CN116485457A - Coupon issuing method and device, computer device and readable storage medium - Google Patents
Coupon issuing method and device, computer device and readable storage medium Download PDFInfo
- Publication number
- CN116485457A CN116485457A CN202310389035.8A CN202310389035A CN116485457A CN 116485457 A CN116485457 A CN 116485457A CN 202310389035 A CN202310389035 A CN 202310389035A CN 116485457 A CN116485457 A CN 116485457A
- Authority
- CN
- China
- Prior art keywords
- target
- ordering
- coupon
- probability
- behavior data
- 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 47
- 230000006399 behavior Effects 0.000 claims description 59
- 238000005457 optimization Methods 0.000 claims description 28
- 238000004364 calculation method Methods 0.000 claims description 23
- 238000012549 training Methods 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 13
- 230000015654 memory Effects 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 5
- 238000004378 air conditioning Methods 0.000 claims 1
- 238000010276 construction Methods 0.000 claims 1
- 230000005284 excitation Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 239000002699 waste material Substances 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000003542 behavioural effect Effects 0.000 description 2
- 230000005291 magnetic effect Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0224—Discounts or incentives, e.g. coupons or rebates based on user history
-
- 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
- G06Q30/0239—Online discounts or incentives
Abstract
The application discloses a coupon issuing method, a coupon issuing device, a computer device and a computer readable storage medium. The coupon issuing method comprises the following steps: acquiring first historical behavior data of each target user using a target application; inputting the first historical behavior data into a valuation model to output valuation probabilities; inputting the first historical behavior data and the pre-issued coupon data on the target application into an ordering model to output initial ordering probabilities corresponding to the coupons; calculating target ordering probabilities corresponding to the coupons based on the valuation probabilities and the initial ordering probabilities; and acquiring a coupon issuing result of each target user based on the target ordering probability. The method and the device can improve the accuracy of coupon distribution for the target user.
Description
Technical Field
The present invention relates to the field of big data processing technologies, and in particular, to a coupon issuing method, a coupon issuing apparatus, a computer device, and a computer readable storage medium.
Background
Issuing coupons to users may facilitate user order conversion, thereby resulting in a platform order size improvement. In the current coupon distribution system, after the users to be distributed are divided into sub-user groups, different coupons are distributed according to the average estimated ordering probability of different sub-user groups by taking the sub-user groups as units, so that the aim of maximizing the ordering amount of the users to be distributed under the limit of a certain subsidy rate is fulfilled. However, this coupon distribution method has two problems as follows:
(1) Coupon distribution strategies of different sub-user groups depend on the accuracy of the prediction model in order probability prediction of the corresponding sub-user groups under the excitation of different coupons. The current prediction model is a single model, and the probability from obtaining the ticket to the next stage of the user waiting to issue the ticket is directly estimated. However, the user also needs to go through the process of opening the app for rating before placing the order, and most of the coupon users will not reach the rating stage due to the low frequency usage characteristics of the shipping user. The single predictive model cannot refine the user's conversion to the valuation stage, which can lead to inaccuracy in the prediction of downstream order probability.
(2) The coupon distribution mode taking the sub-user groups as units can not achieve individuation and precision of coupon distribution because the same coupons are still distributed to users in each group, so that the waste of platform subsidy can be caused.
Disclosure of Invention
To solve at least one technical problem in the background art, embodiments of the present application provide a coupon issuing method, a coupon issuing apparatus, a computer device, and a computer-readable storage medium.
The coupon issuing method of the embodiment of the application comprises the following steps: acquiring first historical behavior data of each target user using a target application; inputting the first historical behavior data into a rating model to output rating probability, wherein the rating model is used for estimating the probability of the target user for rating by using the target application in a preset period; inputting the first historical behavior data and the pre-issued coupon data on the target application into an ordering model to output initial ordering probability corresponding to each coupon, wherein the ordering model is used for estimating the conversion probability from valuation to ordering of the target user under the coupons with different denominations; calculating target ordering probabilities corresponding to the coupons based on the valuation probabilities and the initial ordering probabilities; and acquiring a coupon issuing result of each target user based on the target ordering probability.
In some embodiments, the historical behavior data includes a number of times the target application was opened, a number of valuations, a number of orders, and a number of coupons received.
In some embodiments, the coupon issuing method further comprises: acquiring second historical behavior data of the existing user using the target application, wherein the second historical behavior data comprises the times of opening the target application, the valuation times, the order times, the times of taking coupons and whether the existing user uses the target application for valuation within the preset period;
model training is performed based on the second historical behavior data to obtain the valuation model.
In some embodiments, the coupon issuing method further comprises: acquiring third historical behavior data of the target application used by the existing user, wherein the third historical behavior data comprises the number of times of opening the target application, the number of valuations, the number of times of ordering, the denomination of the received coupon and whether the existing user orders in the target application within the preset period; model training is conducted based on the third historical behavior data to obtain the placing model.
In some embodiments, the calculating the target ordering probability corresponding to each coupon based on the valuation probability and the plurality of initial ordering probabilities includes: and carrying out conditional probability calculation based on the valuation probability and the initial ordering probabilities so as to obtain the target ordering probability corresponding to each coupon.
In some embodiments, the obtaining the coupon issuance outcome of each of the target users based on the target ordering probabilities includes: constructing an optimization problem; and inputting the target order probability into the optimization problem to solve the coupon issuing result of each target user.
In some embodiments, the build optimization problem comprises: taking the maximized order quantity as an optimization target and taking the subsidy rate as a constraint condition; or, taking the running water which maximizes the target application as an optimization target and taking the subsidy rate as a constraint condition.
The coupon issuing apparatus according to an embodiment of the present application includes: the acquisition module is used for acquiring first historical behavior data of each target user using the target application; the first calculation module is used for inputting the first historical behavior data into a rating model to output rating probability, and the rating model is used for estimating the probability of the target user for rating by using the target application in a preset period; the second calculation module is used for inputting the first historical behavior data and the pre-issued coupon data on the target application into an ordering model so as to output initial ordering probability corresponding to each coupon, and the ordering model is used for estimating the conversion probability from valuation to ordering of the target user under the coupons with different denominations; the third calculation module is used for calculating the target ordering probability corresponding to each coupon based on the valuation probability and the initial ordering probabilities; and the fourth calculation module is used for acquiring the coupon issuing result of each target user based on the target ordering probability.
The computer device of the embodiment of the application comprises: one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory and configured to be executed by the one or more processors, the one or more computer programs configured to: executing the coupon issuing method according to any embodiment of the present application.
The non-transitory computer-readable storage medium of the embodiments of the present application stores a computer program that, when executed by one or more processors, causes the processors to perform the coupon issuing method of any of the embodiments of the present application.
In the coupon issuing method, the coupon issuing device, the computer equipment and the computer readable storage medium, on one hand, the problem that the single model estimates the ordering probability inaccurately is solved by splitting the single prediction model into the valuation model and the ordering model, on the other hand, the coupon issuing result of each user waiting to be issued is solved by taking each user waiting to be issued as a unit, and the problem of inaccuracy in issuing coupons by taking sub-user groups as units is solved, so that the waste of platform subsidy budget is avoided.
Additional aspects and advantages of embodiments of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
fig. 1 is a flowchart illustrating a coupon issuing method according to a first embodiment of the present application;
FIG. 2 is a flow chart of a coupon issuing method according to a second embodiment of the present application;
FIG. 3 is a flow chart of a coupon issuing method according to a third embodiment of the present application;
FIG. 4 is a flow chart of a coupon issuing method according to a fourth embodiment of the present application;
FIG. 5 is a flow chart of a coupon issuing method according to a fifth embodiment of the present application;
fig. 6 is a block diagram of a coupon issuing apparatus according to the first embodiment of the present application;
FIG. 7 is a block diagram of a coupon issuing apparatus according to a second embodiment of the present application;
FIG. 8 is a schematic diagram of a computer-readable storage medium in communication with a processor according to some embodiments of the present application;
fig. 9 is a schematic diagram of a computer device according to some embodiments of the present application.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for explaining the embodiments of the present application and are not to be construed as limiting the embodiments of the present application.
Referring to fig. 1 and 5, the present application provides a coupon issuing method. The coupon issuing method comprises the following steps:
01: acquiring first historical behavior data of each target user using a target application;
02: inputting the first historical behavior data into a rating model to output rating probability, wherein the rating model is used for estimating the probability of a target user for rating by using a target application in a preset period;
03: inputting the first historical behavior data and the pre-issued coupon data on the target application into an ordering model to output initial ordering probability corresponding to each coupon, wherein the ordering model is used for estimating the conversion probability from valuation to ordering of the target user under the coupons with different denominations;
04: calculating target ordering probabilities corresponding to the coupons based on the valuation probabilities and the initial ordering probabilities;
05: and acquiring a coupon issuing result of each target user based on the target ordering probability.
The target user is the user waiting to issue the ticket. It can be understood that when a user uses a certain application (i.e., APP) to make an order, the platform to which the application belongs generally distributes corresponding coupons for the user, so as to increase the probability of the user using the application, optimize the user experience, and improve the user viscosity. The coupons may have one or more sheets. When the number of coupons is plural, the plural coupons have different denominations. The user may obtain one or more coupons, such as by drawing a lottery, and use them in subsequent orders.
The target application may be a freight application, a passenger application, etc., without limitation. The freight application may refer to applications such as express delivery and moving, and is not limited herein.
The first historical behavior data may include a number of times the target application was opened, a number of valuations, a number of times the coupon was placed, and a number of times the coupon was received. Wherein the data may be historical usage data of each target user using the target application during a period of time before the time of the issuing of the coupon since the date of registration in the target application by each target user; alternatively, the data may be data of each target user that uses the target application for a period of time, and the period of time may be a month, a half year, a year, two years, or the like, which is not limited herein.
The valuation model and the ordering model are pre-trained models. The valuation probability output by the valuation model refers to the probability that the target user opens the target application at the moment A and then opens the target application at the moment B for valuation. The preset period may be understood as a time difference between the a time and the B time, and may be, for example, 1 day, 2 days, 3 days, 5 days, every other day, etc., without limitation. By way of example, the valuation model may predict that after the target user opens the target application at 2023, 1, the next day (i.e., 2023, 1, 2 days) the target application is opened and the probability of rating the target application is used, in this example, the preset period is every other day. The ordering model may estimate the probability of the target user from valuation to ordering under coupons of different denominations, e.g., the probability of the target user from valuation to ordering under coupons of 2, 5, and 10 denominations, respectively.
Inputting the first historical behavior data into the valuation model may result in a valuation probability. For example, assuming that the number of times the target application is opened, the number of valuations, the number of times the target application is placed, and the number of times the coupon is taken within 7 days are respectively 12, 10, 8, 7, and 4, the data is input into the valuation model, and the valuation model outputs the valuation probability of the target user to be 0.6.
The first historical behavior data and the pre-issued coupon data (i.e., the denomination of the pre-issued coupon) are input into the ordering model, and an initial ordering probability can be obtained. For example, assume that the number of times a target application is opened, the number of valuations, the number of times a target application is placed, and the number of times a coupon is taken within 7 days are respectively 12, 10, 8, 7, and 4, the coupon denomination is respectively 1, 2, and 5, and after the data is input into the placing model, the probability of placing an order after valuation (i.e., initial placing probability) of the user output by the placing model is respectively 0.5, 0.6, and 0.8.
The target ordering probability of the target user under different coupon denominations can be obtained based on the valuation probability and the initial ordering probability, and the coupon issuing result of the target user can be obtained based on the target ordering probability.
According to the coupon issuing method, on one hand, the problem that the single model is inaccurate in issuing probability prediction is solved by splitting the single prediction model into the valuation model and the issuing model, on the other hand, the coupon issuing results of all the users to be issued are solved by taking each user to be issued as a unit, the problem of inaccuracy in issuing coupons by taking sub-user groups as a unit is solved, and the accuracy of issuing coupons of target users is improved, so that the waste of platform subsidy budget is avoided.
In some embodiments, the valuation model may be obtained by training as follows. Referring to fig. 2, the coupon issuing method according to the embodiment of the present application further includes:
061: acquiring second historical behavior data of the target application used by the existing user, wherein the second historical behavior data comprises the times of opening the target application, the times of valuation, the times of ordering, the times of acquiring coupons and whether the target application is used by the existing user in a preset period of time or not for valuation;
062: model training is performed based on the second historical behavioral data to obtain a valuation model.
The existing user refers to a user who completes an order in the target application, and the second historical behavior data of the user using the target application can be acquired for model training. Further, to improve accuracy of model training, the existing user may be a user who has completed an order in the target application within a period of time (e.g., 1 month, 6 months, 1 year, etc.), and the second historical behavior data may be data of the portion of the user using the target application within a period of time (e.g., 1 month, 3 months, 6 months, 1 year, etc.). The second historical behavior data comprises the number of times of opening the target application, the number of valuation times, the number of times of ordering, the number of times of taking the coupon and whether the existing user uses the target application for valuation within a preset period. As one example, the second historical behavior data may include historical behavior data of a number of times each existing user opened the target application within 3 months, a number of times the target application was used for rating, a number of times the target application was placed on a list, a number of times coupons were received on the target application, whether the existing user was using the target application for rating on an alternate day, and the like. The number of times of opening the target application, the number of valuations, the number of times of ordering and the number of times of acquiring coupons in the second historical behavior data are input into a basic model, whether the target application is opened by the existing user for valuation in a preset time period (such as every other day) is used as a label, and the basic model is trained, so that a prediction model for predicting the probability of valuating the target application opened by the user in the preset time period is obtained.
By training the rating model using the second historical behavior data of the existing user, a more accurate rating model may be obtained.
In some embodiments, the order model may be trained in the following manner. Referring to fig. 2 again, the coupon issuing method according to the embodiment of the present application further includes:
071: acquiring third historical behavior data of the target application used by the existing user, wherein the third historical behavior data comprises the number of times the target application is opened, the number of valuations, the number of times the target application is ordered, the denomination of the received coupon and whether the existing user orders in the target application within a preset period;
072: model training is performed based on the third historical behavior data to obtain an order placing model.
Where an existing user refers to a user who has been rated using the target application, the portion of the user's third historical behavior data using the target application may be obtained for model training. Further, to improve accuracy of model training, the existing user may be a user who has been rated in the target application for a period of time (e.g., 1 month, 6 months, 1 year, etc.), and the third historical behavior data may be data of the portion of the user using the target application for a period of time (e.g., 1 month, 3 months, 6 months, 1 year, etc.). The third historical behavior data comprises the number of times of opening the target application, the number of valuations, the number of times of ordering, the denomination of the received coupons, and whether the existing user orders in the target application within a preset period. As one example, the third historical behavior data may include the number of times each existing user opened the target application within 3 months, the number of valuations, the number of orders, the denomination of the coupons received, whether the existing user ordered in the target application on alternate days. The number of times of opening the target application, the number of valuations, the number of times of ordering and the denomination of the received coupons in the third historical behavior data are input into a basic model, whether the user orders in the target application at intervals is used as a label, and the basic model is trained, so that a prediction model for predicting the conversion probability from valuation to ordering of the user under the excitation of coupons with different denominations is obtained. It should be noted that the basic model used for training the underlying model may be the same as or different from the basic model used for training the valuation model, and is not limited herein.
By training the order placing model by using third historical behavior data of the existing user, a more accurate order placing model can be obtained.
In some embodiments, referring to fig. 3, step 04 calculates a target ordering probability corresponding to each coupon based on the valuation probability and the plurality of initial ordering probabilities, including:
041: and carrying out conditional probability calculation based on the valuation probability and the initial ordering probabilities to obtain target ordering probabilities corresponding to the coupons.
As an example, assuming coupon denominations of 1-element, 2-element, and 5-element, respectively, the rating probability of the target user output by the rating model is 0.6, and the initial ordering probabilities of the target user under 1-element, 2-element, and 5-element coupons are 0.5, 0.6, and 0.8, respectively. The conditional probability calculation formula can be known as follows: p (order) =p (order |valuation) ×p (valuation). Therefore, the estimated probability and the ordering probability can be multiplied to obtain the target ordering probabilities of 0.3, 0.36 and 0.48 of the user under the excitation of 1-element, 2-element and 5-element coupons.
In some embodiments, referring to fig. 4, step 05 obtains a coupon issuance outcome for each target user based on the target order probability, including:
051: constructing an optimization problem;
052: and inputting the target order probability into an optimization problem to solve the coupon issuing result of each target user.
In one example, building an optimization problem may include: and taking the maximized order quantity as an optimization target and taking the subsidy rate as a constraint condition. Specifically, the following optimization problem can be constructed by taking the order quantity of the maximized platform as an optimization target, taking the subsidy rate provided by the platform as a constraint condition and taking the coupon issuing result of each target user as a decision variable:
maxΣ i,j p ij x ij (1)
Σ i,j x ij ＝1(3)
wherein x is ij As decision variable to be solved, x ij =1 indicates that the target user i is issued with the coupon j, x ij =0 means that no coupon j is issued to the target user i; p is p ij The ordering probability (i.e., target ordering probability) of the target user i under the excitation of the coupon j; w (w) ij The subsidy cost of the platform when the coupon j is issued to the target user; g ij The estimated order of the target user i is pipelined; θ is the patch rate constraint. Wherein the estimated order pipeline of the target user is an average order price of the target user in a period of time (such as half month, 1 month, 3 months, 6 months, etc.). If the target user has not placed an order, the average order price for the new user in the area where the target user is located (which may be district, city, province, etc.) may be used as the average order price for the target user. The above formula defines that each target user can issue only one ticket. In other embodiments, each target user may issue multiple coupons, and the coupon issuing results of the target users may be solved based on the optimization problem by adaptively modifying the above formula.
In another example, constructing the optimization problem may include: and taking the running water of the maximized target application as an optimization target and taking the subsidy rate as a constraint condition. Specifically, the following optimization problem can be constructed by taking the running water of the maximized platform as an optimization target, taking the subsidy rate provided by the platform as a constraint condition and taking the coupon issuing result of each target user as a decision variable:
max∑ i,j p ij g ij x ij (4)
∑ i,j x ij ＝1(6)
wherein x is ij As decision variable to be solved, x ij =1 indicates that the target user i is issued with the coupon j, x ij =0 means that no coupon j is issued to the target user i; p is p ij The ordering probability (i.e., target ordering probability) of the target user i under the excitation of the coupon j; w (w) ij The subsidy cost of the platform when the coupon j is issued to the target user; g ij The estimated order of the target user i is pipelined; θ is the patch rate constraint. Wherein the estimated order pipeline of the target user is an average order price of the target user in a period of time (such as half month, 1 month, 3 months, 6 months, etc.). If the target user has not placed an order, the average order price for the new user in the area where the target user is located (which may be district, city, province, etc.) may be used as the average order price for the target user. The above formula defines that each target user can issue only one ticket. In other embodiments, each target user may issue multiple coupons, and the coupon issuing results of the target users may be solved based on the optimization problem by adaptively modifying the above formula.
According to the method and the device for distributing the coupons, the coupon distribution results of the users to be distributed are directly constructed to serve as optimization problems of decision variables, so that the inaccuracy problem of distributing the coupons by taking the sub-user groups as units is solved, and the waste of the platform subsidy budget is avoided.
Referring to fig. 6, the embodiment of the present application further provides a coupon issuing apparatus 10. The coupon issuing apparatus 10 includes an acquisition module 11, a first calculation module 12, a second calculation module 13, a third calculation module 14, and a fourth calculation module 15. Wherein, the obtaining module 11 is configured to obtain first historical behavior data of each target user using the target application. The first calculation module 12 is configured to input the first historical behavior data into a rating model to output a rating probability, and the rating model is configured to estimate a probability that the target user is rating using the target application within a preset period of time. The second calculation module 13 is configured to input the first historical behavior data and the coupon data pre-issued on the target application into an ordering model, so as to output an initial ordering probability corresponding to each coupon, where the ordering model is configured to predict a conversion probability from valuation to ordering under coupons of different denominations for the target user. The third calculation module 14 is configured to calculate a target ordering probability corresponding to each coupon based on the valuation probabilities and the multiple initial ordering probabilities. The fourth calculation module 15 is configured to obtain a coupon issuing result of each target user based on the target order probability.
In some embodiments, the first historical behavior data may include a number of times the target application was opened, a number of valuations, a number of times the coupon was placed, and a number of times the coupon was received.
Referring to fig. 7, in some embodiments, the coupon dispensing apparatus 10 further comprises a first training module 16. The first training module 16 may be configured to: acquiring second historical behavior data of the target application used by the existing user, wherein the second historical behavior data comprises the times of opening the target application, the times of valuation, the times of ordering, the times of acquiring coupons and whether the target application is used by the existing user in a preset period of time or not for valuation; model training is performed based on the second historical behavioral data to obtain a valuation model.
Referring again to fig. 7, in some embodiments, the coupon dispensing arrangement 10 further comprises a second training module 17. The second training module 17 may be configured to: acquiring third historical behavior data of the target application used by the existing user, wherein the third historical behavior data comprises the number of times the target application is opened, the number of valuations, the number of times the target application is ordered, the denomination of the received coupon and whether the existing user orders in the target application within a preset period; model training is performed based on the third historical behavior data to obtain an order placing model.
Referring to fig. 6 again, in some embodiments, the third calculation module 14 may be configured to perform a conditional probability calculation based on the valuation probability and the multiple initial ordering probabilities to obtain a target ordering probability corresponding to each coupon.
Referring again to FIG. 6, in some embodiments, the fourth calculation module 15 may be used to construct an optimization problem; and inputting the target order probability into an optimization problem to solve the coupon issuing result of each target user. The optimization problem can be constructed by taking the maximized order quantity as an optimization target and the subsidy rate as a constraint condition; or, taking the running water of the maximized target application as an optimization target and taking the subsidy rate as a constraint condition.
Note that, details of implementation and effects achieved when the coupon issuing device 10 device implements the coupon issuing method according to any embodiment of the present application may refer to the above description of the coupon issuing method, and are not described herein.
Further, referring to fig. 8, an embodiment of the present application provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the coupon issuing method described in any of the above embodiments. The computer readable storage medium includes, but is not limited to, any type of disk including floppy disks, hard disks, optical disks, CD-ROMs, and magneto-optical disks, ROMs (Read-Only memories), RAMs (Random Access Memory, random access memories), EPROMs (Erasable Programmable Read-Only memories), EEPROMs (Electrically Erasable Programmable Read-Only memories), flash memories, magnetic cards, or optical cards. That is, a storage device includes any medium that stores or transmits information in a form readable by a device (e.g., computer, cell phone), and may be read-only memory, magnetic or optical disk, etc.
The content of the method embodiment of the present application is applicable to the storage medium embodiment, and functions of the specific implementation of the storage medium embodiment are the same as those of the method embodiment, and beneficial effects achieved by the method are the same as those achieved by the method, and detailed description of the method embodiment is referred to herein, and will not be repeated.
In addition, referring to fig. 9, the embodiment of the present application further provides a computer device, where the computer device in this embodiment may be a server, a personal computer, a network device, or other devices. The computer device includes one or more processors, memory, and one or more computer programs. Wherein the one or more computer programs are stored in the memory and configured to be executed by the one or more processors. One or more computer programs are configured to perform the coupon issuing method of any of the above embodiments.
In the description of the present specification, reference to the terms "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and further implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.
While embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the present application, and that variations, modifications, alternatives, and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the present application.
Claims (10)
1. A coupon issuing method, comprising:
acquiring first historical behavior data of each target user using a target application;
inputting the first historical behavior data into a rating model to output rating probability, wherein the rating model is used for estimating the probability of the target user for rating by using the target application in a preset period;
inputting the first historical behavior data and the pre-issued coupon data on the target application into an ordering model to output initial ordering probability corresponding to each coupon, wherein the ordering model is used for estimating the conversion probability from valuation to ordering of the target user under the coupons with different denominations;
calculating target ordering probabilities corresponding to the coupons based on the valuation probabilities and the initial ordering probabilities;
and acquiring a coupon issuing result of each target user based on the target ordering probability.
2. The coupon issuing method according to claim 1, wherein the historical behavior data includes a number of times the target application is opened, a number of valuations, a number of times a coupon is placed, and a number of times the coupon is taken.
3. The coupon issuing method according to claim 2, further comprising:
acquiring second historical behavior data of the existing user using the target application, wherein the second historical behavior data comprises the times of opening the target application, the valuation times, the order times, the times of taking coupons and whether the existing user uses the target application for valuation within the preset period;
model training is performed based on the second historical behavior data to obtain the valuation model.
4. The coupon issuing method according to claim 2, further comprising:
acquiring third historical behavior data of the target application used by the existing user, wherein the third historical behavior data comprises the number of times of opening the target application, the number of valuations, the number of times of ordering, the denomination of the received coupon and whether the existing user orders in the target application within the preset period;
model training is conducted based on the third historical behavior data to obtain the placing model.
5. The coupon issuing method according to claim 1, wherein the calculating a target order probability corresponding to each of the coupons based on the valuation probabilities and the plurality of initial order probabilities comprises:
and carrying out conditional probability calculation based on the valuation probability and the initial ordering probabilities so as to obtain the target ordering probability corresponding to each coupon.
6. The coupon issuing method according to claim 1, wherein the acquiring the coupon issuing result of each of the target users based on the target ordering probability comprises:
constructing an optimization problem;
and inputting the target order probability into the optimization problem to solve the coupon issuing result of each target user.
7. The coupon issuing method according to claim 6, wherein the construction optimization problem comprises:
taking the maximized order quantity as an optimization target and taking the subsidy rate as a constraint condition; or (b)
And taking the running water which maximizes the target application as an optimization target and taking the subsidy rate as a constraint condition.
8. A coupon issuing apparatus, comprising:
the acquisition module is used for acquiring first historical behavior data of each target user using the target application;
the first calculation module is used for inputting the first historical behavior data into a rating model to output rating probability, and the rating model is used for estimating the probability of the target user for rating by using the target application in a preset period;
the second calculation module is used for inputting the first historical behavior data and the pre-issued coupon data on the target application into an ordering model so as to output initial ordering probability corresponding to each coupon, and the ordering model is used for estimating the conversion probability from valuation to ordering of the target user under the coupons with different denominations;
the third calculation module is used for calculating the target ordering probability corresponding to each coupon based on the valuation probability and the initial ordering probabilities;
and the fourth calculation module is used for acquiring the coupon issuing result of each target user based on the target ordering probability.
9. A computer device, comprising:
one or more processors;
a memory; a kind of electronic device with high-pressure air-conditioning system
One or more computer programs, wherein the one or more computer programs are stored in the memory and configured to be executed by the one or more processors, the one or more computer programs configured to: a coupon issuing method according to any one of claims 1 to 7.
10. A non-transitory computer-readable storage medium storing a computer program, characterized in that the computer program, when executed by one or more processors, causes the processors to perform the coupon issuing method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310389035.8A CN116485457A (en) | 2023-04-03 | 2023-04-03 | Coupon issuing method and device, computer device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310389035.8A CN116485457A (en) | 2023-04-03 | 2023-04-03 | Coupon issuing method and device, computer device and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116485457A true CN116485457A (en) | 2023-07-25 |
Family
ID=87222465
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310389035.8A Pending CN116485457A (en) | 2023-04-03 | 2023-04-03 | Coupon issuing method and device, computer device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116485457A (en) |
-
2023
- 2023-04-03 CN CN202310389035.8A patent/CN116485457A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Puterman | Markov decision processes: discrete stochastic dynamic programming | |
| Moreno et al. | Evaluating risk-constrained bidding strategies in adjustment spot markets for wind power producers | |
| CN110322169A (en) | A kind of method and device of task publication | |
| Reeves et al. | Getting back on track: the expanded use of PPPs in Ireland since the global financial crisis | |
| US20160055494A1 (en) | Booking based demand forecast | |
| CN113240272A (en) | Enterprise ESG index determination method and related product | |
| CN109492863A (en) | The automatic generation method and device of financial document | |
| CN112163886A (en) | Real-time bidding advertisement resource allocation method based on reinforcement learning | |
| US20210150585A1 (en) | Artificial intelligence techniques for bid optimization used for generating dynamic online content | |
| CN107025575A (en) | Brand client KPI predictor methods in sequencing advertisement putting | |
| CN109615132A (en) | Determination method, apparatus, electronic equipment and the storage medium of region distribution pressure | |
| CN102103714A (en) | Real-time processing platform for predicting service data and predicting method | |
| US20220036411A1 (en) | Method and system for joint optimization of pricing and coupons in ride-hailing platforms | |
| CN116485457A (en) | Coupon issuing method and device, computer device and readable storage medium | |
| CN110796379A (en) | Risk assessment method, device and equipment of business channel and storage medium | |
| CN116091242A (en) | Recommended product combination generation method and device, electronic equipment and storage medium | |
| CN111327661A (en) | Pushing method, pushing device, server and computer readable storage medium | |
| CN114549071A (en) | Marketing strategy determination method and device, computer equipment and storage medium | |
| CN114841451A (en) | Driver travel subsidy method and device and storage medium | |
| CN108449411A (en) | Cloud resource dispatching method towards heterogeneous expense under a kind of stochastic demand | |
| CN112950033A (en) | Reservoir dispatching decision method and system based on reservoir dispatching rule synthesis | |
| WO2021230808A1 (en) | Server and method of determining an advanced booking fee for an advance booking | |
| CN111553736B (en) | Method and device for processing preferential information, readable medium and equipment | |
| CN111798256A (en) | Method for determining fare, method, device and system for acquiring data | |
| CN113391923B (en) | System resource data allocation method and device |
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 |