resources to all historical visiting users in the second historical time period.

[0065] Please continue to refer to Figure 2 ,like Figure 2 As shown, in the above S201, after obtaining the target dual variable corresponding to the current access user based on the target attribute information of the current access user, the virtual resource allocation method may also include but is not limited to:

[0066] S202 : Allocate a target virtual resource to the current access user based on the target dual variable and target-related parameters of the current access user under at least one virtual resource.

[0067] In some possible embodiments, the above S202, before allocating target virtual resources to the current visiting user based on the target dual variable and the target-related parameters of the current visiting user under at least one virtual resource, the virtual resource allocation method may also include, but is not limited to: using machine learning technology to calculate the target-related parameters of the current visiting user under at least one virtual resource based on the target user characteristics of the current visiting user, the above-mentioned target user characteristics including at least one of the following: target attribute information, target transaction frequency, historical virtual resource allocation and related parameter information.

[0068] The above-mentioned target-related parameters may include, but are not limited to, the target redemption rate, target access rate, target transaction volume, etc. of the current visiting user under at least one virtual resource. The above-mentioned target redemption rate can be used to characterize the possibility of the current visiting user using a certain virtual resource after being allocated to the current visiting user, or the probability of the current visiting user actually using the virtual resource, that is, the possibility of the current visiting user actually using a certain virtual resource after obtaining it before the current access time. The embodiments of this specification do not limit this. The above-mentioned target attribute information refers to some basic information of the current visiting user, such as, but not limited to, age, occupation, etc. The above-mentioned target transaction frequency refers to the frequency of transactions conducted by the current visiting user within a certain period of time, which can reflect the current visiting user's activity and the degree of demand for a certain resource. The above-mentioned historical virtual resource allocation and related parameter information refers to the relevant records of the current visiting user's past acquisition and use of virtual resources. These data help predict the possibility of the current visiting user using virtual resources in the future.

[0069] Optionally, after obtaining the target dual variable corresponding to the currently accessing user, the target virtual resource corresponding to the target dual variable can be directly determined from at least one virtual resource that can be allocated to the user in advance according to the pre-set mapping relationship between the dual variable and the virtual resource type, and the target virtual resource can be issued to the current access account on the corresponding terminal of the currently accessing user that is accessing the target application, so as to timely encourage the currently accessing user to use the target virtual resource to conduct online transactions in the target application.

[0070] Optionally, in order to avoid the problem of inaccurate virtual resource allocation caused by allocating the same virtual resources to users in the same group, after obtaining the target dual variable corresponding to the current visiting user, the target dual variable and the target-related parameters of the current visiting user under at least one virtual resource can be directly input into a pre-trained virtual resource allocation model to output the target virtual resource that should be allocated to the current visiting user. In this way, through the target-related parameters of the current visiting user itself under at least one virtual resource, the virtual resource allocation model can perform more accurate and targeted virtual resource allocation for the individual level of a single user at the group level.

[0071] Optionally, the above-mentioned S202, the implementation process of allocating a target virtual resource to the current visiting user based on the target dual variable and the target-related parameters of the current visiting user under at least one virtual resource, may include, but is not limited to: first, searching for the second target value on the decision optimization function corresponding to the dual function based on the target dual variable, the target-related parameters of the current visiting user under at least one virtual resource, the target virtual resource cost, and at least one virtual resource type to obtain the target virtual resource type; then, allocating the corresponding target virtual resource to the current visiting user according to the target virtual resource type. The above-mentioned target virtual resource type is the virtual resource type of at least one virtual resource type for which the decision optimization function takes the second target value when the current visiting user and the target dual variable are known. The second target value on the decision optimization function corresponding to the above-mentioned dual function corresponds to the first target value on the above-mentioned dual function, that is, when the dual function takes the first target value, the value of the corresponding decision optimization function is obtained. The above-mentioned second target value may be, but is not limited to, the maximum value or minimum value of the decision optimization function or a preset target value, etc.

[0072] For example, when the first target value is the minimum value on the dual function, the second target value is the maximum value on the decision optimization function corresponding to the dual function, and the target virtual resource type is ,in, Refers to the target-related parameters corresponding to the current access user i when allocating virtual resource j. Refers to the target dual variable corresponding to the current access user, It refers to the target virtual resource cost corresponding to the current access user i when the virtual resource j is allocated, where j is greater than or equal to 1 and less than or equal to the total number of preset virtual resource types.

[0073] In the embodiments of this specification, on the one hand, the target dual variable corresponding to the currently visiting user is obtained based on the target attribute information of the currently visiting user, and by deeply mining the user attribute information and accurately locating the user characteristics, a scientific basis is provided for the subsequent virtual resource allocation, which helps to improve the pertinence and effectiveness of virtual resource allocation; on the other hand, by introducing dual variables and optimization problems, the virtual resources allocated to the user are decided by the optimization problem, that is, the virtual resource allocation is optimized to maximize the user-related parameters, improve user experience and satisfaction, enhance user stickiness, and lay the foundation for long-term development, and the complex virtual resource allocation problem is converted into a solvable mathematical function (dual function), and the dual function is obtained by accurately solving and predicting. The target dual variable of a target value is convenient for realizing automated and intelligent decision-making, avoiding the limitations of manual decision-making, and significantly improving the efficiency and accuracy of resource allocation; thirdly, through the time series prediction method, the target dual variable required for future virtual resource allocation is predicted in advance according to the historical time series data in the first historical time period. The above-mentioned first historical time period includes multiple different second historical time periods. The above-mentioned historical time series data includes a historical dual variable sequence, that is, the historical time series data records the virtual resource allocation situation and the corresponding dual variable value in the past period of time (the first historical time period). By analyzing and mining these data, the relationship and law between virtual resource allocation and dual variables can be discovered, and the user needs and virtual resources can be accurately grasped. The trend of virtual resource allocation provides a useful reference for future virtual resource allocation, that is, it provides strong support for current resource allocation, helps to improve the predictability and flexibility of virtual resource allocation, avoids the problem of problem solution deviation caused by the asynchronous use of dual solutions assuming that adjacent samples are uniformly distributed in related technologies, resulting in efficiency loss, and improves the accuracy and maximization effect of operational solutions in the process of virtual resource allocation; fourthly, accurate virtual resource allocation can be achieved based on the target dual variables corresponding to the current visiting user and their target-related parameters, forming a "data-decision-feedback" closed loop. For example, if the target-related parameters corresponding to the current visiting user are low, its virtual resource allocation strategy can be dynamically adjusted (such as increasing the denomination of coupons or issuing high-frequency usage coupons). At the same time, the essence of solving the dual problem is to optimize the allocation of virtual resources from a global perspective so that the overall user-related parameters meet the preset conditions, such as but not limited to maximizing the sum of the overall user-related parameters. Therefore, the current visiting user is allocated virtual resources by combining the individual user-related parameters (target-related parameters) of the current visiting user under at least one virtual resource and the target dual variable corresponding to the current visiting user obtained by solving the dual function. This takes into account both group efficiency and individual needs, avoids excessive concentration or waste of virtual resources, and achieves a balance between global optimization and personalization corresponding to virtual resource allocation, thereby improving virtual resource utilization and overall operational efficiency.

[0074] Please refer to the following Figure 3 , which is a schematic diagram of the construction process of a dual function provided by an exemplary embodiment of the present application. Figure 3 As shown, the construction process of the dual function can include but is not limited to the following steps:

[0075] S301: construct an optimization problem based on relevant parameters of a user under at least one virtual resource and a decision variable indicating whether to allocate a virtual resource to the user.

[0076] Specifically, the constraints of the optimization problem include allocating only one type of virtual resource to each user, and ensuring that the total cost of the virtual resources allocated to at least one user does not exceed a preset total cost. The optimization problem is the process of finding a virtual resource allocation strategy that, under these constraints, ensures that user-related parameters meet preset conditions (such as, but not limited to, maximizing or minimizing the sum of user-related parameters). The decision variables are ultimately used to determine which of the at least one virtual resource is allocated to the user. The preset total cost refers to an upper limit on the total cost of virtual resource allocation, set before the optimization problem begins.

[0077] For example, if we want to maximize the sum of user-related parameters, the first objective value is the minimum value on the dual function, and the second objective value is the maximum value on the decision optimization function corresponding to the dual function. The above optimization problem can be characterized as follows: , whose constraints include: (i=1, 2, ..., C, j=1, 2, ..., R, C refers to the total number of users, R refers to the total number of virtual resources), that is, the decision variable The value of the decision variable is 0 or 1. When the value of is 0, it indicates that virtual resource j is not allocated to user i. When the value of is 1, it indicates that virtual resource j is allocated to user i; (i=1, 2, ..., C), that is, each user i is only allocated one virtual resource j; , which is the total cost of virtual resources allocated to users Not exceeding the preset total cost B.

[0078] In the embodiments of this specification, on the one hand, user behavior can be quantified through relevant parameters, so that virtual resource allocation is closely linked to the actual needs of users, thereby improving the scientific nature of virtual resource allocation decisions; on the other hand, the total cost of virtual resources can be constrained to avoid waste of virtual resources and ensure the economy of virtual resource allocation.

[0079] S302: Based on the constraints of the optimization problem, the optimization problem is transformed into a dual problem to obtain a dual function.

[0080] Specifically, the original optimization problem is transformed into a dual problem. By interchanging the dual variables and constraints and converting the functions and coefficients, the complexity of the solution is simplified to obtain the dual function. The dual function can be, but is not limited to, composed of the dual variables, a preset total cost, relevant parameters of the user under at least one virtual resource, and the virtual resource cost.

[0081] For example, when the first objective value is the minimum value on the dual function and the second objective value is the maximum value on the decision optimization function corresponding to the dual function, the optimization problem can be converted into a standard linear programming format based on the constraints of the optimization problem and solved in the dual space using Lagrange multipliers to obtain: ,in, is the dual variable; assuming , then we can get the dual function corresponding to the transformed dual problem as: .

[0082] In the embodiments of this specification, on the one hand, by converting the multi-constraint and multi-variable optimization problem into a single-constraint and single-variable dual problem, it is convenient to use efficient algorithms such as the simplex method and the interior point method to solve the problem, thereby improving the solution efficiency, and can also solve the problem that the original optimization problem is difficult to calculate due to the existence of high-dimensional constraints, provide a low-dimensional and simple alternative solution path, ensure the feasibility of virtual resource allocation, and enhance robustness; on the other hand, by reflecting the shadow price of virtual resource allocation through the dual variable, it is convenient to analyze the impact of changes in virtual resource costs on virtual resource allocation strategies, thereby enhancing decision-making flexibility.

[0083] Please refer to the following Figure 4 , which is a schematic diagram of the implementation flow of an operations solution in a virtual resource allocation scenario provided by an exemplary embodiment of the present application. Figure 4 As shown, the implementation process of the operations research solution in the virtual resource allocation scenario may include but is not limited to the following steps:

[0084] S401: Acquire historical time series data within a first historical time period.

[0085] Specifically, the first historical time period includes multiple different second historical time periods, and the multiple second historical time periods do not overlap and are continuous. The historical time series data includes a historical dual variable sequence, and the historical dual variable sequence includes multiple historical dual variables related to virtual resource allocation in the second historical time period, which are arranged in chronological order within the first historical time period.

[0086] Optionally, the historical time series data may also include, but is not limited to, at least one of the following: a historical virtual resource cost sequence within the first historical time period, a historical time feature sequence, and a historical traffic sequence. The historical virtual resource cost sequence may include, but is not limited to, the historical virtual resource costs that can be allocated to at least one historical access user within multiple second historical time periods arranged in chronological order (i.e., the total virtual resource costs that can be allocated to all historical access users within the second historical time period). The historical time feature sequence refers to a sequence consisting of a series of time feature values extracted from each second historical time period within the first historical time period. These time features are typically used to predict future trends or behaviors, and include, for example, but not limited to, timestamps, periodic features (such as hours, days, weeks, months, etc.), and special time attribute features (such as weekends, holidays, and Singles' Day). The historical traffic sequence may reflect the consumption rate of historical virtual resource costs within each second historical time period, and may include, for example, but not limited to, the historical access traffic corresponding to each of the multiple second historical time periods.

[0087] The implementation process of obtaining the historical time series data within the first historical time period may include, but is not limited to: first obtaining the historical data within the first historical time period, the historical data may include, but is not limited to, multiple historical dual variables and other relevant historical data related to the virtual resource allocation within the second historical time period, the other relevant historical data may include, but is not limited to, at least one of the following: historical virtual resource costs, historical time information, and historical traffic information corresponding to multiple second historical time periods; then, preprocessing the historical data to obtain historical time series data. The preprocessing may include, but is not limited to, converting various data in the historical data into corresponding time series data in chronological order, standardizing the historical data, and mapping the value range of the corresponding data features to the same value range, so as to obtain the historical time series data that can be read and analyzed by the time series prediction model used for prediction.

[0088] Optionally, the implementation process of obtaining the historical time series data within the first historical time period may include, but is not limited to: regularly obtaining the historical time series data of historical visiting users belonging to the same constraint dimension within the first historical time period according to preset time intervals, the above constraint dimension may include, but is not limited to, user groups and / or user access scenarios, and the above historical time series data is updated as the first historical time period is updated.

[0089] For example, but not limited to, after receiving historical access operations from historical users within a first historical time period, user data can be collected and dynamically divided into groups based on user attributes (such as, but not limited to, region, consumption preferences, etc.) or transaction habits (e.g., high-spending, low-spending, etc.). Then, historical time series data for historical users belonging to the same constraint dimension within the first historical time period is collected and stored based on the user groups and / or user access scenarios to which each historical user belongs. When the end of the first historical time period is reached, a solver call is triggered. The solver, taking the historical time series data of historical users belonging to the same constraint dimension as input, constructs a constrained optimization problem with the goal of ensuring that group-related parameters meet preset conditions (such as, but not limited to, maximizing the sum of group-related parameters). Through dual transformation, the original optimization problem is transformed into a dual problem. The dual function is then efficiently solved using time series prediction, resulting in a future dual variable sequence that reflects the marginal value of virtual resources in the next time period (i.e., the future time period) corresponding to the first historical time period.

[0090] Please continue to refer to Figure 4 ,like Figure 4 As shown, after obtaining the historical time series data in the first historical time period in S401, the implementation process of the operations research solution in the virtual resource allocation scenario may also include but is not limited to:

[0091] S402, predicting future dual variable sequences based on historical time series data.

[0092] Specifically, the above-mentioned future dual variable sequence includes predicted dual variables that enable the dual function corresponding to the corresponding optimization problem to obtain the first target value in multiple different future time periods, and the time interval corresponding to the above-mentioned future time period is equal to the time interval corresponding to the second historical time period.

[0093] Optionally, historical time series data can be input into a time series prediction model to output a future dual variable sequence. The time series prediction model can be, but is not limited to, trained based on sample time series data in a second time period of a plurality of known dual variable sequences in a first time period; the time interval corresponding to the first time period is equal to the time interval corresponding to the second time period, and the first time period is the time period after the second time period. The time series prediction model can be, but is not limited to, adopting a Transformer variant structure specifically for multivariate time series prediction, which can achieve reversible transformation through transposition operations of feature and time dimensions.

[0094] Optionally, the above-mentioned prediction of future dual variable sequences based on historical time series data may also include, but is not limited to: predicting future dual variable sequences of historical visiting users under the corresponding historical constraint dimensions based on historical time series data of historical visiting users belonging to the same constraint dimension, thereby splitting the multi-constraint optimization problem of the overall application users into a single-constraint dual problem for the same constraint dimension, reducing the complexity of operational solutions in the virtual resource allocation process and improving efficiency.

[0095] S403: Store the future dual variable sequence in the database.

[0096] Specifically, after obtaining the future dual variable sequence in the future time period through time series prediction, the future dual variable sequence can be directly stored in the database so as to be efficiently called when subsequently allocating virtual resources to visiting users in the future time period.

[0097] Optionally, after obtaining the future dual variable sequence under the same historical constraint dimension in the future time period through time series prediction, the future dual variable sequence and the historical constraint dimension identifier of the corresponding historical visiting user can be associated and stored in a database or other data storage system, so that the dual variable can be called in a targeted manner when allocating virtual resources to the user based on the attribute information of the visiting user in the future time period, thereby improving the targetedness and accuracy of virtual resource allocation.

[0098] The above-mentioned historical constraint dimension identifier may include, but is not limited to, a group identifier and / or an access scenario identifier. The above-mentioned group identifier is a unique identifier used to distinguish different groups, and may be, but is not limited to, a user identity identifier, a user group, a membership level, a user location, etc. Through the group identifier, it is possible to identify and distinguish which specific group each user belongs to. The above-mentioned historical constraint dimension identifier can be obtained by encoding the user's group attributes, or by encoding the user's group attributes and access scenario together. It can be a string composed of numbers and / or symbols, or it can be text or images that can directly represent the identity of the group, etc., and this specification embodiment does not limit this.

[0099] In some possible embodiments, after receiving the online access operation sent by the terminal, the server can also query the target attribute information of the current access user in the database based on the user identifier of the current access user carried in the online access operation, and determine the target group to which the current access user belongs based on the target attribute information according to the preset correspondence between the attribute information and the group or by using a pre-trained group recognition model. Then, based on the target group identifier corresponding to the target group and / or the target access scenario identifier of the current access user carried in the online access operation, the target future dual variable sequence under the target history constraint dimension corresponding to the current access user obtained by time series prediction before the current access time is queried in the database. Finally, the target dual variable corresponding to the current access user is determined based on the current access time of the current access user and the target future dual variable sequence.

[0100] Please refer to the following Figure 5 , which is a schematic diagram of the implementation flow of another operational solution in a virtual resource allocation scenario provided by an exemplary embodiment of the present application. Figure 5 As shown, the implementation process of the operations research solution in the virtual resource allocation scenario may include but is not limited to the following steps:

[0101] S501: Obtain a target time series prediction request, where the target time series prediction request carries a time series prediction constraint condition.

[0102] Specifically, the target timing prediction request may be generated or received at a preset time interval. The timing prediction constraint may include, but is not limited to, that the total cost of virtual resources allocated to the user in multiple different future time periods does not exceed a preset total cost.

[0103] Optionally, the above-mentioned time series prediction constraints may also include, but are not limited to, including that the total cost of virtual resources allocated to users under the target constraint dimension in multiple different future time periods does not exceed the preset total cost; the above-mentioned target constraint dimension may include, but is not limited to, at least one of the following: target user group, target user access scenario.

[0104] S502: Acquire historical time series data within a first historical time period.

[0105] Specifically, the implementation process of the above S502 is similar to that of S401 and will not be repeated here.

[0106] S503 , in response to the target time series prediction request, predict the future dual variable sequence based on the time series prediction constraints and the historical time series data.

[0107] Specifically, since the solution to the independent variable that enables the dual function corresponding to the optimization problem to obtain the first target value is not only related to the historical time series data, but also to the total cost of virtual resources in the corresponding time period, it is possible to respond to the target time series prediction request, based on the time series prediction constraints and historical time series data, and achieve a more flexible and accurate prediction of the future dual variable sequence by analyzing the comprehensive impact of the prediction constraints and the historical time series data on the solution.

[0108] Optionally, when the timing prediction constraints include that the total cost of virtual resources allocated to users under the target constraint dimension in multiple different future time periods does not exceed a preset total cost, the above-mentioned target timing prediction request can be responded to, and the future dual variable sequence under the target constraint dimension can be predicted based on the above-mentioned timing prediction constraints and the historical timing data under the target constraint dimension, thereby achieving more accurate and targeted timing prediction for the constraint dimension of virtual resource allocation.

[0109] S504: Store the future dual variable sequence in the database.

[0110] Specifically, the above S504 is consistent with the above S403 and will not be repeated here.

[0111] In some possible embodiments, the overall implementation process of a virtual resource allocation method provided by an exemplary embodiment of the present application may include, but is not limited to, first periodically acquiring historical time series data within a first historical time period. The historical time series data includes a historical dual variable sequence within the first historical time period and at least one of the following data: a historical virtual resource cost sequence, a historical time feature sequence, a historical traffic sequence, and a historical dual intermediate function sequence within the first historical time period. Then, the historical time series data is input into a pre-trained time series prediction model. The encoding layer of the time series prediction model linearly encodes each sequence in the time series. A multivariate attention mechanism layer calculates attention correlations on the variables, and then a first normalization layer performs normalization to obtain a first normalized result for each sequence. Then, a feedforward network layer performs a nonlinear transformation to enhance the model's expressiveness. A second normalization layer (i.e., a time series normalization layer) performs layer normalization in the time series dimension. Specifically, the mean and variance of the features of each time step are independently calculated and normalized to eliminate distribution differences between time steps and enhance the model's ability to capture time series patterns. Finally, the projection layer performs parameterized transformations (such as weight matrices and bias terms) to learn the nonlinear relationships in the data, extract higher-order feature representations, and obtain and output future dual variable sequences for the future time period. Simultaneously, the future dual variable sequences under the same historical constraint dimension are associated with the corresponding historical constraint dimension identifier and stored in the database. This time series forecasting model can independently process each channel time series, avoiding information confusion between different variables. It also has the ability to capture global information within each channel time series and the correlation between variables.

[0112] When an access operation of the current visiting user is received, the target dual variable corresponding to the current visiting user can be directly obtained based on the target attribute information of the current visiting user and the pre-stored future dual variable sequence, and the target virtual resource can be allocated to the current visiting user based on the above target dual variable and the target-related parameters of the current visiting user under at least one virtual resource.

[0113] In some possible embodiments, when the current accessing user accesses the target application through the terminal, the terminal can obtain the target virtual resources allocated to the current accessing user according to the virtual resource allocation method in the above embodiment, such as but not limited to receiving the target virtual resources allocated to the current accessing user by the above virtual resource allocation method sent by the server corresponding to the target application; after obtaining the target virtual resources allocated to the current accessing user, the terminal can directly display the target virtual resources in the current access page corresponding to the target application, so that the target user can check and use the target virtual resources in a timely manner.

[0114] In order to better understand the virtual resource allocation method provided in the above embodiments of the present application, Figure 6The following is a schematic diagram showing the structure of a virtual resource allocation device provided in an embodiment of the present application. Figure 6 As shown, the virtual resource allocation device 600 includes:

[0115] A first acquisition module 610 is configured to acquire a target dual variable corresponding to the currently accessing user based on the target attribute information of the currently accessing user; the target dual variable is an independent variable that enables the dual function corresponding to the optimization problem to obtain a first target value; the optimization problem is used to determine the virtual resources to be allocated to the user; the target dual variable is predicted based on historical time series data within a first historical time period; the first historical time period includes multiple different second historical time periods, the historical time series data includes a historical dual variable sequence, and the historical dual variable sequence includes multiple historical dual variables related to the virtual resource allocation within the second historical time period, arranged in chronological order;

[0116] The virtual resource allocation module 620 is configured to allocate target virtual resources to the current access user based on the target dual variable and the target-related parameters of the current access user under at least one virtual resource.

[0117] In a possible implementation, the virtual resource allocation apparatus 600 further includes:

[0118] A second acquisition module is used to acquire historical time series data within a first historical time period;

[0119] A time series prediction module is configured to predict a future dual variable sequence based on the historical time series data; the future dual variable sequence includes predicted dual variables that enable a dual function corresponding to a corresponding optimization problem to achieve a first target value within a plurality of different future time periods; the time interval corresponding to the future time period is equal to the time interval corresponding to the second historical time period;

[0120] The storage module is used to store the above future dual variable sequence in a database.

[0121] In one possible implementation, the historical time series data also includes at least one of the following data: a historical virtual resource cost sequence, a historical time feature sequence, and a historical traffic sequence within the first historical time period; the second acquisition module is specifically used to: obtain historical data within the first historical time period; the historical data includes multiple historical dual variables and other relevant historical data related to the virtual resource allocation within the second historical time period; the other relevant historical data include at least one of the following: multiple historical virtual resource costs, historical time information, and historical traffic information corresponding to each of the second historical time periods; the historical data is preprocessed to obtain historical time series data.

[0122] In a possible implementation, the virtual resource allocation apparatus 600 further includes:

[0123] The third acquisition module is configured to acquire a target timing prediction request; the target timing prediction request carries a timing prediction constraint, wherein the timing prediction constraint includes that the total cost of virtual resources allocated to the user in multiple different future time periods does not exceed a preset total cost;

[0124] The above-mentioned time series prediction module is specifically used to: respond to the above-mentioned target time series prediction request, and predict the future dual variable sequence based on the above-mentioned time series prediction constraints and the above-mentioned historical time series data.

[0125] In one possible implementation, the time series prediction constraint condition includes that the total cost of virtual resources allocated to users under the target constraint dimension in multiple different future time periods does not exceed a preset total cost; the target constraint dimension includes at least one of the following: a target user group, a target user access scenario;

[0126] The above time series prediction module is specifically used for:

[0127] In response to the target time series prediction request, the future dual variable sequence under the target constraint dimension is predicted based on the time series prediction constraints and the historical time series data under the target constraint dimension.

[0128] In one possible implementation, the time series prediction module is specifically used to:

[0129] The above historical time series data is input into the time series prediction model to output the future dual variable sequence; the above time series prediction model is trained based on the sample time series data in the second time period of multiple known dual variable sequences in the first time period; the time interval corresponding to the above first time period is equal to the time interval corresponding to the above second time period, and the above first time period is the time period after the above second time period.

[0130] In a possible implementation, the second acquisition module is specifically configured to:

[0131] Obtaining historical time series data of historical access users belonging to the same constraint dimension within a first historical time period at preset time intervals; the constraint dimension includes user groups and / or user access scenarios; and the historical time series data is updated as the first historical time period is updated.

[0132] The time series prediction module is specifically used to: predict the future dual variable sequence of the historical visiting users under the historical constraint dimension corresponding to the historical visiting users based on the historical time series data of the historical visiting users belonging to the same constraint dimension;

[0133] The storage module is specifically used to associate the future dual variable sequence with the historical constraint dimension identifier corresponding to the historical access user and store it in a database.

[0134] In a possible implementation, the first acquisition module 610 is specifically used to: determine the target group to which the current visiting user belongs based on the target attribute information of the current visiting user; query in the database based on the target group identifier corresponding to the target group and / or the target access scenario identifier corresponding to the current visiting user to obtain the target future dual variable sequence corresponding to the current visiting user; determine the target dual variable corresponding to the current visiting user based on the current access time of the current visiting user and the target future dual variable sequence.

[0135] In a possible implementation, the virtual resource allocation module 620 is specifically configured to:

[0136] Based on the above-mentioned target dual variable, the target-related parameters and target virtual resource cost of the above-mentioned current visiting user under at least one virtual resource, and at least one virtual resource type, the second target value on the decision optimization function corresponding to the above-mentioned dual function is searched to obtain the target virtual resource type; the above-mentioned target virtual resource type is the virtual resource type corresponding to the second target value of the above-mentioned decision optimization function in the above-mentioned at least one virtual resource type when the above-mentioned current visiting user and the above-mentioned target dual variable are known; the corresponding target virtual resource is allocated to the above-mentioned current visiting user according to the above-mentioned target virtual resource type.

[0137] In a possible implementation, the virtual resource allocation apparatus 600 further includes:

[0138] The relevant parameter calculation module is used to use machine learning technology to calculate the target relevant parameters of the above-mentioned current visiting user under at least one virtual resource based on the target user characteristics of the above-mentioned current visiting user; the above-mentioned target user characteristics include at least one of the following: target attribute information, target transaction frequency, historical virtual resource allocation and related parameter information.

[0139] In a possible implementation, the virtual resource allocation apparatus 600 further includes:

[0140] a problem construction module, configured to construct the optimization problem based on relevant parameters of the user under at least one virtual resource and a decision variable indicating whether to allocate a virtual resource to the user; the constraints of the optimization problem include that each user is allocated only one virtual resource and that the total cost of the virtual resources allocated to at least one user does not exceed a preset total cost;

[0141] The problem conversion module is used to convert the above optimization problem into a dual problem based on the constraints of the above optimization problem to obtain the above dual function.

[0142] The division of the modules in the above-mentioned virtual resource allocation device is for illustration only. In other embodiments, the virtual resource allocation device can be divided into different modules as needed to complete all or part of the functions of the above-mentioned virtual resource allocation device. The implementation of each module in the virtual resource allocation device provided in the embodiments of the present application can be in the form of a computer program. The computer program can be executed on a terminal or server. The program modules comprising the computer program can be stored in the memory of the terminal or server. When the computer program is executed by a processor, it implements all or part of the steps of the virtual resource allocation method described in the embodiments of the present application.

[0143] See next Figure 7 , Figure 7 This is a schematic diagram of the structure of an electronic device provided by an exemplary embodiment of the present application. Figure 7 As shown, the electronic device 700 may include: at least one processor 710 , at least one network interface 720 , a user interface 730 , a memory 740 , and at least one communication bus 750 .

[0144] The communication bus 750 may be used to implement connection and communication among the above-mentioned components.

[0145] The user interface 730 may include a display and a camera. Optional user interfaces may also include standard wired interfaces and wireless interfaces.

[0146] The network interface 720 may optionally include a Bluetooth module, a Near Field Communication (NFC) module, a Wireless Fidelity (Wi-Fi) module, and the like.

[0147] The processor 710 may include one or more processing cores. The processor 710 utilizes various interfaces and circuits to connect various components within the electronic device 700. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 740 and accessing data stored in the memory 740, the processor 710 performs various functions and processes data within the routing electronic device 700. Optionally, the processor 710 may be implemented in hardware using at least one of a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). The processor 710 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing content displayed on the display; and the modem handles wireless communications. It is understood that the modem may also be implemented independently of the processor 710 and implemented on a separate chip.

[0148] Among them, the memory 740 may include a random access memory (RAM) or a read-only memory (ROM). Optionally, the memory 740 includes a non-transitory computer-readable medium. The memory 740 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 740 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as an acquisition function, a virtual resource allocation function, a dual solution function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 740 may also be optionally at least one storage device located away from the aforementioned processor 710. As Figure 7 As shown, the memory 740 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program.

[0149] In some possible embodiments, the electronic device 700 is the aforementioned Figure 6Regarding the virtual resource allocation device 600 mentioned in the embodiment, the processor 710 can be used to call the virtual resource allocation application stored in the memory 740, and specifically perform the following operations: based on the target attribute information of the currently visiting user, obtain the target dual variable corresponding to the currently visiting user; the target dual variable is the independent variable that enables the dual function corresponding to the optimization problem to obtain the first target value; the optimization problem is used to decide the virtual resources allocated to the user; the target dual variable is predicted based on the historical time series data within the first historical time period; the first historical time period includes multiple different second historical time periods, the historical time series data includes a historical dual variable sequence, and the historical dual variable sequence includes multiple historical dual variables related to the virtual resource allocation within the second historical time period arranged in chronological order; based on the target dual variable, and the target-related parameters of the currently visiting user under at least one virtual resource, allocate the target virtual resource to the currently visiting user.

[0150] In some possible embodiments, the processor 710 is further configured to: obtain historical time series data within a first historical time period; predict a future dual variable sequence based on the historical time series data; the future dual variable sequence includes predicted dual variables that enable the dual function corresponding to the corresponding optimization problem to obtain a first target value within a plurality of different future time periods; the time interval corresponding to the future time period is equal to the time interval corresponding to the second historical time period; and the future dual variable sequence is stored in a database.

[0151] In one possible implementation, the historical time series data also includes at least one of the following data: a historical virtual resource cost sequence, a historical time feature sequence, and a historical traffic sequence within the first historical time period; when the processor 710 executes the above-mentioned acquisition of historical time series data within the first historical time period, it is specifically used to execute: acquiring historical data within the first historical time period; the historical data includes multiple historical dual variables and other relevant historical data related to the virtual resource allocation within the second historical time period; the other relevant historical data include at least one of the following: multiple historical virtual resource costs, historical time information, and historical traffic information corresponding to each of the above-mentioned second historical time periods; the historical data is preprocessed to obtain historical time series data.

[0152] In some possible embodiments, before the processor 710 executes the above-mentioned prediction of the future dual variable sequence based on the above-mentioned historical time series data, it is also used to execute: obtaining a target time series prediction request; the above-mentioned target time series prediction request carries a time series prediction constraint condition, and the above-mentioned time series prediction constraint condition includes that the total cost of the virtual resources allocated to the user in each of multiple different future time periods does not exceed a preset total cost.

[0153] When the processor 710 executes the above-mentioned prediction of the future dual variable sequence based on the above-mentioned historical time series data, it is specifically used to execute: in response to the above-mentioned target time series prediction request, predict the future dual variable sequence based on the above-mentioned time series prediction constraints and the above-mentioned historical time series data.

[0154] In some possible embodiments, the above-mentioned time series prediction constraints include that the total cost of virtual resources allocated to users under the target constraint dimension in multiple different future time periods does not exceed a preset total cost; the above-mentioned target constraint dimension includes at least one of the following: target user group, target user access scenario; when the above-mentioned processor 710 executes the above-mentioned prediction of the future dual variable sequence based on the above-mentioned historical time series data, it is specifically used to execute: in response to the above-mentioned target time series prediction request, predict the future dual variable sequence under the target constraint dimension based on the above-mentioned time series prediction constraints and the above-mentioned historical time series data under the above-mentioned target constraint dimension.

[0155] In some possible embodiments, when the processor 710 executes the above-mentioned prediction of the future dual variable sequence based on the above-mentioned historical time series data, it is specifically used to execute: inputting the above-mentioned historical time series data into a time series prediction model and outputting a future dual variable sequence; the time series prediction model is trained based on sample time series data in a second time period of a plurality of known dual variable sequences in a first time period; the time interval corresponding to the above-mentioned first time period is equal to the time interval corresponding to the above-mentioned second time period, and the above-mentioned first time period is a time period after the above-mentioned second time period.

[0156] In some possible embodiments, when the processor 710 executes the above-mentioned acquisition of historical time series data within the first historical time period, it is specifically configured to execute: periodically acquiring historical time series data of historical access users belonging to the same constraint dimension within the first historical time period at a preset time interval; the constraint dimension includes a user group and / or a user access scenario; and the historical time series data is updated as the first historical time period is updated;

[0157] When the processor 710 executes the above-mentioned prediction of the future dual variable sequence based on the above-mentioned historical time series data, it is specifically configured to execute: predicting the future dual variable sequence of the above-mentioned historical visiting users under the historical constraint dimension corresponding to the above-mentioned historical visiting users based on the historical time series data of the above-mentioned historical visiting users belonging to the same constraint dimension;

[0158] When the processor 710 executes the step of storing the future dual variable sequence into the database, the processor 710 is specifically configured to: associate the future dual variable sequence with the historical constraint dimension identifier corresponding to the historical access user and store them into the database.

[0159] In some possible embodiments, when the processor 710 executes the above-mentioned acquisition of the target dual variable corresponding to the current visiting user based on the target attribute information of the current visiting user, it is specifically used to execute: determining the target group to which the current visiting user belongs based on the target attribute information of the current visiting user; querying the database based on the target group identifier corresponding to the target group and / or the target access scenario identifier corresponding to the current visiting user to obtain the target future dual variable sequence corresponding to the current visiting user; determining the target dual variable corresponding to the current visiting user based on the current access time of the current visiting user and the target future dual variable sequence.

[0160] In some possible embodiments, when the processor 710 executes the above-mentioned allocation of target virtual resources to the current visiting user based on the target dual variable and the target-related parameters of the current visiting user under at least one virtual resource, it is specifically used to execute: searching for the second target value on the decision optimization function corresponding to the dual function based on the target dual variable, the target-related parameters and target virtual resource cost of the current visiting user under at least one virtual resource and at least one virtual resource type to obtain the target virtual resource type; the target virtual resource type is the virtual resource type corresponding to the second target value of the decision optimization function in the at least one virtual resource type when the current visiting user and the target dual variable are known; and allocating the corresponding target virtual resource to the current visiting user according to the target virtual resource type.

[0161] In some possible embodiments, before executing the allocation of the target virtual resource to the current access user based on the target dual variable and the target-related parameter of the current access user under at least one virtual resource, the processor 710 is further configured to execute:

[0162] Using machine learning technology, the target-related parameters of the current visiting user under at least one virtual resource are calculated based on the target user characteristics of the current visiting user; the target user characteristics include at least one of the following: target attribute information, target transaction frequency, historical virtual resource allocation and related parameter information.

[0163] In some possible embodiments, the processor 710 is further configured to execute: constructing the optimization problem based on relevant parameters of the user under at least one virtual resource and a decision variable indicating whether to allocate a virtual resource to the user; the constraints of the optimization problem include that each user is allocated only one virtual resource, and that the total cost of the virtual resources allocated to at least one user does not exceed a preset total cost; based on the constraints of the optimization problem, converting the optimization problem into a dual problem to obtain a dual function.

[0164] The present application also provides a computer-readable storage medium having instructions stored therein that, when executed on a computer or processor, cause the computer or processor to perform one or more steps of the above-described embodiments. If the components of the electronic device described above are implemented as software functional units and sold or used as independent products, they may be stored in the computer-readable storage medium described above.

[0165] In the above embodiments, all or part of the embodiments can be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted via the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a Digital Versatile Disc (DVD)), or a semiconductor medium (eg, a Solid State Disk (SSD)).

[0166] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When executed, the program can include the processes of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks. The technical features of this embodiment and the implementation scheme can be combined in any manner unless they conflict.

[0167] The embodiments described above are merely descriptions of preferred embodiments of the present application and are not intended to limit the scope of the present application. Without departing from the design spirit of the present application, various modifications and improvements made to the technical solutions of the present application by ordinary technicians in this field should fall within the scope of protection determined by the claims.

[0168] The foregoing description describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A virtual resource allocation method, characterized in that: The method comprises: A target dual variable corresponding to the currently visiting user is obtained based on the target attribute information of the currently visiting user; the target dual variable is an independent variable that enables the dual function corresponding to the optimization problem to obtain a first target value; the optimization problem is used to decide on virtual resources to be allocated to the user; the target dual variable is obtained by predicting the independent variable that enables the dual function corresponding to the optimization problem to obtain the first target value in the current time period based on historical time series data in a first historical time period; the first historical time period includes multiple different second historical time periods, the historical time series data includes a historical dual variable sequence, and the historical dual variable sequence includes multiple historical dual variables related to the allocation of virtual resources in the second historical time period, which are arranged in chronological order; A target virtual resource is allocated to the current visiting user based on the target dual variable and a target-related parameter of the current visiting user under at least one virtual resource.

2. The method according to claim 1, wherein The method further comprises: Obtain historical time series data within the first historical time period; Predicting a future dual variable sequence based on the historical time series data; the future dual variable sequence includes predicted dual variables that enable a dual function corresponding to a corresponding optimization problem to obtain a first target value within a plurality of different future time periods; the time interval corresponding to the future time period is equal to the time interval corresponding to the second historical time period; The future dual variable sequence is stored in a database.

3. The method according to claim 2, wherein The historical time series data further includes at least one of the following data: a historical virtual resource cost sequence, a historical time feature sequence, and a historical traffic sequence within the first historical time period; The acquiring of historical time series data within the first historical time period includes: Acquire historical data within a first historical time period; the historical data includes a plurality of historical dual variables related to virtual resource allocation within a second historical time period and other relevant historical data; the other relevant historical data includes at least one of the following: historical virtual resource costs, historical time information, and historical traffic information corresponding to a plurality of respective second historical time periods; The historical data is preprocessed to obtain historical time series data.

4. The method according to claim 2, wherein Before predicting the future dual variable sequence based on the historical time series data, the method further includes: Obtain a target timing prediction request; the target timing prediction request carries a timing prediction constraint, wherein the timing prediction constraint includes that the total cost of virtual resources allocated to the user in multiple different future time periods does not exceed a preset total cost; The predicting of the future dual variable sequence based on the historical time series data includes: In response to the target time series prediction request, a future dual variable sequence is predicted based on the time series prediction constraints and the historical time series data.

5. The method according to claim 4, wherein The time series prediction constraint condition includes that the total cost of virtual resources allocated to users under the target constraint dimension in multiple different future time periods does not exceed a preset total cost; The target constraint dimension includes at least one of the following: target user group, target user access scenario; The predicting of the future dual variable sequence based on the historical time series data includes: In response to the target time series prediction request, a future dual variable sequence under the target constraint dimension is predicted based on the time series prediction constraint condition and the historical time series data under the target constraint dimension.

6. The method according to claim 2, wherein The predicting of the future dual variable sequence based on the historical time series data includes: The historical time series data is input into a time series prediction model to output a future dual variable sequence; the time series prediction model is trained based on sample time series data in a second time period of multiple known dual variable sequences in a first time period; the time interval corresponding to the first time period is equal to the time interval corresponding to the second time period, and the first time period is the time period after the second time period.

7. The method according to claim 2, wherein The acquiring of historical time series data within the first historical time period includes: Obtaining historical time series data of historical access users belonging to the same constraint dimension within a first historical time period at preset time intervals; the constraint dimension includes user groups and / or user access scenarios; and the historical time series data is updated as the first historical time period is updated; The predicting of the future dual variable sequence based on the historical time series data includes: Predicting the future dual variable sequence of the historical visiting user under the corresponding historical constraint dimension based on the historical time series data of the historical visiting user belonging to the same constraint dimension; The storing of the future dual variable sequence into a database comprises: The future dual variable sequence and the historical constraint dimension identifier corresponding to the historical access user are associated and stored in a database.

8. The method according to claim 7, wherein The step of obtaining a target dual variable corresponding to the current visiting user based on the target attribute information of the current visiting user includes: Determining the target group to which the current visiting user belongs based on the target attribute information of the current visiting user; Based on the target group identifier corresponding to the target group and / or the target access scenario identifier corresponding to the current access user, a query is performed in the database to obtain a target future dual variable sequence corresponding to the current access user; The target dual variable corresponding to the current visiting user is determined based on the current visiting time of the current visiting user and the target future dual variable sequence.

9. The method according to claim 1, wherein The allocating a target virtual resource to the current visiting user based on the target dual variable and the target-related parameter of the current visiting user under at least one virtual resource includes: Based on the target dual variable, the target-related parameters and target virtual resource cost of the current access user under at least one virtual resource, and at least one virtual resource type, a search is performed for a second target value on the decision optimization function corresponding to the dual function to obtain a target virtual resource type; the target virtual resource type is a virtual resource type in the at least one virtual resource type that corresponds to the second target value of the decision optimization function when the current access user and the target dual variable are known; The corresponding target virtual resource is allocated to the current access user according to the type of the target virtual resource.

10. The method according to claim 1, wherein Before allocating a target virtual resource to the current visiting user based on the target dual variable and the target-related parameter of the current visiting user under at least one virtual resource, the method further includes: Using machine learning technology, the target-related parameters of the current visiting user under at least one virtual resource are calculated based on the target user characteristics of the current visiting user; the target user characteristics include at least one of the following: target attribute information, target transaction frequency, historical virtual resource allocation and related parameter information.

11. The method according to any one of claims 1 to 10, wherein: The method further comprises: The optimization problem is constructed based on relevant parameters of the user under at least one virtual resource and a decision variable indicating whether to allocate a virtual resource to the user; the constraints of the optimization problem include that each user is allocated only one virtual resource and that the total cost of the virtual resources allocated to at least one user does not exceed a preset total cost; Based on the constraints of the optimization problem, the optimization problem is transformed into a dual problem to obtain the dual function.

12. A virtual resource allocation method, characterized in that: The method comprises: Obtaining a target virtual resource allocated to a current access user according to the virtual resource allocation method according to any one of claims 1 to 11; The target virtual resource is displayed.

13. A virtual resource allocation device, characterized in that: The virtual resource allocation device includes: An acquisition module is configured to acquire a target dual variable corresponding to a currently visiting user based on target attribute information of the currently visiting user; the target dual variable is an independent variable that enables a dual function corresponding to an optimization problem to obtain a first target value; the optimization problem is used to decide on virtual resources to be allocated to a user; the target dual variable is obtained by predicting an independent variable that enables a dual function corresponding to the optimization problem to obtain a first target value within a current time period based on historical time series data within a first historical time period; the first historical time period includes a plurality of different second historical time periods, the historical time series data includes a historical dual variable sequence, and the historical dual variable sequence includes a plurality of historical dual variables related to virtual resource allocation within the second historical time period, arranged in chronological order; The virtual resource allocation module is configured to allocate target virtual resources to the current visiting user based on the target dual variable and target-related parameters of the current visiting user under at least one virtual resource.

14. An electronic device, characterized in that: include: processor and memory; The processor is connected to the memory; The memory is used to store executable program code; The processor reads the executable program code stored in the memory to run a program corresponding to the executable program code, so as to execute the method steps according to any one of claims 1 to 12.

15. A computer storage medium, characterized in that The computer storage medium stores a plurality of instructions, which are suitable for being loaded by a processor and executing the method steps according to any one of claims 1 to 12.

Images