CN117314030A - Virtual resource issuing method and device - Google Patents
Virtual resource issuing method and device Download PDFInfo
- Publication number
- CN117314030A CN117314030A CN202310126972.4A CN202310126972A CN117314030A CN 117314030 A CN117314030 A CN 117314030A CN 202310126972 A CN202310126972 A CN 202310126972A CN 117314030 A CN117314030 A CN 117314030A
- Authority
- CN
- China
- Prior art keywords
- merchant
- virtual resource
- target
- amount
- optimization problem
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000005457 optimization Methods 0.000 claims abstract description 96
- 230000009977 dual effect Effects 0.000 claims description 64
- 230000006870 function Effects 0.000 claims description 11
- 238000003860 storage Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 description 14
- 239000013598 vector Substances 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 239000002699 waste material Substances 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000013178 mathematical model Methods 0.000 description 3
- 230000002829 reductive effect Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005304 joining Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 229920001690 polydopamine Polymers 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 239000004984 smart glass Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
One or more embodiments of the present disclosure provide a virtual resource issuing method and apparatus, where the method includes: constructing an optimization problem based on historical user order amounts of at least one merchant under at least one virtual resource amount, and historical decision variables representing whether to allocate one virtual resource amount to one merchant; wherein the objective of optimizing the problem comprises solving a maximum of a sum of user orders for at least one merchant; constraints on the optimization problem include that only one virtual resource amount is allocated to one merchant, and that the sum of the virtual resource amounts allocated to at least one merchant does not exceed a preset threshold; updating the optimization problem based on the predicted user order quantity of the target merchant under at least one virtual resource quantity and a target decision variable indicating whether to allocate one virtual resource quantity to the target merchant, and solving the updated optimization problem to determine the value of the target decision variable; and allocating a target virtual resource amount for the target merchant based on the target decision variable.
Description
Technical Field
One or more embodiments of the present disclosure relate to the field of computer application technologies, and in particular, to a method and apparatus for virtual resource issuing.
Background
Nowadays, with the development of internet technology, online shopping is becoming more and more popular. A user may purchase goods from a merchant over the internet, for example: the user can use the take-out APP (Application) to purchase food from restaurants near the location, articles of daily use from supermarkets near the location, medicines from drugstores near the location, and the like, and the goods purchased by the user can be subsequently distributed to the user by a distributor (such as take-out rider), so that the trouble that the user needs to go to an entity store on line with the merchant for purchasing the goods can be avoided. Typically, after a user purchases a commodity from a merchant, a corresponding user order is created for the user to distribute the commodity for the user according to the user order, and this process is a user ordering process.
For each platform providing online shopping service for users, the range of online services provided based on the Internet already covers most users, new users are limited in growth, and each platform is more and more competitive for stock users. Under the situation, the improvement of the user ordering rate is a key for expanding the market share advantage, and the mode of issuing virtual resources to the user is adopted to attract the user to participate in the marketing activities, so that the user ordering rate can be effectively improved, and the user viscosity can be enhanced. However, if the amount of the issued virtual resources is too small, the user ordering is not easy to pry, and the user ordering rate is affected; if the amount of the released virtual resources is too large, virtual resource waste is easy to be caused, and the consumption budget of the platform on the virtual resources can be consumed in advance, so that the duration of the marketing activity is insufficient, the perception of the marketing activity by a user is influenced, and the ordering rate of the user is influenced. Therefore, how to balance the relationship between the virtual resource amount and the user ordering rate is an important point and difficulty of the platform in the marketing cycle.
Disclosure of Invention
One or more embodiments of the present disclosure provide the following technical solutions:
the specification provides a virtual resource issuing method, which comprises the following steps:
constructing an optimization problem for deciding on the amount of virtual resources allocated to at least one merchant based on the historical user order amount of the at least one merchant under the at least one amount of virtual resources and a historical decision variable representing whether to allocate one amount of virtual resources to the at least one merchant; wherein the objective of the optimization problem comprises solving a maximum of a sum of user orders for the at least one merchant; constraints of the optimization problem include that only one virtual resource amount is allocated to one merchant, and that the sum of the virtual resource amounts allocated to the at least one merchant does not exceed a preset threshold;
acquiring a predicted user order quantity of a target merchant under the at least one virtual resource quantity;
updating the optimization problem based on the predicted user order quantity and a target decision variable representing whether a virtual resource quantity is allocated to the target merchant, and solving the updated optimization problem to determine the value of the target decision variable;
And distributing a target virtual resource amount to the target merchant based on the target decision variable so as to distribute virtual resources to users through the target merchant according to the target virtual resource amount.
The present specification also provides a virtual resource issuing apparatus, the apparatus comprising:
a construction module for constructing an optimization problem for deciding the amount of virtual resources allocated to at least one merchant based on the amount of historical user orders of the at least one merchant under the amount of at least one virtual resource and a historical decision variable representing whether to allocate one amount of virtual resources to the at least one merchant; wherein the objective of the optimization problem comprises solving a maximum of a sum of user orders for the at least one merchant; constraints of the optimization problem include that only one virtual resource amount is allocated to one merchant, and that the sum of the virtual resource amounts allocated to the at least one merchant does not exceed a preset threshold;
the obtaining module is used for obtaining the predicted user order quantity of the target merchant under the at least one virtual resource quantity;
the solving module is used for updating the optimization problem based on the predicted user order quantity and a target decision variable which indicates whether a virtual resource quantity is distributed to the target merchant, and solving the updated optimization problem so as to determine the value of the target decision variable;
And the allocation module is used for allocating target virtual resource quantity to the target merchant based on the target decision variable so as to issue virtual resources to a user through the target merchant according to the target virtual resource quantity.
The present specification also provides an electronic apparatus including:
a processor;
a memory for storing processor-executable instructions;
wherein the processor implements the steps of the method as described in any of the preceding claims by executing the executable instructions.
The present specification also provides a computer readable storage medium having stored thereon computer instructions which when executed by a processor perform the steps of the method as claimed in any one of the preceding claims.
In the above technical solution, an optimization problem may be constructed based on a historical user order quantity of at least one merchant under at least one virtual resource quantity, and a historical decision variable indicating whether to allocate a virtual resource quantity to one merchant, the objective of the optimization problem includes solving a maximum value of a sum of user order quantities of the merchants, constraint conditions of the optimization problem include that only one virtual resource quantity is allocated to one merchant, and the sum of virtual resource quantities allocated to the merchants does not exceed a threshold value, and a predicted user order quantity of a target merchant under the virtual resource quantities is obtained, and based on the predicted user order quantities, and a objective decision variable indicating whether to allocate a virtual resource quantity to the target merchant, the optimization problem is updated, and the updated objective decision variable is solved to determine a value of the objective decision variable, and finally, the objective virtual resource quantity may be allocated to the target merchant based on the objective decision variable, so that virtual resources are allocated to a user by the target merchant according to the objective virtual resource quantity, so that the user may use the obtained virtual resources are ordered at the objective merchant to enjoy the corresponding preferential.
In this way, the maximum value of the sum of the user orders of the merchants when one and only one virtual resource amount is allocated to one merchant and the sum of the virtual resource amounts allocated to the merchants does not exceed the threshold value can be calculated according to the historical user order amounts of the merchants under various virtual resource amounts and the predicted user order amounts of the target merchants needing to be allocated with the virtual resource amounts under various virtual resource amounts, so that the target virtual resource amount can be allocated to the target merchant according to the virtual resource amount allocated to the target merchant so that the sum of the user order amounts of the merchants is the maximum. Therefore, a related theory of solving the optimal solution by linear programming is introduced, the maximization of the user order quantity is targeted, only one virtual resource quantity is allocated to one merchant, and the sum of the virtual resource quantities does not exceed a threshold value as a constraint condition, a mathematical model is established to solve the virtual resource quantity allocated to each merchant, the probability that the situation that the virtual resource quantity is too small to attract a user to order or the virtual resource quantity is too large to cause virtual resource waste can be reduced, and the balance between the virtual resource quantity and the user ordering rate is realized.
Drawings
FIG. 1 is a schematic diagram of a virtual resource provisioning system according to an exemplary embodiment of the present disclosure;
FIG. 2 is a flow chart of a virtual resource provisioning method according to an exemplary embodiment of the present disclosure;
FIG. 3 is a schematic illustration of a predictive model shown in an exemplary embodiment of the present disclosure;
FIG. 4 is a schematic diagram of another predictive model shown in an exemplary embodiment of the present disclosure;
FIG. 5 is a flow chart illustrating a virtual resource provisioning method according to an exemplary embodiment of the present disclosure;
fig. 6 is a hardware configuration diagram of an electronic device in which a virtual resource issuing apparatus is located, according to an exemplary embodiment of the present disclosure;
fig. 7 is a block diagram of a virtual resource issuing apparatus according to an exemplary embodiment of the present specification.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with one or more embodiments of the present specification. Rather, they are merely examples of apparatus and methods consistent with aspects of one or more embodiments of the present description as detailed in the accompanying claims.
It should be noted that: in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this specification. In some other embodiments, the method may include more or fewer steps than described in this specification. Furthermore, individual steps described in this specification, in other embodiments, may be described as being split into multiple steps; while various steps described in this specification may be combined into a single step in other embodiments.
For a platform providing online shopping services for users, multiple merchants of multiple types can join the platform, and the merchants can create corresponding electronic stores on the platform, so that the users can select and place orders in the electronic stores to purchase goods from the merchants. In this case, the user order rate of the platform may be reflected by the sum of the user order amounts of the merchants, and the greater the sum of the user order amounts of the merchants, the higher the user order rate of the platform is explained.
In general, the platform allocates different amounts of virtual resources to different merchants according to actual demands, so as to issue different amounts of virtual resources to users through different merchants, and users can use the obtained virtual resources to place orders at the merchants to enjoy corresponding offers. In practical applications, the virtual resource may be a subsidy, a coupon, or a virtual score, and accordingly the virtual resource amount may be a subsidy amount, a denomination of a coupon, or a virtual score, which is not limited in this specification.
For example, assuming that the merchant on which the electronic store is created on the platform includes merchant A and merchant B, the subsidy amount allocated by the platform for merchant A may be 5 yuan and the subsidy amount allocated for merchant B may be 7 yuan; at this time, the platform may issue sufficient patches to the merchant a and the merchant B, respectively, so that the merchant a may issue 5-membered patches to the user who places the order at the merchant a, that is, the user may enjoy 5-membered offers when placing the order at the merchant a, and the merchant B may issue 7-membered patches to the user who places the order at the merchant B, that is, the user may enjoy 7-membered offers when placing the order at the merchant B.
However, for any merchant, the amount of virtual resources that the platform issues to the user through the merchant is either too small or too large, which affects the user order rate of the platform, i.e., the amount of user orders by the merchant. Because the user order amounts of the same merchant under different virtual resource amounts are different, in order to balance the relationship between the virtual resource amounts and the user order rates of the platform, the sum of the user order amounts of all merchants under the virtual resource amounts respectively allocated to the merchants by the platform can be limited according to actual requirements, for example: the sum of the user order amounts of all merchants under the virtual resource amounts respectively allocated to the merchants by the platform is maximized. In this case, the problem of how to balance the relationship between the virtual resource amount and the user order rate of the platform translates into the problem of how to allocate the virtual resource amount for each merchant for the platform.
The specification provides a technical scheme for virtual resource amount allocation. In the technical scheme, an optimization problem can be constructed based on historical user order quantity of at least one merchant under at least one virtual resource quantity and a historical decision variable representing whether to allocate one virtual resource quantity to one merchant, the objective of the optimization problem comprises solving the maximum value of the sum of the user order quantities of the merchants, the constraint condition of the optimization problem comprises that only one virtual resource quantity is allocated to one merchant, the sum of the virtual resource quantities allocated to the merchants does not exceed a threshold value, the predicted user order quantity of the target merchant under the virtual resource quantities is obtained, the optimization problem is updated based on the predicted user order quantities and a target decision variable representing whether to allocate one virtual resource quantity to the target merchant, the updated optimization problem is solved to determine the value of the target decision variable, finally, the target virtual resource quantity can be allocated to the target merchant based on the target decision variable, virtual resources are allocated to users through the target merchant according to the target virtual resource quantity, and the users can use the obtained virtual resources to place the target merchant for enjoyment.
In particular implementations, there may be at least one merchant that provides online shopping services to users through the platform, and there may also be at least one virtual resource amount allocated by the platform to those merchants. That is, the platform may allocate the same amount of virtual resources for the merchants, or may allocate different amounts of virtual resources for different merchants.
For the above platform, an optimization problem for deciding the amount of virtual resources allocated to each of the merchants may be constructed based on the historical user order amounts of at least one merchant under at least one amount of virtual resources, and historical decision variables representing whether to allocate one amount of virtual resources to one merchant.
Wherein, since the user order rate of the platform can be reflected by the sum of the user order amounts of all merchants, the objective of the optimization problem can also include: solving for a maximum value of the sum of the user order amounts of each merchant in the at least one merchant under the virtual resource amount allocated for the merchant.
Since the spending budget of a platform on virtual resources is typically limited, and a platform will typically allocate only one amount of virtual resources to merchants, constraints on the optimization problem described above may include: (1) There is and only one virtual resource amount assigned to one merchant; (2) The sum of the amounts of virtual resources allocated to the merchants of the at least one merchant does not exceed a preset threshold (which may be specifically set according to actual needs).
For any merchant for which a virtual resource amount needs to be allocated (which may be referred to as a target merchant; e.g., a merchant newly joining the platform, or a merchant participating in a new marketing campaign, etc.), a predicted user order amount for that target merchant under each of the at least one virtual resource amounts may be obtained.
In the case where the predicted user order amounts are obtained, the optimization problem may be updated based on the predicted user order amounts and a decision variable (which may be referred to as a target decision variable) indicating whether or not to assign a virtual resource amount to the target merchant.
That is, the updated optimization problem described above may be considered an optimization problem configured to determine the amount of virtual resources allocated to the at least one merchant and each of the target merchants based on the historical user order amount of the at least one merchant under the at least one virtual resource amount, the predicted user order amount of the target merchant under the at least one virtual resource amount, and the historical decision variable indicating whether to allocate one virtual resource amount to one merchant, the target decision variable indicating whether to allocate one virtual resource amount to the target merchant. Accordingly, the updated objective of the optimization problem may include solving a maximum of a sum of user orders for each of the at least one merchant and the target merchants under the amount of virtual resources allocated for the merchant; the updated constraint of the optimization problem may include: (1) There is and only one virtual resource amount assigned to one merchant; (2) The sum of the amounts of virtual resources allocated to each of the at least one merchant and the target merchant does not exceed the threshold.
In the above case, the updated optimization problem may be solved to determine the value of the target decision variable.
When the decision variable is calculated, a virtual resource amount (which may be referred to as a target virtual resource amount) may be allocated to the target merchant based on the calculated decision variable, so that virtual resources may be issued to the user by the target merchant according to the target virtual resource amount, that is, the number of virtual resources issued to the user by the target merchant is equal to the target virtual resource amount.
In this way, the maximum value of the sum of the user orders of the merchants when one and only one virtual resource amount is allocated to one merchant and the sum of the virtual resource amounts allocated to the merchants does not exceed the threshold value can be calculated according to the historical user order amounts of the merchants under various virtual resource amounts and the predicted user order amounts of the target merchants needing to be allocated with the virtual resource amounts under various virtual resource amounts, so that the target virtual resource amount can be allocated to the target merchant according to the virtual resource amount allocated to the target merchant so that the sum of the user order amounts of the merchants is the maximum. Therefore, a related theory of solving the optimal solution by linear programming is introduced, the maximization of the user order quantity is targeted, only one virtual resource quantity is allocated to one merchant, and the sum of the virtual resource quantities does not exceed a threshold value as a constraint condition, a mathematical model is established to solve the virtual resource quantity allocated to each merchant, the probability that the situation that the virtual resource quantity is too small to attract a user to order or the virtual resource quantity is too large to cause virtual resource waste can be reduced, and the balance between the virtual resource quantity and the user ordering rate is realized.
Referring to fig. 1, fig. 1 is a schematic diagram of a virtual resource provisioning system according to an exemplary embodiment of the present disclosure.
As shown in fig. 1, in the virtual resource provisioning system, a user client may be installed on an electronic device used by a user, a merchant client may be installed on an electronic device used by a merchant, and a server may include a platform for providing an online shopping service to the user; the platform may provide online shopping services to users through user clients.
The server may run on a physical server comprising an independent host, or may run on a virtual server, cloud server, etc. carried by the host cluster. The electronic device on which the user client is mounted may be a mobile phone, a tablet device, a notebook computer, a palm computer (PDAs, personal Digital Assistants), a wearable device (such as smart glasses, smart watches, etc.), and the present disclosure is not limited to this embodiment. The electronic device on which the merchant client is installed may be a desktop computer, a tablet device, a notebook computer, a palm top computer, a wearable device, etc., and one or more embodiments of the present disclosure are not limited in this regard. The server may communicate with the user client and the merchant client via various types of wired or wireless networks.
Specifically, the platform can output a user interface for realizing online shopping to a user through a user client, so that the user can execute interactive operations such as clicking, double clicking, long pressing and the like in the user interface to finish online shopping. After the user selects a merchant through the user interface and purchases goods at the merchant, the user client can create a corresponding user order for the user and remind the user to pay for the user order; after the user completes payment for the user order, the user client may send the user order to the platform, which alerts the merchant to follow-up processing for the user order.
Subsequently, when the platform receives the user order sent by the user client, the user order may be further sent to a merchant client corresponding to the merchant, and the merchant performs subsequent processing such as commodity preparation (for example, assuming that the commodity selected and purchased by the user is a jin orange, the merchant may prepare a jin orange as the commodity corresponding to the commodity) and commodity distribution according to the user order.
In practical application, the platform can allocate various virtual resource amounts for each merchant, so that the user order amounts of each merchant under various virtual resource amounts can be obtained through statistics.
Referring to fig. 2 in conjunction with fig. 1, fig. 2 is a flowchart illustrating a virtual resource issuing method according to an exemplary embodiment of the present disclosure.
The virtual resource issuing method can be applied to a server (i.e. a platform for providing online shopping service for users) as shown in fig. 1, and may include the following steps:
step 201: constructing an optimization problem for deciding on the amount of virtual resources allocated to at least one merchant based on the historical user order amount of the at least one merchant under the at least one amount of virtual resources and a historical decision variable representing whether to allocate one amount of virtual resources to the at least one merchant; wherein the objective of the optimization problem comprises solving a maximum of a sum of user orders for the at least one merchant; constraints of the optimization problem include that only one virtual resource amount is allocated to one merchant, and that the sum of the virtual resource amounts allocated to the at least one merchant does not exceed a preset threshold.
In this embodiment, at least one merchant providing online shopping services to users through the platform may be provided, and at least one virtual resource amount allocated to the merchants by the platform may also be provided. That is, the platform may allocate the same amount of virtual resources for the merchants, or may allocate different amounts of virtual resources for different merchants.
For the above platform, an optimization problem for deciding the amount of virtual resources allocated to each of the merchants may be constructed based on the historical user order amounts of at least one merchant under at least one amount of virtual resources, and historical decision variables representing whether to allocate one amount of virtual resources to one merchant.
As described above, the platform can allocate various virtual resource amounts to each merchant, so that the user order amounts of each merchant under various virtual resource amounts can be obtained statistically. Thus, the historical user order amount of the at least one merchant under the at least one virtual resource amount may specifically be a user order amount of the at least one merchant under the at least one virtual resource amount within a certain historical period counted by the platform. Accordingly, a historical decision variable indicating whether a virtual resource amount is allocated to a merchant may be specifically a decision variable indicating whether a virtual resource amount is allocated to a merchant during the historical time period. It should be noted that the historical time period may be the same or different for different merchants, and one or more embodiments of the present disclosure are not limited in this regard.
For example, assuming that I (i=1, 2, …, I) represents one virtual resource amount, i=1 represents a first virtual resource amount, i=2 represents a second virtual resource amount, i=i represents an I-th virtual resource amount, J (j=1, 2, …, J) represents one merchant, j=1 represents a first merchant, j=2 represents a second merchant, j=j represents a J-th merchant, then c ij May be the user order quantity, x, of merchant j under virtual resource quantity i ij May be a decision variable indicating whether to assign a virtual resource amount i to merchant j. At this time, c can be based on ij (i=1, 2, …, I, j=1, 2, …, J), and x ij (i=1, 2, …, I, j=1, 2, …, J) an optimization problem for deciding the amount of virtual resources allocated to merchant J (j=1, 2, …, J) is constructed. Generally, x ij =0 means that no virtual resource amount i is assigned to merchant j, x ij =1 means that the virtual resource amount i is assigned to merchant j.
Wherein, since the user order rate of the platform can be reflected by the sum of the user order amounts of all merchants, the objective of the optimization problem can also include: solving for a maximum value of the sum of the user order amounts of each merchant in the at least one merchant under the virtual resource amount allocated for the merchant.
Continuing with the above example, the user order volume for merchant j under the virtual resource volume allocated for that merchant may be represented asThe sum of the user order amounts of each of the at least one merchant under the amount of virtual resources allocated to that merchant can thus be expressed as +.>At this time, the targets of the above-described optimization problem may include: solving->Is a maximum value of (a).
Since the spending budget of a platform on virtual resources is typically limited, and a platform will typically allocate only one amount of virtual resources to merchants, constraints on the optimization problem described above may include: (1) There is and only one virtual resource amount assigned to one merchant; (2) The sum of the amounts of virtual resources allocated to the merchants of the at least one merchant does not exceed a preset threshold (which may be specifically set according to actual needs).
In some embodiments, to ensure real-time performance of the optimization problem, the platform may periodically obtain historical user order amounts of at least one merchant under at least one virtual resource amount according to a preset time period (the time period may be specifically set according to actual requirements), and a historical decision variable indicating whether to allocate one virtual resource amount to one merchant, and construct the optimization problem based on the obtained historical user order amounts and the historical decision variables. Wherein the historical order volume may be the user order volume during the current time period and the historical decision variable may be the decision variable during the current time period.
For example, assuming the time period is 12 hours, the platform may obtain, at 12 points in the day, the user order amounts for at least one merchant in the 0-12 points in the day for at least one virtual resource amount, and decision variables in the 0-12 points in the day indicating whether to allocate one virtual resource amount to one merchant, and construct the optimization problem based on the user order amounts and the decision variables in the 0-12 points in the day; and at 24 points on the day (i.e., 0 point on the next day), obtaining user order amounts for at least one merchant in at least one virtual resource amount from 12 points on the day to 24 points on the day, and decision variables representing whether to allocate one virtual resource amount to one merchant from 12 points on the day to 24 points on the day, and reconstructing the optimization problem based on the user order amounts and the decision variables from 12 points on the day to 24 points on the day; and so on.
By periodically acquiring the historical user order quantity and the historical decision variable according to the time period and constructing the optimization problem based on the acquired historical user order quantity and the historical decision variable, the problem that the change of the user order quantity of a merchant under a certain virtual resource quantity cannot be reflected on the constructed optimization problem in reality, namely the constructed optimization problem cannot be changed along with the change of the user order quantity and the historical decision variable can be avoided, and therefore the instantaneity of the user order quantity and the decision variable for constructing the optimization problem can be ensured, and the instantaneity of the constructed optimization problem can be ensured.
Step 202: a predicted user order quantity of the target merchant under the at least one virtual resource quantity is obtained.
In this embodiment, the predicted user order volume for any merchant for which a virtual resource volume needs to be allocated (which may be referred to as a target merchant; e.g., a merchant newly joining the platform, or a merchant participating in a new marketing campaign, etc.), may be obtained for each of the at least one virtual resource volumes.
In practical applications, the platform does not have the user order volume of the target merchant under various virtual resource volumes, because the target merchant is a merchant that needs to be allocated with a virtual resource volume, which means that the target merchant may not be allocated with a virtual resource volume before. In this case, the predicted user order quantity of the target merchant under the at least one virtual resource quantity may specifically be a user order quantity predicted by the platform based on the relevant information of the target merchant and the at least one virtual resource quantity. Alternatively, if the platform has the user order amounts of the target merchant under various virtual resource amounts (for example, the user order amounts of the target merchant under various virtual resource amounts obtained by statistics when the target merchant participates in the previous marketing campaign), the historical user order amounts of the target merchant under the at least one virtual resource amount may also be directly used as the predicted user order amounts of the target merchant under the at least one virtual resource amount. The present description is not limited in one or more embodiments.
In some embodiments, to improve the convenience of obtaining the predicted user order quantity, the platform may use a machine learning model to calculate, based on the relevant information of the target merchant and the at least one virtual resource quantity, a predicted user order quantity of the target merchant under the virtual resource quantities. Wherein the relevant information of the target merchant may be data that may affect the user order volume of the target merchant, which may be referred to as merchant feature data.
Specifically, the platform may first obtain the merchant feature data of the target merchant, and then input the obtained merchant feature data of the target merchant and the at least one virtual resource amount into a machine learning model (may be referred to as a prediction model) for predicting a user order amount, so that the prediction model may determine, based on the merchant feature data of the target merchant and the at least one virtual resource amount, a predicted user order amount of the target merchant under the virtual resource amounts. The prediction model may be a machine learning model obtained by supervised learning based on training samples, and for any training sample, the training sample may include merchant feature data of a merchant and a virtual resource amount, and the training sample may be labeled with a user order amount of the merchant under the virtual resource amount. Accordingly, the target merchant's merchant characteristics and a virtual resource amount may be input into the predictive model to determine, by the predictive model, a predicted user order amount for the target merchant at the virtual resource amount based on the target merchant's merchant characteristics data and the virtual resource amount.
In some embodiments, the predictive model may be DNN (Deep Neural Network ).
In some embodiments, the merchant characteristic data may include one or more of the data shown below: user base data (User Base Feature); user sequence data (User Sequence Feature); merchant base data (Shop Base Feature); context data (Context Feature).
As shown in fig. 3, when determining a predicted user order amount of a merchant under a virtual resource amount by the above prediction model, embedding (embedding) may be performed on merchant feature data of the merchant and the virtual resource amount to obtain feature vectors corresponding to the merchant feature data of the merchant and the virtual resource amount, and then these feature vectors are input into the DNN to calculate, and the DNN outputs the predicted user order amount of the merchant under the virtual resource amount.
Or, as shown in fig. 4, when determining the predicted user order quantity of a merchant under a virtual resource quantity by the above prediction model, embedding (embedding) may be performed on merchant feature data of the merchant to obtain first feature vectors corresponding to the merchant feature data of the merchant, then the first feature vectors are input into a front part layer of the DNN to perform a calculation once to obtain processed first feature vectors, and then the virtual resource quantity may be subjected to embedding processing to obtain second feature vectors corresponding to the virtual resource quantity, and the second feature vectors and the processed first feature vectors are input into a rear part layer of the DNN to perform a second calculation, so that the predicted user order quantity of the merchant under the virtual resource quantity is output by the DNN.
By using the machine learning model to determine the predicted user order quantity of the merchant under the virtual resource quantity based on the relevant information of the merchant and the virtual resource quantity, the convenience in acquiring the predicted user order quantity can be improved, and the accuracy of the acquired predicted user order quantity can be ensured.
Step 203: updating the optimization problem based on the predicted user order quantity and a target decision variable indicating whether to allocate a virtual resource quantity to the target merchant, and solving the updated optimization problem to determine the value of the target decision variable.
In the present embodiment, in the case where the predicted user order amounts are acquired, the optimization problem may be updated based on the predicted user order amounts and a decision variable (which may be referred to as a target decision variable) indicating whether or not to assign a virtual resource amount to the target merchant.
That is, the updated optimization problem described above may be considered an optimization problem configured to determine the amount of virtual resources allocated to the at least one merchant and each of the target merchants based on the historical user order amount of the at least one merchant under the at least one virtual resource amount, the predicted user order amount of the target merchant under the at least one virtual resource amount, and the historical decision variable indicating whether to allocate one virtual resource amount to one merchant, the target decision variable indicating whether to allocate one virtual resource amount to the target merchant. Accordingly, the updated objective of the optimization problem may include solving a maximum of a sum of user orders for each of the at least one merchant and the target merchants under the amount of virtual resources allocated for the merchant; the updated constraint of the optimization problem may include: (1) There is and only one virtual resource amount assigned to one merchant; (2) The sum of the amounts of virtual resources allocated to each of the at least one merchant and the target merchant does not exceed the threshold.
In the above case, the updated optimization problem may be solved to determine the value of the target decision variable.
Step 204: and distributing a target virtual resource amount to the target merchant based on the target decision variable so as to distribute virtual resources to users through the target merchant according to the target virtual resource amount.
In this embodiment, when the decision variable is calculated, a virtual resource amount (may be referred to as a target virtual resource amount) may be allocated to the target merchant based on the calculated decision variable, so that virtual resources may be issued to the user by the target merchant according to the target virtual resource amount, that is, the number of virtual resources issued to the user by the target merchant is equal to the target virtual resource amount.
In the above technical solution, an optimization problem may be constructed based on a historical user order quantity of at least one merchant under at least one virtual resource quantity, and a historical decision variable indicating whether to allocate a virtual resource quantity to one merchant, the objective of the optimization problem includes solving a maximum value of a sum of user order quantities of the merchants, constraint conditions of the optimization problem include that only one virtual resource quantity is allocated to one merchant, and the sum of virtual resource quantities allocated to the merchants does not exceed a threshold value, and a predicted user order quantity of a target merchant under the virtual resource quantities is obtained, and based on the predicted user order quantities, and a objective decision variable indicating whether to allocate a virtual resource quantity to the target merchant, the optimization problem is updated, and the updated objective decision variable is solved to determine a value of the objective decision variable, and finally, the objective virtual resource quantity may be allocated to the target merchant based on the objective decision variable, so that virtual resources are allocated to a user by the target merchant according to the objective virtual resource quantity, so that the user may use the obtained virtual resources are ordered at the objective merchant to enjoy the corresponding preferential.
In this way, the maximum value of the sum of the user orders of the merchants when one and only one virtual resource amount is allocated to one merchant and the sum of the virtual resource amounts allocated to the merchants does not exceed the threshold value can be calculated according to the historical user order amounts of the merchants under various virtual resource amounts and the predicted user order amounts of the target merchants needing to be allocated with the virtual resource amounts under various virtual resource amounts, so that the target virtual resource amount can be allocated to the target merchant according to the virtual resource amount allocated to the target merchant so that the sum of the user order amounts of the merchants is the maximum. Therefore, a related theory of solving the optimal solution by linear programming is introduced, the maximization of the user order quantity is targeted, only one virtual resource quantity is allocated to one merchant, and the sum of the virtual resource quantities does not exceed a threshold value as a constraint condition, a mathematical model is established to solve the virtual resource quantity allocated to each merchant, the probability that the situation that the virtual resource quantity is too small to attract a user to order or the virtual resource quantity is too large to cause virtual resource waste can be reduced, and the balance between the virtual resource quantity and the user ordering rate is realized.
In some embodiments, to reduce the amount of computation in solving the above-described optimization problem, the optimization problem may be converted into a dual problem according to a method of converting the original problem into the dual problem in linear programming. And accordingly, the objective of the dual problem may include solving a minimum of the dual function corresponding to the optimization problem. In the process of converting the above-mentioned optimization problem into the above-mentioned dual problem, it is necessary to introduce a dual variable. That is, the above-described dual function may include the dual variable.
In the above case, the above-described dual problem may be solved to determine the value of the dual variable in the dual problem. Specifically, the value of the dual variable that minimizes the function value of the dual function may be determined based on the historical user order quantity of the at least one merchant under the at least one virtual resource quantity, the historical decision variable that indicates whether to assign a virtual resource quantity to a merchant, and the threshold.
In determining the value of the target decision variable, the dual problem may be updated based on the predicted user order quantity of the target merchant under the at least one virtual resource quantity and the target decision variable indicating whether to assign a virtual resource quantity to the target merchant, and the updated dual problem may be solved according to the value of the dual variable determined as described above to determine the values of the target decision variables. The updated dual problem is the same as the dual problem which is converted from the updated optimization problem according to the method for converting the original problem into the dual problem in the linear programming.
Fig. 5 is a flowchart illustrating a virtual resource provisioning method according to an exemplary embodiment of the present disclosure. As shown in fig. 5, the platform may solve the dual problem based on the historical user order volume of the at least one merchant at the at least one virtual resource volume, the historical decision variable indicating whether to assign a virtual resource volume to a merchant, and the threshold to determine the value of the dual variable in the dual problem. Since this process does not require the involvement of the target merchant in predicting the user order volume, the value of the dual variable may be determined by means of offline calculations.
Correspondingly, the platform may update the dual problem based on the predicted user order volume of the target merchant under the at least one virtual resource volume and a target decision variable indicating whether to assign a virtual resource volume to the target merchant, and solve the updated dual problem according to the value of the dual variable determined by the offline computing process to determine the values of the target decision variables. In this process, the values of these target decision variables may be determined by means of online calculations, and thus this process may also be referred to as an online decision process.
Subsequently, the platform can allocate virtual resource quantity for the target merchant according to the value of the target decision variable.
The method comprises the steps of determining the value of a dual variable through offline calculation in advance based on the historical user order quantity and the historical decision variable of a merchant and the threshold value of the sum of the virtual resource quantities, determining the value of a target decision variable through online calculation based on the predicted user order quantity of the target merchant and the value of the dual variable when the virtual resource quantity is required to be distributed to the target merchant, and distributing the virtual resource quantity to the target merchant according to the value of the target decision variable.
In some embodiments, assume x ij C to a decision variable indicating whether to assign a virtual resource amount i to merchant j ij For merchant j, user order quantity, m, placed at virtual resource quantity i ij For the actual virtual resource amount allocated to merchant J at virtual resource amount I, b is the threshold, I is the at least one virtual resource amount, J is the at least one merchant, in which case the objective of the optimization problem may include:
Constraints of the optimization problem may include:
/>
generally, x ij =0 means that no virtual resource amount i is assigned to merchant j, x ij =1 means willThe virtual resource amount i is assigned to merchant j. But in practical application, x ij And may be any number between 0 and 1, indicating the probability of assigning a virtual resource amount i to merchant j.
Due to m ij For the actual virtual resource amount allocated to merchant j under virtual resource amount i, therefore, typically m ij =i, but in practical application, m ij May be approximately equal to the value of i, for example: assuming i=2, then m ij May be 2.3.
In some embodiments, assuming λ is the dual variable and f (λ) is the dual function, in which case the objective of the dual problem may include:
min[f(λ)]
wherein:
in practical applications, to prevent overfitting, a regularization term may also be added to f (λ), as follows:
wherein,namely, an added regular term; alpha may be a preset constant.
In some embodiments, in determining the value of the target decision variable, the value of the target decision variable may be specifically determined based on the predicted user order quantity of the target merchant under the at least one virtual resource quantity and a target decision variable indicating whether to allocate a virtual resource quantity to the target merchant, according to the value of the dual variable, through a solution of the dual problem shown below:
Wherein x is in To represent whether virtual resource amount i is assigned to the target decision variable of the target merchant,for the predicted user order quantity, m, of the target merchant under virtual resource quantity i in For the actual virtual resource amount allocated to the target merchant at virtual resource amount i, α is a preset constant (i.e., a constant in the regularization term as previously described).
Corresponding to the foregoing embodiments of the virtual resource issuing method, the present specification also provides embodiments of the virtual resource issuing apparatus.
Fig. 6 is a hardware configuration diagram of an electronic device in which the virtual resource issuing apparatus is located, according to an exemplary embodiment of the present disclosure. Referring to fig. 6, at the hardware level, the device includes a processor 601, an internal bus 602, a network interface 603, a memory 604, and a nonvolatile memory 605, and may include hardware required by other services. One or more embodiments of the present description may be implemented in a software-based manner, such as by the processor 601 reading a corresponding computer program from the non-volatile storage 605 into the memory 604 and then running. Of course, in addition to software implementation, one or more embodiments of the present disclosure do not exclude other implementation manners, such as a logic device or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic module, but may also be a hardware or logic device.
Referring to fig. 7, fig. 7 is a block diagram of a virtual resource issuing apparatus according to an exemplary embodiment of the present specification.
The virtual resource issuing apparatus may be applied to the electronic device shown in fig. 6, and may include:
a construction module 701 for constructing an optimization problem for deciding the amount of virtual resources allocated to at least one merchant based on the amount of historical user orders of the at least one merchant under the amount of at least one virtual resource and a historical decision variable representing whether to allocate one amount of virtual resources to the at least one merchant; wherein the objective of the optimization problem comprises solving a maximum of a sum of user orders for the at least one merchant; constraints of the optimization problem include that only one virtual resource amount is allocated to one merchant, and that the sum of the virtual resource amounts allocated to the at least one merchant does not exceed a preset threshold;
an obtaining module 702, configured to obtain a predicted user order quantity of the target merchant under the at least one virtual resource quantity;
a solving module 703, configured to update the optimization problem based on the predicted user order quantity and a target decision variable indicating whether to allocate a virtual resource quantity to the target merchant, and solve the updated optimization problem to determine a value of the target decision variable;
And the allocation module 704 is configured to allocate a target virtual resource amount to the target merchant based on the target decision variable, so as to issue virtual resources to a user through the target merchant according to the target virtual resource amount.
Optionally, the construction module 701 is specifically configured to:
periodically obtaining a historical user order quantity of at least one merchant under at least one virtual resource quantity according to a preset time period, and representing whether to allocate the virtual resource quantity to one merchant, and constructing an optimization problem for deciding the virtual resource quantity allocated to the at least one merchant based on the historical user order quantity and the historical decision variable.
Optionally, the apparatus further comprises:
a conversion module 705, configured to convert the optimization problem into a dual problem, and solve the dual problem to determine a value of a dual variable in the dual problem; wherein the objective of the dual problem includes solving a minimum of a dual function corresponding to the optimization problem;
the solving module 703 is specifically configured to:
based on the predicted user order quantity and a target decision variable representing whether a virtual resource quantity is allocated to the target merchant, updating the dual problem, and solving the updated dual problem according to the value of the dual variable to determine the value of the target decision variable.
Optionally, the objective of the optimization problem includes:
constraints on the optimization problem include:
wherein x is ij C to a decision variable indicating whether to assign a virtual resource amount i to merchant j ij For merchant j, user order quantity, m, placed at virtual resource quantity i ij For the actual virtual resource amount allocated to merchant J at virtual resource amount I, b is the threshold, I is the at least one virtual resource amount, and J is the at least one merchant.
Optionally, the objective of the dual problem includes:
/>
wherein λ is the dual variable and f (λ) is the dual function.
Optionally, the solving module 703 is specifically configured to:
determining the value of a target decision variable based on the predicted user order quantity and a target decision variable representing whether to allocate a virtual resource quantity to the target merchant, according to the value of the dual variable, by solving the dual problem as shown below:
wherein x is in To represent whether virtual resource amount i is assigned to the target decision variable of the target merchant,for the predicted user order quantity, m, of the target merchant under virtual resource quantity i in For the actual virtual resource amount allocated to the target merchant at virtual resource amount i, α is a preset constant.
Optionally, the obtaining module 702 is specifically configured to:
acquiring merchant feature data of a target merchant;
the merchant characteristic data and the at least one virtual resource amount are input into a predictive model to determine, by the predictive model, a predicted user order amount for the target merchant under the at least one virtual resource amount based on the merchant characteristic data and the at least one virtual resource amount.
Optionally, the prediction model is a deep neural network DNN.
Optionally, the merchant characteristic data includes one or more of the data shown below: user base data; user sequence data; merchant base data; context data.
The implementation process of the functions and roles of each module in the above device is specifically shown in the implementation process of the corresponding steps in the above method, and will not be described herein again.
For the device embodiments, reference is made to the description of the method embodiments for the relevant points, since they essentially correspond to the method embodiments. The apparatus embodiments described above are merely illustrative, wherein the modules illustrated as separate components may or may not be physically separate, and the components shown as modules may or may not be physical, i.e., may be located in one place, or may be distributed over a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purposes of the present description. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. A typical implementation device is a computer, which may be in the form of a personal computer, laptop computer, cellular telephone, camera phone, smart phone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or a combination of any of these devices.
In a typical configuration, a computer includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, read only compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic disk storage, quantum memory, graphene-based storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by the computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The terminology used in the one or more embodiments of the specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the one or more embodiments of the specification. As used in this specification, one or more embodiments and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used in one or more embodiments of the present description to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of one or more embodiments of the present description. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "responsive to a determination", depending on the context.
The foregoing description of the preferred embodiment(s) is (are) merely intended to illustrate the embodiment(s) of the present invention, and it is not intended to limit the embodiment(s) of the present invention to the particular embodiment(s) described.
Claims (10)
1. A virtual resource issuance method, the method comprising:
constructing an optimization problem for deciding on the amount of virtual resources allocated to at least one merchant based on the historical user order amount of the at least one merchant under the at least one amount of virtual resources and a historical decision variable representing whether to allocate one amount of virtual resources to the at least one merchant; wherein the objective of the optimization problem comprises solving a maximum of a sum of user orders for the at least one merchant; constraints of the optimization problem include that only one virtual resource amount is allocated to one merchant, and that the sum of the virtual resource amounts allocated to the at least one merchant does not exceed a preset threshold;
acquiring a predicted user order quantity of a target merchant under the at least one virtual resource quantity;
Updating the optimization problem based on the predicted user order quantity and a target decision variable representing whether a virtual resource quantity is allocated to the target merchant, and solving the updated optimization problem to determine the value of the target decision variable;
and distributing a target virtual resource amount to the target merchant based on the target decision variable so as to distribute virtual resources to users through the target merchant according to the target virtual resource amount.
2. The method of claim 1, the constructing an optimization problem for deciding the amount of virtual resources allocated to at least one merchant based on the amount of historical user orders of the at least one merchant for the amount of at least one virtual resource and a historical decision variable representing whether to allocate one amount of virtual resources to the one merchant, comprising:
periodically obtaining a historical user order quantity of at least one merchant under at least one virtual resource quantity according to a preset time period, and representing whether to allocate the virtual resource quantity to one merchant, and constructing an optimization problem for deciding the virtual resource quantity allocated to the at least one merchant based on the historical user order quantity and the historical decision variable.
3. The method of claim 1, the method further comprising:
converting the optimization problem into a dual problem, and solving the dual problem to determine the value of a dual variable in the dual problem; wherein the objective of the dual problem includes solving a minimum of a dual function corresponding to the optimization problem;
the updating the optimization problem based on the predicted user order quantity and a target decision variable indicating whether to allocate a virtual resource quantity to the target merchant, and solving the updated optimization problem to determine the value of the target decision variable, includes:
based on the predicted user order quantity and a target decision variable representing whether a virtual resource quantity is allocated to the target merchant, updating the dual problem, and solving the updated dual problem according to the value of the dual variable to determine the value of the target decision variable.
4. A method according to claim 3, the objective of the optimization problem comprising:
constraints on the optimization problem include:
wherein x is ij C to a decision variable indicating whether to assign a virtual resource amount i to merchant j ij For merchant j, user order quantity, m, placed at virtual resource quantity i ij For the actual virtual resource amount allocated to merchant J at virtual resource amount I, b is the threshold, I is the at least one virtual resource amount, and J is the at least one merchant.
5. The method of claim 4, the objective of the dual problem comprising:
wherein λ is the dual variable and f (λ) is the dual function.
6. The method of claim 5, wherein updating the dual problem based on the predicted user order quantity and a target decision variable indicating whether to assign a virtual resource quantity to the target merchant, and solving the updated dual problem according to the value of the dual variable to determine the value of the target decision variable, comprises:
determining the value of a target decision variable based on the predicted user order quantity and a target decision variable representing whether to allocate a virtual resource quantity to the target merchant, according to the value of the dual variable, by solving the dual problem as shown below:
wherein x is in To represent whether virtual resource amount i is assigned to the target decision variable of the target merchant, For the predicted user order quantity, m, of the target merchant under virtual resource quantity i in For the actual virtual resource amount allocated to the target merchant at virtual resource amount i, α is a preset constant.
7. The method of claim 1, the obtaining a predicted user order volume for a target merchant under the at least one virtual resource volume, comprising:
acquiring merchant feature data of a target merchant;
the merchant characteristic data and the at least one virtual resource amount are input into a predictive model to determine, by the predictive model, a predicted user order amount for the target merchant under the at least one virtual resource amount based on the merchant characteristic data and the at least one virtual resource amount.
8. A virtual resource issuing apparatus, the apparatus comprising:
a construction module for constructing an optimization problem for deciding the amount of virtual resources allocated to at least one merchant based on the amount of historical user orders of the at least one merchant under the amount of at least one virtual resource and a historical decision variable representing whether to allocate one amount of virtual resources to the at least one merchant; wherein the objective of the optimization problem comprises solving a maximum of a sum of user orders for the at least one merchant; constraints of the optimization problem include that only one virtual resource amount is allocated to one merchant, and that the sum of the virtual resource amounts allocated to the at least one merchant does not exceed a preset threshold;
The obtaining module is used for obtaining the predicted user order quantity of the target merchant under the at least one virtual resource quantity;
the solving module is used for updating the optimization problem based on the predicted user order quantity and a target decision variable which indicates whether a virtual resource quantity is distributed to the target merchant, and solving the updated optimization problem so as to determine the value of the target decision variable;
and the allocation module is used for allocating target virtual resource quantity to the target merchant based on the target decision variable so as to issue virtual resources to a user through the target merchant according to the target virtual resource quantity.
9. An electronic device, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to implement the method of any one of claims 1 to 7 by executing the executable instructions.
10. A computer readable storage medium having stored thereon computer instructions which, when executed by a processor, implement the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310126972.4A CN117314030A (en) | 2023-02-16 | 2023-02-16 | Virtual resource issuing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310126972.4A CN117314030A (en) | 2023-02-16 | 2023-02-16 | Virtual resource issuing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117314030A true CN117314030A (en) | 2023-12-29 |
Family
ID=89287233
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310126972.4A Pending CN117314030A (en) | 2023-02-16 | 2023-02-16 | Virtual resource issuing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117314030A (en) |
-
2023
- 2023-02-16 CN CN202310126972.4A patent/CN117314030A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108351999B (en) | System and method for providing multi-channel inventory distribution avenues for retailers | |
| US11556877B2 (en) | Generation of engagement and support recommendations for content creators | |
| CN109660574B (en) | Data providing method and device | |
| US11127066B2 (en) | Multi-layer optimization for a multi-sided network service | |
| CN111586162A (en) | Information pushing method and system | |
| CN102282551A (en) | Automated decision support for pricing entertainment tickets | |
| US11410117B2 (en) | System and method for controlling inventory depletion by offering different prices to different customers | |
| CN108108933B (en) | Storage position distribution method and device | |
| US20220180392A1 (en) | Predictive recommendation system using tiered feature data | |
| CN111080206A (en) | Method, device and equipment for generating replenishment list and storage medium | |
| CN112084223A (en) | User portrait generation method, device, equipment and storage medium | |
| WO2021222413A1 (en) | Resource capacity planning system | |
| CN113204712A (en) | Information pushing method, device, medium and program product based on community service | |
| CN110858346A (en) | Data processing method, device and machine readable medium | |
| CN113657879A (en) | Resource scheduling method and device | |
| CN113822734A (en) | Method and apparatus for generating information | |
| CN108733685B (en) | Object interaction, browsing, searching and configuration method and device | |
| CN113298610A (en) | Information recommendation and acquisition method, equipment and storage medium | |
| US20150058135A1 (en) | Optimizing an assortment and allocation of groups of items | |
| CN112567410B (en) | System, method and program product for displaying information of activities in a geographic area | |
| CN117333186A (en) | Acquisition method of credit information and establishment method and device of credit management and control rule | |
| US20240095777A1 (en) | Input normalization for model based recommendation engines | |
| CN117314030A (en) | Virtual resource issuing method and device | |
| CN113469462B (en) | Order heat prediction and order allocation method and equipment | |
| US11276081B1 (en) | Targeted communication using order fulfillment logic |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |