CN110634010A - Method and device for determining coupon issuing strategy - Google Patents

Method and device for determining coupon issuing strategy Download PDF

Info

Publication number
CN110634010A
CN110634010A CN201810663437.1A CN201810663437A CN110634010A CN 110634010 A CN110634010 A CN 110634010A CN 201810663437 A CN201810663437 A CN 201810663437A CN 110634010 A CN110634010 A CN 110634010A
Authority
CN
China
Prior art keywords
users
coupons
target user
user category
determining
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
Application number
CN201810663437.1A
Other languages
Chinese (zh)
Inventor
汪恒智
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Didi Infinity Technology and Development Co Ltd
Original Assignee
Beijing Didi Infinity Technology and Development Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Didi Infinity Technology and Development Co Ltd filed Critical Beijing Didi Infinity Technology and Development Co Ltd
Priority to CN201810663437.1A priority Critical patent/CN110634010A/en
Publication of CN110634010A publication Critical patent/CN110634010A/en
Pending legal-status Critical Current

Links

Images

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
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • 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

Landscapes

  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application provides a method and a device for determining a coupon issuing strategy, which are used for accurately pushing an electronic coupon to a user. The method for determining the coupon issuing strategy comprises the following steps: pushing different types of coupons for users of the target user category; counting the probability of transferring the user of the target user category to other user categories after receiving the coupons of various types, and forming a transfer probability matrix of the target user category; and determining a strategy for issuing the coupons to the users of the target user category according to the transition probability matrix.

Description

Method and device for determining coupon issuing strategy
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a method and an apparatus for determining a coupon issuing policy.
Background
Electronic Coupon (Electronic Coupon) refers to a sales promotion voucher made, spread and used by various Electronic media (including internet, multimedia message, short message, two-dimensional code, picture and the like). The electronic coupon is different from the common paper coupon in characteristics, mainly low in manufacturing and transmission cost and high in transmission speed.
However, the prior art lacks a scheme for accurately pushing the electronic coupon to the user.
Disclosure of Invention
In view of this, embodiments of the present application provide a method and an apparatus for determining a coupon issuing policy, so as to accurately push an electronic coupon to a user.
Mainly comprises the following aspects:
in a first aspect, the present application provides a method for determining a coupon issuance policy, comprising: pushing different types of coupons for users of the target user category; counting the probability of transferring the user of the target user category to other user categories after receiving the coupons of various types, and forming a transfer probability matrix of the target user category; and determining a strategy for issuing the coupons to the users of the target user category according to the transition probability matrix.
In some optional implementations of the first aspect, after the determining the policy for issuing coupons to users of the target user category according to the transition probability matrix, the method further includes: issuing coupons to users of the target user category according to the determined strategy; counting the number of users in the target user category, who are transferred to other user categories after receiving the coupons, and updating the transfer probability matrix according to the number; and updating a strategy for issuing the coupons to the users of the target user category according to the updated transition probability matrix.
In some optional implementations of the first aspect, the determining a policy for issuing coupons to users of the target user category according to the transition probability matrix includes: determining the income of the user after the user is transferred from the target user category to each user category; determining the expected profit of the users of the target user category after receiving each coupon according to the profit and the transition probability matrix; determining the most revenue expected coupon, and determining the policy comprises issuing the most revenue expected coupon to the user of the target user category.
In some optional implementation manners of the first aspect, the determined policy is specifically: and issuing the coupons with the largest profit expectation to a first part of users of the target user category, and issuing the coupons except the coupons with the largest profit expectation to a second part of users of the target user category, wherein the number of the first part of users is larger than that of the second part of users.
In some optional implementations of the first aspect, before the pushing different types of coupons for the users of the target user category, further comprising:
and acquiring the behavior characteristics of a plurality of users, clustering the behavior characteristics to obtain a plurality of user categories.
In a second aspect, the present application provides an apparatus for determining a coupon issuance policy, comprising: the first pushing module is used for pushing different types of coupons aiming at users of the target user category; the transition probability determining module is used for counting the probability that the user of the target user category transfers to other user categories after receiving the coupons of various types, and forming a transition probability matrix of the target user category; and the strategy determining module is used for determining a strategy for issuing the coupons to the users of the target user category according to the transition probability matrix.
In some optional implementations of the second aspect, the apparatus further comprises: a second pushing module for: after the strategy determining module determines a strategy for issuing coupons to the users of the target user category according to the transition probability matrix, issuing the coupons to the users of the target user category according to the determined strategy; the transition probability determination module is further configured to: counting the number of users in the target user category, who are transferred to other user categories after receiving the coupons, and updating the transfer probability matrix according to the number; the policy determination module is further configured to: and updating a strategy for issuing the coupons to the users of the target user category according to the updated transition probability matrix.
In some optional implementations of the second aspect, the policy determination module is specifically configured to: determining the income of the user after the user is transferred from the target user category to each user category; determining the expected profit of the users of the target user category after receiving each coupon according to the profit and the transition probability matrix; determining the most revenue expected coupon, and determining the policy comprises issuing the most revenue expected coupon to the user of the target user category.
In some optional implementation manners of the second aspect, the determined policy is specifically: and issuing the coupons with the largest profit expectation to a first part of users of the target user category, and issuing the coupons except the coupons with the largest profit expectation to a second part of users of the target user category, wherein the number of the first part of users is larger than that of the second part of users.
In some optional implementations of the second aspect, the apparatus further comprises:
and the clustering module is used for acquiring the behavior characteristics of a plurality of users before the pushing module pushes different types of coupons for the users of the target user category, clustering the behavior characteristics and obtaining a plurality of user categories through clustering.
In a third aspect, the present application provides a server, comprising: a memory for storing computer program instructions; the communication module is used for communicating with the user terminal; a processor, connected to the memory and the communication module, configured to execute the computer program instructions to perform the method of the first aspect or any optional implementation manner of the first aspect when the computer program instructions are executed.
In a fourth aspect, the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the method of the first aspect or any of the alternative implementations of the first aspect.
In a fifth aspect, the present application provides a computer program product which, when run on a computer, causes the computer to perform the method of the first aspect or any possible implementation manner of the first aspect.
In the technical scheme, different types of coupons are pushed to users of a target user category, the probability that the users transfer from the target user category to each other user category under the stimulation of each type of coupon is counted, a transfer probability matrix is formed, and the transfer probability matrix represents the possibility that the users of the target user category transfer to each other user category under any coupon stimulation, so that the transfer effect of the user category for issuing the coupons to the users of the target user category can be determined according to the transfer probability matrix, the optimal coupon issuing strategy for the target user category is determined according to the transfer effect, the pertinence of issuing the coupons is enhanced, and the issuing effect of the coupons is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 shows a schematic diagram of a communication system in the present application;
FIG. 2 illustrates a flow diagram of a method of determining a coupon-issuance policy provided by some embodiments of the present application;
FIG. 3 shows a schematic diagram of user category transition probabilities;
FIGS. 4-6 illustrate flow diagrams of a method of determining a coupon-issuance policy provided by some embodiments of the present application;
FIG. 7 is a block diagram illustrating an exemplary architecture of an apparatus 400 for determining a coupon-issuance policy provided in some embodiments of the present application;
fig. 8 is a block diagram illustrating a schematic structure of a server 500 according to some embodiments of the present disclosure.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. The following detailed description of the embodiments of the present application is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.
The plural in the present application means two or more. In addition, in the description of the present application, the terms "first," "second," and the like are used for descriptive purposes only and are not intended to indicate or imply relative importance nor order to be construed. Further, the term "and/or" in the present application is only one kind of association relationship describing the associated object, and means that three kinds of relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone.
The method, the apparatus, the electronic device, or the computer storage medium described in the embodiments of the present application may be applied to a scenario in which an electronic coupon is issued over a network, for example, may be applied to the fields of a network appointment platform, a shared bicycle platform, a takeaway platform, an electronic mall, and the like. The embodiment of the present application does not limit the specific application scenario, and any scheme for issuing and evaluating the electronic coupons by using the method provided by the embodiment of the present application is within the protection scope of the present application. For convenience of explanation, the following description of the embodiments of the present application takes a network appointment platform as an example.
Fig. 1 shows a communication system in an embodiment of the present application, and the communication system includes a platform 10 and several user terminals 20, where the platform 10 may include one or several servers and may further include one or several storage devices for storing data that the servers need to use. The user terminal 20 may be a smartphone, a tablet computer, or the like. In the communication system, a platform pushes a coupon to a user terminal, collects behavior characteristics (or consumption data) of the user terminal, determines a user category of a user according to the behavior characteristics of the user, and further determines whether the user category of the user is changed and to which user category the user is transferred under the stimulation of the coupon.
Fig. 2 illustrates a method for determining a coupon issuance policy provided by the present application, which is performed by the platform 10 illustrated in fig. 1, and includes:
step 301, platform 10 pushes different types of coupons to users of the target user category.
Specifically, the user category may be a plurality of categories pre-classified by the platform 10, for example, the user may be classified into a plurality of categories such as a user who makes a taxi 10 times or less, a user who makes a taxi 10 times to 50 times, and the like according to the taxi number. And for example, according to the taxi taking frequency, dividing the users into users with taxi taking less than 1 time per week, users with taxi taking 1-3 times per week and the like. In addition, the platform can also be used for classifying the user categories according to various standards such as travel distance, taxi taking cost, common taxi taking types and the like. In addition, the user category may be determined after statistics is performed on the taxi taking data of the user, that is, the platform 10 does not pre-divide a plurality of user categories, but determines different characteristics of the user according to the actual taxi taking data of the user, so as to determine a plurality of user categories.
Coupon types may also be implemented in a variety of ways, for example, coupon types may be classified into conditional coupons (e.g., coupons that are used only after a certain amount of money has been consumed) and unconditional coupons, each of which may be classified into full-discount coupons and discount coupons. For example, the coupon types may be divided according to usage scenarios, and the coupons may be divided into windward coupons, special car coupons, car pool coupons, and the like, taking a car booking platform as an example. Various types of coupons in the present application can be found in various prior art implementations of coupons and are not listed here.
In addition, the platform 10 pushes the coupon to the user, the coupon can be pushed by pointing to the account of the user, and the user can receive the coupon after logging in the account through any terminal.
Step 302, the platform 10 counts the probability that the user of the target user category transfers to other user categories after receiving the coupons of various types, and forms a transfer probability matrix of the target user category.
Specifically, after sending the coupon to the user, the platform 10 counts the behavior feature data (or consumption data) of each user receiving the coupon, classifies the user into a user category according to the behavior feature data, and further determines the probability that the user transfers to other user categories after receiving various types of coupons.
For example, referring to fig. 3, let a discount coupon (e.g. 6-fold, 7-fold, 8-fold, etc.) issuing action (action) be aiThe value of i is 1 to k, k is the total number of types of the coupons,let the user category include S1,S2,S3,S4The target user category is S1. Platform 10 is oriented S1User of category carries out aiAfter the coupon issuing operation, the N2 users who received the coupon shift to S2N3 user transition to S3N4 users shift to S4Also N1 users maintain S1Is unchanged, then is in aiUnder the action of issuing ticket, S1User transition of category to user category S2Has a probability of N2/(N1+ N2+ N3+ N4), and is shifted to the user class S3Has a probability of N3/(N1+ N2+ N3+ N4), and is shifted to the user class S4Has a probability of N4/(N1+ N2+ N3+ N4), maintains the user class S1The probability of (a) is N1/(N1+ N2+ N3+ N4), which can be labeled as P2, P3, P4, P1, respectively. Then S2Users of the category are at aiThe transition state matrix in the ticket issuing action is represented as Q (s1, a)i) (P1, P2, P3, P4). One such transition probability matrix Q may be derived for each coupon action (i.e., each type of coupon).
Step 303, the platform 10 determines a policy for issuing coupons to users of the target user category according to the transition probability matrix.
Specifically, the platform 10 may determine an optimal scheme for issuing the coupon according to the transition probability matrix, that is, a policy for issuing the coupon. Wherein the issuance policy determined by the platform 10 may be different according to different optimization objectives.
For example, when the optimization objective is the highest profit, the aforementioned transition state matrix is followed as Q (S)1，ai) Let us assume that the user is classified by the user category S1Transition to user category S2Average profit from the user is r2, from user class S1Transition to user category S3Average profit from the user is r3, from user class S1Transition to user category S4The average profit made by the user is r4, and the user remains at S1The profit average for the state is r1, then platform 10 may incorporate S1Probability of transfer to user categories and transferred profits to determine a coupon that optimizes profit for the platformAnd (4) strategy.
It should be understood that the platform 10 may determine its transition probability matrix and its issuance policy based on the transition probability matrix using a portion of the user categories or even each user category as the target user category.
In the technical scheme, different types of coupons are pushed to users of target user categories, the probability that the users transfer from the target user category to each other user category under the stimulation of each type of coupon is counted to form a transition probability matrix, the probability that the users of the target user category transfer to each other user category under the stimulation of any coupon can be simply and clearly shown by the transition probability matrix, and then the stimulation effect of each type of coupon on the users of each user category can be rapidly evaluated according to the transition probability matrix. Moreover, the platform 10 can determine the optimal coupon issuing strategy for the user of the target user category according to the transition probability matrix of the target user category, so as to enhance the pertinence of issuing the coupon and improve the issuing effect of the coupon.
In the embodiment of the present application, the platform 10 in step 301 pushes different types of coupons to users in the category of target users, and there may be multiple implementation manners, including but not limited to the following:
firstly, the platform 10 selects a part of users from the target user category as experimental users, randomly issues coupons to the experimental users, and sends one coupon to each experimental user, and the difference of the issuing quantity of each type of coupons is smaller than the constraint value.
Secondly, the difference is that a plurality of coupons can be issued to some or all of the experimental users, for example, 8-fold coupons are sent to the users on monday, and 2-element vouchers are sent to the users on wednesday after the coupons are used.
Thirdly, the difference between the first coupon and the second coupon is that a plurality of coupons can be sent to the user at the same time, then the steps regard the plurality of coupons as a coupon combination and still regard the coupon combination as a coupon sending action, and a transition probability matrix of the target user category under the coupon combination is determined according to the step 302.
Fourthly, combining the first item and the third item, for example, the coupon is issued by adopting the first way for one part of the experimental users, and the coupon is issued by adopting the third way for the other part of the experimental users.
In the above technical solution, the platform 10 can collect user category migration data of the user under the effect of the coupon in a flexible manner, and further obtain an accurate migration probability matrix.
As an alternative design, referring to fig. 4, after step 303, the following steps are further included:
step 304, the platform 10 issues coupons to users of the target user category according to the determined strategy;
step 305, the platform 10 counts the number of users who are transferred to other user categories after receiving the coupons in the users of the target user category, and updates the transfer probability matrix of the target user category according to the number;
step 306, the platform 10 updates the policy of issuing the coupons to the users of the target user category according to the updated transition probability matrix.
Specifically, after pushing the coupon to the user, the platform 10 may obtain behavior feature data of the user under the coupon, determine the user category of the user after migration under the stimulation of the coupon according to the behavior feature data, and obtain the number of the user migrating to each user category under the effect of the coupon, which is hereinafter referred to as user category migration data for short. And updating the transition probability matrix of the target user category by combining the user category migration data of the current time and the user category migration data in the history (before the coupon of the current time is issued).
For another example, the predicted values of the corresponding orders of different cycle lengths can be obtained through calculation by means of a Bellman equation and the like. For example, a first-order migration probability matrix may be determined based on the user category migration data of the last half year, a coupon issuing policy may be determined according to the first-order migration probability matrix, a coupon may be issued to the user according to the coupon issuing policy in the first week of 7 months, a second-order migration probability matrix may be obtained according to the user category migration data of the first week of 7 months and the user category migration data of the last half year, and the coupon issuing policy may be updated according to the second-order migration probability matrix. By analogy, the migration probability matrix and the coupon issuing strategy are continuously trained, so that the coupon issuing strategy is continuously optimized.
When the migration probability matrix is updated, different weighting factors can be used for the migration data of the new user category and the migration data of the historical user category, for example, the weighting factor of the migration data of the historical user category can be smaller than that of the migration data of the current user category, so that the real-time performance of the migration probability matrix is enhanced. For another example, the weighting factor of the historical user category migration data may be greater than the migration data of the current user category, so as to enhance the stability of the migration probability matrix.
In the above technical solution, the platform 10 may update the transition probability matrix according to the actual effectiveness of the issued coupon on the user category migration of the user, iterate to obtain a new transition probability matrix, and further determine a new optimal coupon issuing policy according to the updated transition probability matrix, so as to train the coupon issuing policy continuously, and optimize the coupon issuing policy continuously.
As an alternative design, referring to fig. 5, step 303 may include the following steps:
step 3031, the platform 10 determines the income of the user after the user is transferred from the target user category to each user category;
step 3032, the platform 10 determines the expected profit of the users of the target user category after receiving each coupon according to the profit and the transition probability matrix;
step 3033, the platform 10 determines the coupon with the largest profit expectation, and the determining the policy comprises issuing the coupon with the largest profit expectation to the users of the target user category.
The profit is different depending on the optimization objective, for example, if the optimization objective is the highest profit, the profit is the profit; for another example, if the optimization target is the user's finished order quantity, the profit is the user's average finished order quantity; for another example, if the optimization objective is user experience, the benefit is a user score value.
Following the foregoing example, the user is classified by user class S1Transition to user category S2Average profit from the user is r2, from user class S1Transition to user category S3Average profit from the user is r3, from user class S1Transition to user category S4The average profit made by the user is r4, and the user remains at S1The profit average of the state is r1, the coupon a is issuediProfit expectation R (S) brought by the post-user1,ai) R1 × P1+ r2 × P2+ r3 × P3+ r4 × P4. Comparison of R (S)1A1) to R (S)1，ak) Determining the maximum value of (s1, a)k1) Then it may be determined that coupon a is issued to the userk1For maximum revenue, it may be used as a coupon issue strategy to maximize revenue for the platform 10.
It should be noted that the coupon issuing policy may include issuing other types of coupons in addition to those that maximize the benefit of the platform 10 to users in the target user category. Specifically, the platform 10 distributes the coupon with the largest profit expectation to a first part of users in the target user category, and distributes the coupon except the coupon with the largest profit expectation to a second part of users in the target user category, wherein the first part of users is more than the second part of users. The method has the advantages that other coupons can be issued to a small number of users to check whether the previous migration probability matrix is accurate or not, and the migration probability matrix can be updated all the time, so that the matrix is prevented from being inaccurate due to the fact that user category migration data of other coupons are missing.
In specific implementation, the experimental data may be selected according to the confidence of the Q value and the R value obtained in the first experiment for performing subsequent reinforcement learning, where the confidence may be set according to an empirical value or determined according to a prediction error value of the transition probability matrix Q. For example, if the confidence of the new Q and R values obtained by the experiment is P and the total number of the experiment data is N, then N × P user data is selected to perform the coupon issuing experiment with the maximum predicted profit, and the remaining N × (1-P) user data are used to explore other possibilities.
According to the technical scheme, the platform 10 can determine the coupon strategy for optimizing the platform yield according to the migration probability matrix, and the method effect of the coupon is improved.
As an optional design, the user categories in the embodiment of the present application may be obtained by clustering. Referring to fig. 6, before step 301, the method further includes:
step 307, the platform 10 obtains behavior characteristics of a plurality of users, and clusters the behavior characteristics to obtain a plurality of user categories.
The behavior characteristics of the user can be realized in various ways, for example, the user category of the user can be divided into a low-frequency user, a medium-frequency user and a high-frequency user according to the frequency of using the network appointment software by the user. For another example, the user categories of the users can be divided into low-satisfaction users, medium-satisfaction users and high-satisfaction users according to the rating of the users to the online car booking service. For another example, the user categories may be divided into short-distance taxi taking users, medium-distance taxi taking users, and long-distance taxi taking users according to taxi taking distances of the users. Besides, clustering can be performed according to the data such as the taxi taking grade of the user (such as the taxi taking, the express taxi, the carpool, the shared taxi, the special taxi and the like), the taxi taking time period of the user, taxi taking cost of the user, the score of the user after taxi taking and the like, and the algorithm used for clustering the behavior characteristics of the user can refer to various existing clustering technologies, for example, the algorithm can be an unsupervised learning algorithm such as K-means or density clustering and the like, and can also be a neural network algorithm.
It should be understood that one user category may also be an intersection of multiple user behavior characteristics, for example, the user category may be divided into high frequency low satisfaction user, high frequency high satisfaction user, low frequency low satisfaction user, low frequency high satisfaction client, and the like.
In the above technical solution, the platform 10 determines a plurality of user categories according to the behavior characteristics of the users in a clustering manner, and determines that the user categories are more objective and more comprehensive, and can reflect the real state of the users.
Fig. 7 illustrates an apparatus 400 for determining a coupon issuance policy according to an embodiment of the present application, and referring to fig. 7, the apparatus includes:
the first pushing module 401 is configured to push different types of coupons for users of the target user category;
a transition probability determining module 402, configured to count probabilities that users of the target user category transition to other user categories after receiving coupons of various types, and form a transition probability matrix of the target user category;
and a policy determining module 403, configured to determine, according to the transition probability matrix, a policy for issuing a coupon to the user of the target user category.
Optionally, with continued reference to fig. 7, the apparatus 400 further comprises:
a second pushing module 404 for: after the policy determining module 403 determines a policy for issuing coupons to users of the target user category according to the transition probability matrix, issuing coupons to users of the target user category according to the determined policy;
the transition probability determination module 402 is further configured to: counting the number of users in the target user category, who are transferred to other user categories after receiving the coupons, and updating the transfer probability matrix according to the number;
the policy determination module 403 is further configured to: and updating a strategy for issuing the coupons to the users of the target user category according to the updated transition probability matrix.
Optionally, the policy determining module 403 is specifically configured to: determining the income of the user after the user is transferred from the target user category to each user category; determining the expected profit of the users of the target user category after receiving each coupon according to the profit and the transition probability matrix; determining the most revenue expected coupon, and determining the policy comprises issuing the most revenue expected coupon to the user of the target user category.
Optionally, the policy determined by the policy determining module 403 specifically includes: and issuing the coupons with the largest profit expectation to a first part of users of the target user category, and issuing the coupons except the coupons with the largest profit expectation to a second part of users of the target user category, wherein the number of the first part of users is larger than that of the second part of users.
Optionally, the apparatus 400 further includes:
the clustering module 405 is configured to obtain behavior characteristics of multiple users before the pushing module pushes different types of coupons for users of a target user category, and perform clustering on the behavior characteristics to obtain multiple user categories.
It should be understood that the division of the modules of the apparatus 400 in the embodiment of the present application is schematic, and only one logical function division is provided, and in actual implementation, there may be another division manner, and in addition, each functional module in each embodiment of the present invention may be integrated in one processor, or may exist alone physically, or two or more modules are integrated in one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.
The implementation of the modules of the apparatus 400 can refer to the implementation of the steps of the method for determining the coupon issuing policy in the foregoing embodiment, and will not be repeated here.
Fig. 8 shows that the present embodiment provides a server 500, and referring to fig. 8, the server 500 includes: a processor 501, a memory 502, and a communication module 503. The memory 502 and the communication module 503 may be connected to the processor 501 through a bus.
Wherein the memory 502 is used to store computer program instructions; the communication module 503 is configured to communicate with a user terminal; the processor 501 is connected to the memory and the communication module, and is configured to execute the computer program instructions to execute the method for determining a coupon issuance policy in the foregoing embodiment when the computer program instructions are executed.
The processor 501 may be a single processing element or may be a general term for a plurality of processing elements. For example, the processor may be a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement embodiments of the present invention, such as: one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs).
The memory 502 may be a single memory element or a combination of multiple memory elements, and is used for storing executable program codes or parameters, data, and the like required by the terminal to operate. And the Memory 502 may include a Random-Access Memory (RAM) or a Non-Volatile Memory (NVM), such as a magnetic disk Memory, a Flash Memory (Flash), and the like.
The implementation of the components of the server 500 can refer to the implementation of the steps of the method for determining the coupon issuing policy in the foregoing embodiment, and will not be repeated here.
Embodiments of the present application further provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program performs the method for determining a coupon release policy in the foregoing embodiments.
Specifically, the storage medium can be a general-purpose storage medium, such as a mobile magnetic disk, a hard disk, an optical disk, and the like, and when a computer program on the storage medium is executed, the method for determining the coupon issuing policy can be executed, so that the electronic coupon is accurately pushed to the user.
In addition, embodiments of the present application also provide a computer program product, which when run on a computer, causes the computer to execute the method for determining a coupon issuance policy in the foregoing embodiments.
It should be understood that the functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (12)

1. A method of determining a coupon issuance policy, comprising:
pushing different types of coupons for users of the target user category;
counting the probability of transferring the user of the target user category to other user categories after receiving the coupons of various types, and forming a transfer probability matrix of the target user category;
and determining a strategy for issuing the coupons to the users of the target user category according to the transition probability matrix.
2. The method of claim 1, further comprising, after determining the policy for issuing coupons to users of the target user category based on the transition probability matrix:
issuing coupons to users of the target user category according to the determined strategy;
counting the number of users in the target user category, who are transferred to other user categories after receiving the coupons, and updating the transfer probability matrix according to the number;
and updating a strategy for issuing the coupons to the users of the target user category according to the updated transition probability matrix.
3. The method of claim 1, wherein determining a policy for issuing coupons to users of the target user category based on the transition probability matrix comprises:
determining the income of the user after the user is transferred from the target user category to each user category;
determining the expected profit of the users of the target user category after receiving each coupon according to the profit and the transition probability matrix;
determining the most revenue expected coupon, and determining the policy comprises issuing the most revenue expected coupon to the user of the target user category.
4. The method according to claim 3, wherein the determined policy is specifically: and issuing the coupons with the largest profit expectation to a first part of users of the target user category, and issuing the coupons except the coupons with the largest profit expectation to a second part of users of the target user category, wherein the number of the first part of users is larger than that of the second part of users.
5. The method according to any one of claims 1 to 4, wherein before the pushing different types of coupons for the users of the target user category, further comprising:
and acquiring the behavior characteristics of a plurality of users, clustering the behavior characteristics to obtain a plurality of user categories.
6. An apparatus for determining a coupon issuance policy, comprising:
the first pushing module is used for pushing different types of coupons aiming at users of the target user category;
the transition probability determining module is used for counting the probability that the user of the target user category transfers to other user categories after receiving the coupons of various types, and forming a transition probability matrix of the target user category;
and the strategy determining module is used for determining a strategy for issuing the coupons to the users of the target user category according to the transition probability matrix.
7. The apparatus of claim 6, further comprising:
a second pushing module for: after the strategy determining module determines a strategy for issuing coupons to the users of the target user category according to the transition probability matrix, issuing the coupons to the users of the target user category according to the determined strategy;
the transition probability determination module is further configured to: counting the number of users in the target user category, who are transferred to other user categories after receiving the coupons, and updating the transfer probability matrix according to the number;
the policy determination module is further configured to: and updating a strategy for issuing the coupons to the users of the target user category according to the updated transition probability matrix.
8. The apparatus of claim 6, wherein the policy determination module is specifically configured to: determining the income of the user after the user is transferred from the target user category to each user category; determining the expected profit of the users of the target user category after receiving each coupon according to the profit and the transition probability matrix; determining the most revenue expected coupon, and determining the policy comprises issuing the most revenue expected coupon to the user of the target user category.
9. The apparatus according to claim 8, wherein the determined policy is specifically: and issuing the coupons with the largest profit expectation to a first part of users of the target user category, and issuing the coupons except the coupons with the largest profit expectation to a second part of users of the target user category, wherein the number of the first part of users is larger than that of the second part of users.
10. The apparatus of any one of claims 6 to 9, further comprising: and the clustering module is used for acquiring the behavior characteristics of a plurality of users before the pushing module pushes different types of coupons for the users of the target user category, clustering the behavior characteristics and obtaining a plurality of user categories through clustering.
11. A server, comprising: a memory for storing computer program instructions; the communication module is used for communicating with the user terminal; a processor, coupled to the memory and the communication module, for executing the computer program instructions to perform the method of any of claims 1 to 5 when the computer program instructions are executed.
12. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, performs the method of any one of claims 1 to 5.
CN201810663437.1A 2018-06-25 2018-06-25 Method and device for determining coupon issuing strategy Pending CN110634010A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810663437.1A CN110634010A (en) 2018-06-25 2018-06-25 Method and device for determining coupon issuing strategy

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810663437.1A CN110634010A (en) 2018-06-25 2018-06-25 Method and device for determining coupon issuing strategy

Publications (1)

Publication Number Publication Date
CN110634010A true CN110634010A (en) 2019-12-31

Family

ID=68968701

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810663437.1A Pending CN110634010A (en) 2018-06-25 2018-06-25 Method and device for determining coupon issuing strategy

Country Status (1)

Country Link
CN (1) CN110634010A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111292122A (en) * 2020-01-16 2020-06-16 支付宝(杭州)信息技术有限公司 Method and apparatus for facilitating user to perform target behavior for target object
CN111385351A (en) * 2020-02-20 2020-07-07 珠海格力电器股份有限公司 Cleaning control method, device, terminal and computer readable medium
CN112163879A (en) * 2020-09-18 2021-01-01 深圳市分期乐网络科技有限公司 User rights pushing method, device, server and storage medium
CN112600756A (en) * 2020-09-04 2021-04-02 京东数字科技控股股份有限公司 Service data processing method and device
CN113327141A (en) * 2021-08-03 2021-08-31 南栖仙策(南京)科技有限公司 Travel platform coupon issuing optimization method based on simulation environment
CN114862432A (en) * 2021-02-04 2022-08-05 武汉斗鱼鱼乐网络科技有限公司 Target user determination method and device, electronic equipment and storage medium

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111292122A (en) * 2020-01-16 2020-06-16 支付宝(杭州)信息技术有限公司 Method and apparatus for facilitating user to perform target behavior for target object
CN111385351A (en) * 2020-02-20 2020-07-07 珠海格力电器股份有限公司 Cleaning control method, device, terminal and computer readable medium
CN111385351B (en) * 2020-02-20 2021-05-25 珠海格力电器股份有限公司 Cleaning control method, device, terminal and computer readable medium
CN112600756A (en) * 2020-09-04 2021-04-02 京东数字科技控股股份有限公司 Service data processing method and device
CN112600756B (en) * 2020-09-04 2023-08-04 京东科技控股股份有限公司 Service data processing method and device
CN112163879A (en) * 2020-09-18 2021-01-01 深圳市分期乐网络科技有限公司 User rights pushing method, device, server and storage medium
CN112163879B (en) * 2020-09-18 2024-05-24 深圳市分期乐网络科技有限公司 User rights pushing method, device, server and storage medium
CN114862432A (en) * 2021-02-04 2022-08-05 武汉斗鱼鱼乐网络科技有限公司 Target user determination method and device, electronic equipment and storage medium
CN113327141A (en) * 2021-08-03 2021-08-31 南栖仙策(南京)科技有限公司 Travel platform coupon issuing optimization method based on simulation environment

Similar Documents

Publication Publication Date Title
CN110634010A (en) Method and device for determining coupon issuing strategy
WO2019184583A1 (en) Activity content push method based on electronic book, and electronic device
US20140330741A1 (en) Delivery estimate prediction and visualization system
CN110827138B (en) Push information determining method and device
US10445789B2 (en) Segment-based floors for use in online ad auctioning techniques
US8856130B2 (en) System, a method and a computer program product for performance assessment
CN106415642B (en) Sponsored online content management using query clusters
US11093977B2 (en) Ad ranking system and method utilizing bids and adjustment factors based on the causal contribution of advertisements on outcomes
CN109636490A (en) Real-time predicting method, the advertisement valuation method and system of ad conversion rates
US10713692B2 (en) Systems and methods for user propensity classification and online auction design
CN111667311B (en) Advertisement putting method, related device, equipment and storage medium
US20110264516A1 (en) Limiting latency due to excessive demand in ad exchange
US11514471B2 (en) Method and system for model training and optimization in context-based subscription product suite of ride-hailing platforms
US10181130B2 (en) Real-time updates to digital marketing forecast models
Zhang et al. Online auction-based incentive mechanism design for horizontal federated learning with budget constraint
US20100250362A1 (en) System and Method for an Online Advertising Exchange with Submarkets Formed by Portfolio Optimization
US20220036411A1 (en) Method and system for joint optimization of pricing and coupons in ride-hailing platforms
CN111090677A (en) Method and device for determining data object type
US20140372350A1 (en) System, A Method and a Computer Program Product for Performance Assessment
CN110210885B (en) Method, device, equipment and readable storage medium for mining potential clients
US20140200990A1 (en) Scoring and ranking advertisement content creators
US20220366437A1 (en) Method and system for deep reinforcement learning and application at ride-hailing platform
WO2022081128A1 (en) Systems and methods for automated intervention
CN114596109A (en) Method and device for determining recommendation information, electronic equipment and storage medium
US20150066581A1 (en) Device for increasing self-service adoption

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20191231