CN109389431B

CN109389431B - Method and device for distributing coupons, electronic equipment and readable storage medium

Info

Publication number: CN109389431B
Application number: CN201811161310.6A
Authority: CN
Inventors: 范聪; 李邵明
Original assignee: Beijing Sankuai Online Technology Co Ltd
Current assignee: Beijing Sankuai Online Technology Co Ltd
Priority date: 2018-09-30
Filing date: 2018-09-30
Publication date: 2022-12-27
Anticipated expiration: 2038-09-30
Also published as: CN109389431A

Abstract

The embodiment of the disclosure provides a coupon distribution method, a coupon distribution device, an electronic device and a readable storage medium, wherein the method comprises the following steps: acquiring coupon configuration information of each target merchant, and generating at least one coupon according to the coupon configuration information; aiming at each target user and each target merchant, acquiring user characteristics of the target user and interaction characteristics of the target user and the target merchant; for each target user and each coupon of each target merchant, predicting the use parameters of the target user for the coupon according to the user characteristics of the target user and the interaction characteristics of the target user and the target merchant; and distributing each coupon to each target user according to the use parameters. The coupon distribution method and the system can determine the use parameters of the coupon of the user according to the user characteristics and the interaction characteristics of the user and the merchant, and distribute the coupon according to the use parameters, so that the coupon distribution accuracy is improved.

Description

Coupon distribution method and device, electronic equipment and readable storage medium

Technical Field

The embodiment of the disclosure relates to the technical field of network sales, and in particular relates to a coupon distribution method and device, electronic equipment and a readable storage medium.

Background

To increase the turnover, the network sales platform often pushes coupons to the user to increase the turnover.

In the prior art, a coupon delivery method is proposed in patent application No. CN 2017110717067. The method mainly comprises the following steps: firstly, after a merchant makes a coupon list according to a marketing strategy and stores the coupon list, when a user settles accounts, the user information and shopping information of the consumer are obtained from a system and stored; then, analyzing historical shopping data of the consumer and the shopping information to obtain one or more commodities which the consumer most needs to buy recently; and finally, matching the coupon list from the coupon library according to the commodity which is most needed to be purchased by the consumer recently, screening out a plurality of coupons with the highest matching degree, and sending the coupons to a cash register system.

It can be seen that the above method matches the coupons only through the user's historical shopping data, and the accuracy of distribution is low.

Disclosure of Invention

The embodiment of the disclosure provides a coupon distribution method, a coupon distribution device, electronic equipment and a readable storage medium, which are used for improving the distribution accuracy of coupons.

According to a first aspect of embodiments of the present disclosure, there is provided a method of distributing a coupon, the method including:

acquiring coupon configuration information of each target merchant, and generating at least one coupon according to the coupon configuration information;

aiming at each target user and each target merchant, acquiring user characteristics of the target user and interaction characteristics of the target user and the target merchant;

for each target user and each coupon of each target merchant, predicting the use parameters of the target user for the coupon according to the user characteristics of the target user and the interaction characteristics of the target user and the target merchant;

and distributing each coupon to each target user according to the use parameters.

According to a second aspect of embodiments of the present disclosure, there is provided a coupon dispensing apparatus, the apparatus including:

the coupon generating module is used for acquiring the coupon configuration information of each target merchant and generating at least one coupon according to the coupon configuration information;

the characteristic acquisition module is used for acquiring the user characteristics of the target user and the interaction characteristics of the target user and the target merchant aiming at each target user and each target merchant;

the usage parameter determining module is used for predicting usage parameters of the coupons of the target users according to the user characteristics of the target users and the interaction characteristics of the target users and the target merchants aiming at each target user and each coupon of each target merchant;

and the coupon distribution module is used for distributing each coupon to each target user according to the use parameters.

According to a third aspect of embodiments of the present disclosure, there is provided an electronic apparatus including:

a processor, a memory, and a computer program stored on the memory and executable on the processor, wherein the processor implements the aforementioned coupon distribution method when executing the program.

According to a fourth aspect of embodiments of the present disclosure, there is provided a readable storage medium, wherein instructions, when executed by a processor of an electronic device, enable the electronic device to perform the aforementioned coupon distribution method.

The embodiment of the disclosure provides a coupon distribution method, a coupon distribution device, an electronic device and a readable storage medium, wherein the method comprises the following steps: obtaining coupon configuration information of each target merchant, and generating at least one coupon according to the coupon configuration information; aiming at each target user and each target merchant, acquiring user characteristics of the target user and interaction characteristics of the target user and the target merchant; for each target user and each coupon of each target merchant, predicting the use parameters of the target user for the coupons according to the user characteristics of the target user and the interaction characteristics of the target user and the target merchant; and distributing each coupon to each target user according to the use parameters. The coupon distribution method and the system can determine the use parameters of the coupon of the user according to the user characteristics and the interaction characteristics of the user and the merchant, and distribute the coupon according to the use parameters, so that the coupon distribution accuracy is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required to be used in the description of the embodiments of the present disclosure will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and it is also possible for those skilled in the art to obtain other drawings based on the drawings without inventive labor.

FIG. 1 shows a flow chart of steps of a method of distribution of coupons in one embodiment of the present disclosure;

FIG. 2 shows a flow chart of steps of a method of coupon distribution in another embodiment of the present disclosure;

FIG. 3 shows a schematic diagram of a usage parameter matrix;

FIG. 4 shows a block diagram of a coupon dispensing apparatus in one embodiment of the present disclosure;

FIG. 5 shows a block diagram of a coupon dispensing apparatus in another embodiment of the present disclosure;

fig. 6 shows a block diagram of an electronic device provided by an embodiment of the present disclosure.

Detailed Description

Technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is apparent that the described embodiments are some, but not all, of the embodiments of the present disclosure. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present disclosure, belong to the protection scope of the embodiments of the present disclosure.

Example one

Referring to fig. 1, a flow chart of steps of a coupon distribution method in one embodiment of the present disclosure is shown, including:

step 101, obtaining coupon configuration information of each target merchant, and generating at least one coupon according to the coupon configuration information.

Wherein the target merchant pays and registers on the application platform, and then can sell goods or other services through the platform.

The coupon is a preferential strategy provided by an application platform or a merchant to stimulate consumption, and is usually realized by the coupon. So that the user can use the coupon to reduce the consumption amount when consuming at the merchant.

Coupon configuration information includes, but is not limited to: merchant information, coupon thresholds, and coupon levels. It will be appreciated that the merchant information may be merchant identification and/or merchant name information, the threshold of the coupon may be a minimum mean price per unit that the coupon must satisfy when in use, and the benefit may be a reduced denomination. For example, for a coupon "full 100 minus 20", the threshold is 100 and the offer level is 20.

It is to be appreciated that the coupon configuration information can be set at the time of registration of the target merchant, or can be set or modified after registration. In addition, one or more types of coupon configuration information can be set for the same target merchant, and each type of coupon configuration information can generate at least one coupon correspondingly.

In practical applications, the coupon configuration information may be stored in a database corresponding to the application platform based on the merchant information.

And 102, aiming at each target user and each target merchant, acquiring the user characteristics of the target user and the interaction characteristics of the target user and the target merchant.

The target user may be an active user of the application platform, that is, a user who purchases goods or performs other services by registering the application platform or logging in the application platform.

In practical applications, a corresponding relationship between the target merchant and the target user may be established, that is: the target merchants can be all merchants in a certain range near the resident position of the target user, wherein the resident position can be the current position of the target user, and if the current position fails to be located, the position with the largest occurrence number is obtained from the historical order information of the user and is used as the resident position. For example, for instant delivery of goods, since the goods to be delivered are often sent to the user within a certain time, the target merchant may set a delivery range, that is, only order of the user within the delivery range is accepted.

User characteristics include, but are not limited to: channel information for user initiated orders, channel information for coupons, number of orders in recent historical time periods, average number of orders per week, average number of orders per month, average price of orders in recent historical orders, user type.

The channel information for initiating the order can be a mode for initiating the order by the user. Such as others recommendations, application platforms, etc.

The channel information of the coupon may be the source of the coupon, including but not limited to: shared red envelope, sky red envelope, coupon center.

The average price of the bill is the average consumption amount of each order of the user and can be divided into an average price of an original price bill and an average price of an actual payment bill, wherein the average price of the original price bill is the average consumption amount before the discount, and the average price of the actual payment bill is the actual average consumption amount after the discount.

The user types can be classified according to age classification and professional characteristics. For example, students, workers, etc. are classified according to occupational characteristics.

The interaction characteristics of the target user and the target merchant include, but are not limited to: and the target user has the characteristics of operations such as access, order placing, bargaining and collection of the target merchant. The access is a behavior that the user enters a target merchant to browse commodities, the order placing is a behavior that the user purchases commodities at the target merchant, the transaction is a behavior that the commodities placed by the user complete a transaction, and the collection is a behavior that the user adds the commodities into a collection list and indicates that the user has a purchasing intention on the commodities.

It can be understood that the channel information, the order number, the average price of the orders and the interactive features in the user features can be obtained from a platform log, the user type can be obtained from a configuration database of the application platform, and the user type can be written into the configuration database when the user registers.

Step 103, predicting the use parameters of the target user for the coupons according to the user characteristics of the target user and the interaction characteristics of the target user and the target merchants aiming at each target user and each coupon of each target merchant.

The usage parameter of the coupon by the target user can indicate the possibility of using the coupon by the user. For example, the larger the usage parameter, the more likely the usage; the smaller the usage parameter, the less likely the usage.

In the embodiment of the disclosure, the usage parameters are related to not only the channel information of the target user initiating the order, the number of orders in the recent history time period, the average number of orders per week, the average number of orders per month, the average price of the orders in the recent history orders, and the user type, but also the characteristics of the target user's operations of visiting, placing orders, bargaining, collecting and the like to the target merchant, so that the obtained usage parameters are more accurate.

It can be understood that the channel information of the order initiated by the target user can reflect which channel is frequently used by the target user for placing an order, and the use parameter of the frequently used channel is usually larger.

The larger the number of orders in the most recent historical time period, the larger the average number of orders per week, the larger the average number of orders per month, the larger the usage parameters are typically; the smaller the number of orders in the most recent historical time period, the smaller the average number of orders per week, and the smaller the average number of orders per month, the smaller the usage parameters are typically.

The average price of the orders in the recent historical order determines which coupon is more likely to be used by the user. For example, when the unit average price is 50, only coupons with a threshold less than 50 can be used, and coupons with a threshold greater than or equal to 50 cannot be used.

The user type can analyze the consuming ability of the user and the preference goods, so that the possibility of using which coupon is high can be determined. For example, for students, low threshold coupons are likely to be used due to poor economic performance; for high-end business personnel, the economic ability is strong, so that the consumption ability is strong, and the use possibility of high-threshold coupons is high.

The characteristics of the access operation of the target user to the target merchant can be comprehensively determined by using the access time and the access times, for example, the closer the access time is to the current time, the more the access times are, the higher the use possibility is; the earlier the access time, the fewer the number of accesses, and the smaller the possibility of use.

The characteristics of the order placing operation of the target user on the target merchant can be comprehensively determined by the order placing time and the order placing times, for example, the closer the order placing time is to the current time, the more the order placing times are, the higher the use possibility is; the earlier the order placing time is, the fewer the order placing times are, and the smaller the use possibility is.

The characteristics of the transaction operation of the target user to the target merchant can be comprehensively determined by the transaction time and the transaction times, for example, the closer the transaction time is to the current time, the more the transaction times are, the higher the use possibility is; the earlier the transaction time is, the fewer the number of transactions is, and the less the possibility of use is.

The characteristics of the collection operation of the target user on the target merchant can be comprehensively determined by the collection time and the collection times, for example, the collection time is closer to the current time, the collection times are more, and the use possibility is higher; the earlier the collection time, the less the collection times and the less the possibility of use.

And 104, distributing the coupons to the target users according to the use parameters.

Specifically, if the usage parameter of the target user to the coupon is larger, the coupon is preferentially distributed to the target user; if the usage parameter of the coupon by the target user is smaller, the priority of the target user is lower when the coupon is distributed.

In practical applications, the coupon may be sent to the account where the target user is located. The account may be an account that the target user registers and logs in on the application platform.

In the embodiment of the invention, the coupon can be preferentially distributed to the user who is most likely to use the coupon, so that the utilization rate of the coupon can be effectively improved, and the income of merchants can be improved.

In summary, an embodiment of the present disclosure provides a method for distributing a coupon, where the method includes: acquiring coupon configuration information of each target merchant, and generating at least one coupon according to the coupon configuration information; aiming at each target user and each target merchant, acquiring user characteristics of the target user and interaction characteristics of the target user and the target merchant; for each target user and each coupon of each target merchant, predicting the use parameters of the target user for the coupons according to the user characteristics of the target user and the interaction characteristics of the target user and the target merchant; and distributing each coupon to each target user according to the use parameters. The coupon distribution method and the system can determine the use parameters of the coupon of the user according to the user characteristics and the interaction characteristics of the user and the merchant, and distribute the coupon according to the use parameters, so that the coupon distribution accuracy is improved.

Example two

Referring to fig. 2, a flow chart of steps of a coupon distribution method in another embodiment of the present disclosure is shown, as follows.

Step 201, obtaining the coupon configuration information of each target merchant, and generating at least one coupon according to the coupon configuration information.

For this step, reference may be made to the detailed description of step 101, which is not described herein again.

Step 202, aiming at each target user and each target merchant, obtaining the user characteristics of the target user and the interaction characteristics of the target user and the target merchant.

This step can refer to the detailed description of step 102, and is not described herein again.

Step 203, calculating the ratio of the average price per unit of the target user to the threshold value of the coupon for each target user and each coupon of each target merchant to obtain a first matching sub-parameter.

In particular, for the target user U _i Coupons C _j First matching sub-parameter MAT1 _i,j The formula (c) is as follows:

wherein, PRC _i Is a target user U _i Mono-valent of (D), THS _j As a coupon C _j The threshold value of (c).

According to the formula, if the unit average price is larger and the threshold value is smaller, the first matching sub-parameter is larger; if the smaller the unit average price is, the larger the threshold value is, the smaller the first matching sub-parameter is.

It should be understood that, in practical applications, a logarithm, an exponential, or a linear transformation may be further performed on the ratio of the single average value to the threshold value to obtain the first matching sub-parameter, and the specific relationship between the first matching sub-parameter and the ratio of the single average value to the threshold value is not limited in the embodiment of the present invention.

And 204, determining matching parameters of the target user and the coupons according to the first matching sub-parameters aiming at each target user and each coupon of each target merchant.

It is understood that the larger the first matching parameter, the larger the matching parameter; the smaller the first matching parameter, the smaller the matching parameter.

Specifically, the matching parameter may be a linear, a logarithmic, an exponential, or the like of the first matching sub-parameter, and the specific relation is not limited in the embodiment of the present invention.

Optionally, in another embodiment of the present disclosure, the user characteristic includes an offer sensitivity parameter, the coupon characteristic includes an offer level parameter, and the step 204 includes sub-steps 2041 to 2042:

substep 2041, aiming at each target user and each coupon of each target merchant, calculating the ratio of the coupon degree parameter to the coupon sensitive parameter of the target user to obtain a second matching subparameter.

The preference degree parameter is used for representing the preference degree of the coupon, and can be represented by a ratio or a deduction amount. For example, for a coupon "full 100 minus 20", the offer level parameter may be 20, or may be a ratio of 20 to 100 of 0.2. It can be understood that the larger the preference degree parameter is, the greater the preference degree is; the smaller the preference degree parameter is, the smaller the preference degree is.

The coupon sensitivity parameter represents the preference degree of the user for using the coupon, and can be represented by the using frequency of the coupon of the user. It can be understood that the higher the frequency of use, the higher the user's preference for using coupons; the less frequent the usage, the less the user will prefer to use the coupon.

In particular, for the target user U _i Coupons C _j Second match sub-parameter MAT2 _i,j The calculation formula of (a) is as follows:

wherein, FRLVL _j As a coupon C _j Preference level parameter of (F), FRSST _i Is a target user U _i The offer sensitivity parameter.

It can be seen from the above formula that the larger the preference degree parameter is, the smaller the preference sensitive parameter is, the larger the second matching sub-parameter is; the smaller the preference degree parameter is, the larger the preference sensitive parameter is, and the smaller the second matching sub-parameter is.

It can be understood that, in practical application, a logarithm, an exponential, or a linear transformation may also be taken on a ratio of the benefit degree parameter to the benefit sensitive parameter to obtain the second matching subparameter.

Substep 2042, aiming at each target user and each coupon of each target merchant, determining matching parameters of the target user and the coupon according to the first matching sub-parameter and the second matching sub-parameter.

It is understood that based on the relationship between the first matching subparameter and the matching parameter in step 204, the larger the second matching parameter is, the larger the matching parameter is; the smaller the second matching parameter, the smaller the matching parameter.

Specifically, the matching parameter may be a linear weighting, a product, or the like of the first and second matching sub-parameters, and the embodiment of the present invention does not limit the specific relation.

Optionally, in another embodiment of the present disclosure, the sub-step 2042 includes sub-steps 20421 to 20424:

substep 20421, calculating the product of the first matching subparameter and a preset first matching weight for each target user and each coupon of each target merchant, and obtaining a first matching numerical value.

In particular, for the target user U _i Coupon C _j First matching sub-parameter MATVU1 _i,j The calculation formula of (c) is as follows:

wherein, w ₁ The first matching weight may be set according to an actual application scenario, and is not limited by the embodiments of the present disclosure.

It can be understood that w ₁ The larger the result is, the larger the influence of the first matching subparameter on the matching parameter is; w is a ₁ The smaller the first matching sub-parameter is, the smaller the influence of the first matching sub-parameter on the matching parameter is.

Substep 20422, calculating the product of the second matching subparameter and the preset second matching weight for each target user and each coupon of each target merchant, and obtaining a second matching numerical value.

In particular, for the target user U _i Coupon C _j Second match value MATVU2 _i,j The calculation formula of (a) is as follows:

wherein, w ₂ The second matching weight may be set according to an actual application scenario, and embodiments of the present disclosure do not limit this.

It can be understood that w ₂ The larger the result is, the larger the influence of the second matching subparameter on the matching parameters is; w is a ₂ The smaller the second matching sub-parameter is, the smaller the influence of the second matching sub-parameter on the matching parameter is.

Substep 20423, for each coupon of each target user and each target merchant, calculating the product of the coupon degree parameter and the preset third matching weight to obtain a third matching numerical value.

In particular, for coupon C _j Third matching value MATVU3 _j The calculation formula of (c) is as follows:

MATVU3 _j ＝w ₃ ·FRLVL _j (5)

wherein w ₃ The third matching weight may be set according to an actual application scenario, and is not limited by the embodiment of the present disclosure.

Can cleanSolution of w ₃ The larger the preference degree parameter is, the larger the influence of the preference degree parameter on the matching parameter is; w is a ₃ The smaller the preference parameter is, the smaller the influence of the preference parameter on the matching parameter is.

Substep 20424, calculating the sum of the first matching value, the second matching value and the third matching value for each target user and each coupon of each target merchant, and obtaining the matching parameters of the target user and the coupon.

In particular, for the target user U _i Coupon C _j Match parameter MAT _i,j The calculation formula of (c) is as follows:

step 205, for each target user, prohibiting the distribution of the coupon with the matching parameter smaller than a preset matching threshold value to the target user.

The matching threshold may be set according to a formula of the matching parameter, a value of data used in the formula, and an actual application scenario, which are not limited in the embodiments of the present disclosure.

Specifically, the coupons with matching parameters less than the matching threshold may be marked, so that the distribution of the coupons to the target users is avoided during distribution, and the coupons for the target users may also be directly deleted.

As can be seen from equation (6), the embodiments of the present disclosure have the following advantages: firstly, distributing coupons with equivalent single average price and threshold to target users, and avoiding distributing coupons with high threshold to target users with low single average price; then, distributing the coupons with larger discount degree parameters to the target users with higher discount sensitivity, and avoiding distributing the coupons with low discount degree by the target users with high discount sensitivity and distributing the coupons with high discount degree by the target users with low discount sensitivity; finally, coupons with higher preference degree parameters are preferentially distributed.

And step 206, aiming at each target user and each coupon of each target merchant, acquiring merchant characteristics of the target merchant and coupon characteristics of the coupon.

Among other features of the merchant are, but not limited to: the number of historical orders of the merchant over the last period of time, the click rate of the user on the merchant, the conversion rate, etc.

The click rate is the ratio of the number of clicks of the user to the merchant to the number of impressions of the merchant in a period of time. For example, for a merchant, the merchant is shown M times under the recommendation of the platform, wherein N times are clicked, and the click rate is N/M.

The conversion rate is the ratio of the number of effective operations of the user to the merchant to the number of clicks in a period of time. For example, for a merchant, N times are clicked, wherein L times of order placement operations exist, the conversion rate is L/N.

It will be appreciated that the historical number of orders, the user's click-through rate to the merchant, and the conversion rate may all be obtained from the user's historical access records to the merchant.

Coupon features include, but are not limited to: historical usage, inventory, deduction amount, and discount rate.

Wherein the historical usage rate is the ratio of the number of the tickets used by the user in the historical time period to the total number of the distribution.

The inventory amount is the maximum number of coupons dispensed, and decreases as coupons are dispensed.

The benefit rate may be a ratio of the deduction amount to a threshold. For example, for a coupon "full 100 minus 20", since the deduction amount is 20 and the threshold is 100, the benefit rate is 0.2.

It can be understood that the historical usage rate can be counted from the historical usage record of the coupon by the user, the inventory can be obtained from a designated database, and the deduction amount and the discount rate can be obtained or counted from the corresponding coupon.

And step 207, inputting the user characteristics of the target user, the interaction characteristics of the target user and the target merchant, the merchant characteristics of the target merchant and the coupon characteristics of the coupon into a pre-trained use probability prediction model to obtain the use probability of the coupon by the target user.

The use probability is the use possibility of the coupon by the target user, and the higher the use probability is, the more likely the user is to use the coupon; the smaller the probability of use, the less likely the user is to use the coupon. The probability of use can thus be used to guide the distribution of coupons to users who are most likely to use the coupon.

The probability model can be obtained by training by adopting an XGBOOST model. The XGBOOST model is a binary model, and in the embodiment of the present disclosure, samples of user characteristics, interaction characteristics, merchant characteristics, and coupon characteristics are labeled as whether the user uses a coupon.

The user characteristic is the user characteristic of the user, the interactive characteristic is the interactive characteristic of the user and a merchant to which the coupon belongs, the merchant characteristic is the characteristic of the merchant to which the coupon belongs, and the coupon characteristic is the characteristic of the coupon.

And 208, the coupon characteristics comprise a discount degree parameter, and the discount degree parameter of each coupon of each target merchant is increased according to a preset increase.

Wherein, the increment may be increased step by step within a certain range, for example, if the preference parameter is represented by the exempt denomination, the increment may be increased step by step 10 within a range of 100 to 150; if the preference level parameter is expressed as a ratio, the increase may be increased stepwise by 5% in steps in the range of 10% to 50%.

It is to be understood that the increase range and the increase amount may be set according to an actual application scenario, and the embodiment of the disclosure does not limit the increase range and the increase amount.

Optionally, in another embodiment of the present disclosure, the step 208 includes sub-steps 2081 to 2087:

substep 2081, calculating the sum of a preset increment and the discount degree parameter of the coupon for each coupon of each target merchant to obtain the increased discount degree parameter.

In particular, for coupon C _j Increased preference level parameter FRLVL' _j Can be based onThe following formula is calculated:

FRLVL′ _j ＝INCRE+FRLVL _j (7)

wherein INCEL is an increase, FRLVL _j Is the original preference degree parameter.

Substep 2082, for each target user, inputting the user characteristics of the target user, the interaction characteristics of the target user and the target merchant, the merchant characteristics of the target merchant, and the changed coupon characteristics into the usage probability prediction model to obtain a second usage probability of the coupon by the target user, wherein the changed coupon characteristics include increased coupon degree parameters.

It can be understood that the coupon degree parameter is the coupon feature of the coupon, and the coupon degree parameter is increased, so that the use parameter or the use probability of the coupon by the user needs to be estimated again.

Substep 2083, calculating, for each target user, a difference between the second usage probability and a first usage probability, where the first usage probability is a usage probability of the coupon before the target user increases the preference level parameter.

In particular, for the target user U _i Coupon C _j For the difference DIS between the second usage parameter and the first usage parameter _j The following formula can be used for calculation:

DIS _i,j ＝UsePar′ _i,j -UsePar _i,j (8)

wherein, useParar' _i,j For the second use parameter, usepar _i,j Is the first usage parameter.

Substep 2084, calculating the product of the single average price of the target user and the difference value for each target user to obtain a profit parameter.

Wherein the benefit parameter is used to represent the degree of benefit resulting from the increased probability of use. The larger the profit parameter is, the larger the profit degree is; the smaller the benefit parameter, the smaller the benefit degree.

In particular, for the target user U _i Coupon C _j Profit parameter BFT _i,j Can be based onCalculated by the following formula:

BFT _i,j ＝PRC _i ·DIS _i,j ＝PRC _i ·(UsePar′ _i,j -UsePar _i,j ) (9)

substep 2085, calculating the product of the increment and the second usage probability for each target user to obtain a cost parameter.

The cost parameter is used for representing the cost increase caused by adding the preference degree parameter, and the cost increase is larger when the cost parameter is larger; the smaller the cost parameter, the smaller the cost increase.

In particular, for the target user U _i Coupons C _j Cost parameter CST _i,j Can be calculated according to the following formula:

CST _i,j ＝INCRE·UsePar′ _i,j (10)

and a substep 2086 of calculating the ratio of the benefit parameter to the cost parameter for each target user to obtain a benefit index.

Wherein the profit index is used to determine whether it is worth increasing the preference level parameter. The larger the profit index is, the more worthwhile the increase of the preference degree parameter is; the smaller the profit index, the less worthwhile is to increase the preference parameter.

In particular, for the target user U _i Coupons C _j Profit index BFIN _i,j Can be calculated according to the following formula:

substep 2087, for each target user, updating the discount degree parameter of the coupon to the increased discount degree parameter when the profit index is greater than a preset profit index threshold value.

The profit index threshold is used for determining whether to increase the discount degree parameter, and the larger the profit index threshold is, the smaller the number of coupons with the discount degree parameter increased is; the fewer the revenue index threshold, the greater the number of coupons that increase the benefit level parameter. It is to be understood that the profit index threshold may be set according to an actual application scenario, and embodiments of the present disclosure do not limit it.

In the embodiment of the disclosure, in order to improve the competitiveness of the platform, the merchant ticket is added on the basis of the original preference degree parameter of the merchant ticket, and the cost corresponding to the increased amount is provided by the platform.

And 209, for each target user, adjusting the use probability of the coupon of the target user according to the increased discount degree parameter.

It will be appreciated that since the preference level parameter is a coupon feature of the coupon, which has an effect on the probability of use, the probability of use is re-predicted after the preference level parameter is increased.

Optionally, in another embodiment of the present disclosure, the step 209 includes the sub-step 2091:

substep 2091, updating the usage probability of the coupon by the target user to the second usage probability.

It will be appreciated that the second usage probability is calculated in sub-step 2085, thereby directly replacing the usage probability with the original usage probability.

And step 210, determining a penalty factor of the target user for the coupon according to the increment for each target user.

Wherein the penalty factor is used for properly reducing the increased usage probability.

In the embodiment of the disclosure, since the platform adds the preference degree parameter to the coupon, resulting in cost increase, in order to keep the cost properly, after adding the preference degree parameter, the usage parameter is adjusted by a penalty factor. It is understood that the penalty factor is less than or equal to 1.

It will be appreciated that for coupons that do not have an increased preference level parameter, the penalty factor is 0. In addition, the larger the increment is, the larger the discount degree parameter is, and the larger the threshold value is, the larger the penalty factor is; the larger the increment is, the smaller the preference degree parameter is, and the smaller the threshold value is, the smaller the penalty factor is.

Optionally, in another embodiment of the present disclosure, the step 210 includes a sub-step 2101:

in substep 2101, the increment, the merchant characteristics of the target merchant, and the coupon characteristics of the coupon are input into a penalty prediction model obtained by pre-training to obtain a penalty factor of the target user on the coupon, wherein the coupon characteristics are the coupon characteristics after the coupon degree parameters are increased.

The penalty prediction model can be obtained through training, and the trained samples can be coupons marked with penalty factors, increment of discount degree parameters of the coupons, merchant characteristics of target merchants to which the coupons belong and coupon characteristics of the coupons. The penalty factor may be labeled according to the description in step 210.

In embodiments of the present disclosure, the SIGMOID function may be employed as an activation function for the training process.

Step 211, calculating a product of an adjustment factor and the second usage probability for each target user to obtain a usage probability after penalty, wherein the sum of the adjustment factor and the penalty factor is 1.

In particular, for the target user U _i Coupon C _j Use parameter after penalty UsePar ″ _i,j Can be calculated according to the following formula:

UsePar″ _i,j ＝UsePar′ _i,j ·(1-LIN _j ) (12)

wherein LIN _j As a coupon C _j Of Usemar' _i,j Is the second usage parameter.

And step 212, for each target merchant, predicting the maximum coupon sending number of the target merchant in the current coupon sending period.

The coupon issuing period may be day, week, month, etc., and the specific duration of the coupon issuing period is not limited by the embodiments of the present disclosure.

Specifically, the maximum coupon sending number of the current coupon sending period can be estimated according to the actual coupon sending number and the usage number of the historical coupon sending period, and when the number of the issued coupons of the merchant reaches the maximum coupon sending number, the distribution of the coupons is stopped.

Optionally, in another embodiment of the present disclosure, the step 212 includes sub-steps 2121 to 2124:

and a substep 2121 of counting the total number of issued tickets and the number of used tickets of each target merchant in the last issuing period for each target merchant.

The total number of issued coupons is the total number of coupons distributed to each target user by the target merchants; the coupon use number is the total number of coupons each target user uses the target merchant to assign.

And a substep 2122 of calculating the ratio of the number of the used coupons to the total number of the issued coupons for each target merchant to obtain a usage percentage.

Specifically, for the target merchant S _k Use ratio UsePP _k Can be calculated according to the following formula:

wherein, numUse _k For the target merchant S _k Number of tickets used, numTtl _k For the target merchant S _k Total number of coupons issued.

And a substep 2123 of calculating, for each target merchant, a ratio of the usage percentage of the target merchant to the total usage percentage to obtain an estimated coupon sending percentage, wherein the total usage percentage is the sum of the usage percentages of the target merchants.

Specifically, for target merchant S _k ESPP with estimated coupon distribution ratio _k Can be calculated according to the following formula:

wherein K is the total number of target merchants, and the target merchant S _l Is a variable merchant, usePP _l For the target merchant S _l Using ratio of (1), numUse _l 、NumTtl _l Are respectively the targetMerchant S _l The number of used coupons and the total number of issued coupons.

And a substep 2124 of calculating the product of the estimated coupon sending percentage and the preset cellular coupon sending total number aiming at each target merchant to obtain the maximum coupon sending number of the target merchant in the current coupon sending period.

Specifically, for target merchant S _k The maximum coupon number NumMax of the target merchant in the current coupon period _k Can be calculated according to the following formula:

NUM is the total number of the cellular coupons, and can be set according to practical application scenarios, which is not limited by the embodiment of the present disclosure.

In practical application, the coupons are distributed by taking a cellular area as a unit, the cellular area is provided with a total number of issued coupons, and the coupons of target merchants in the cellular area are distributed to target users in the cellular area until the total number of sent coupons reaches the total number of cellular issued coupons. It can be understood that the larger the total number of cellular coupons is, the larger the maximum coupon number of each target merchant in the current coupon period is; the smaller the total number of the cellular coupons is, the smaller the maximum coupon number of each target merchant in the current coupon period is. In addition, under the condition that the total number of the cellular coupons is fixed, the larger the usage proportion of the target merchant in the last coupon sending period is, the larger the maximum coupon sending number of the target merchant in the current coupon sending period is; the smaller the usage proportion of the target merchant in the last coupon period is, the smaller the maximum coupon number of the target merchant in the current coupon period is.

And step 213, distributing each coupon to each target user according to the maximum coupon sending number and the use parameters.

And the maximum number of issued coupons is used for controlling the number of issued coupons of the target merchant, and when the number of issued coupons reaches the value, the coupon distribution to the target user is stopped.

This step can refer to the detailed description of step 104, and will not be described herein.

Optionally, in another embodiment of the present disclosure, the step 213 includes sub-steps 2131 to 2132:

sub-step 2131, selecting the element with the largest usage parameter from the usage parameter matrix to obtain a coupon sending element, where each element in the usage parameter matrix includes a target user, a target merchant, a coupon, and a usage parameter of the target user for the coupon.

In the embodiment of the present disclosure, the rows of the parameter matrix correspond to the target users, and the columns correspond to the coupons of the target merchants, as shown in fig. 3, I and J are the number of the target users and the number of the coupons, respectively, and the first behavior user U ₁ Second behavior user U for usage parameters of J coupons ₂ Usage parameters for J coupons, and so on. Thus, sub-step 2121 can be understood as selecting the element with the largest usage parameter from each row, for example, for the first row, if the element with the largest usage parameter is UsePar _1,2 Then represents U for the target user ₁ The target user is to the coupon C _j The usage parameter of (2) is maximal.

Sub-step 2132, in case that the number of issued tickets of the target merchant contained in the issuing element is smaller than the maximum number of issued tickets of the target merchant, distributing the coupons contained in the issuing element to the target users contained in the issuing element, wherein the number of issued tickets is updated after each issuing.

Wherein the number of issued coupons is initially set to 0 and updated once per coupon is assigned, i.e.: plus the number of coupons assigned.

Specifically, the coupon may be sent to an account where the target user is located, so that the target user may use the coupon when logging in through the account.

In practical applications, since each coupon is only allocated once, the target user only allocates one coupon, so that after one coupon is allocated to one target user each time, the row and column where the coupon sending element is located are deleted from the usage parameter matrix.

In the embodiment of the present disclosure, after a coupon of a target merchant is allocated to a target user, the row and column where the coupon element is located are deleted from the usage parameter matrix, that is: the coupon and the target user are invalidated.

The embodiment of the disclosure can select a coupon with the largest use parameter from all coupons of all merchants for each target user, so that the coupon can be guaranteed to be used as far as possible.

Optionally, in another embodiment of the present disclosure, the step 213 includes sub-steps 2133 to 2135:

sub-step 2133, for each target merchant, determining a usage parameter threshold value according to the usage parameter and the maximum number of issued tickets.

Wherein the usage parameter threshold is used to determine whether to distribute the coupon.

Specifically, firstly, for each coupon of each merchant, the use parameters of each target user for each coupon are arranged according to a descending order; then, acquiring a use parameter with the sequence number of the sequencing position as the maximum number of issued tickets as a first reference use parameter, and acquiring a use parameter of the next position as a second reference use parameter; and finally, taking the value which is less than or equal to the first reference use parameter and greater than the second reference use parameter as a use parameter threshold value. For example, if the target user U ₁ For coupon C ₁ 、C ₂ 、C ₃ Are 0.5, 0.3, 0.1, respectively, target user U ₂ For coupon C ₁ 、C ₂ 、C ₃ 0.4, 0.2, 0.1, the sorted usage parameters are 0.5, 0.4, 0.3, 0.2, 0.1, when the maximum number of coupons is 2, the first usage parameter is 0.4, the second usage parameter is 0.3, and the usage parameter threshold may be selected to be a value less than or equal to 0.4 and greater than 0.3.

It will be appreciated that in practical applications, the first reference usage parameter may be directly selected as the usage parameter threshold.

Sub-step 2134, selecting the element with the largest usage parameter from the usage parameter matrix to obtain a coupon sending element, where each element in the usage parameter matrix includes a target user, a target merchant, a coupon, and a usage parameter of the target user for the coupon.

As shown in FIG. 3, if the first to 2 nd columns are the target merchants S ₁ The coupon of (4), the coupon issuing elements are obtained from the first column to the second column.

Sub-step 2135, if the usage parameter is greater than or equal to the usage parameter threshold corresponding to the target merchant, distributing the coupon included in the coupon element to the target user included in the target element.

It will be appreciated that when the usage parameter is less than the usage parameter threshold, the distribution of the targeted merchant's coupons to any targeted users is stopped and the targeted merchant's coupon distribution ends.

And similarly, deleting the row and the column where the coupon element is positioned from the use parameter matrix.

Optionally, in another embodiment of the present disclosure, for the above usage parameter threshold, the adjustment may be performed according to the following steps A1 to A4:

step A1, counting the actual number of issued tickets of each target merchant in the last adjustment period, wherein the last adjustment period is a sub-period in the current issuing period.

And at the end of the coupon distribution of the target merchant, the number of issued coupons is the actual number of issued coupons.

In the embodiment of the disclosure, one coupon sending period is divided into a plurality of adjusting periods, and after each adjusting period is finished, the use parameter threshold value is adjusted according to the actual coupon sending number, so that the actual coupon sending number of the ring sending period is close to or equal to the estimated maximum coupon sending number.

And step A2, calculating the ratio of the actual ticket issuing number to the actual cellular ticket issuing number for each target merchant to obtain the actual ticket issuing ratio, wherein the actual cellular ticket issuing number is the sum of the actual ticket issuing numbers of the target merchants in the last adjustment period.

Specifically, for target merchant S _k Actual coupon ratio ACTPP _k Can be calculated according to the following formula:

wherein, numACT _k For the target merchant S _k Number of actual coupons sent, numACT _l For any merchant S _l The actual number of coupons issued.

And A3, calculating the ratio of the actual coupon sending ratio to the estimated coupon sending ratio for each target merchant to obtain a threshold value adjusting parameter.

Specifically, for target merchant S _k Threshold adjustment parameter TPAR _k Can be calculated according to the following formula:

and A4, calculating the product of the threshold value adjusting parameter and the use parameter threshold value aiming at each target merchant to obtain the adjusted use parameter threshold value.

Specifically, for target merchant S _k Adjusted use parameter threshold value THR' _k Can be calculated according to the following formula:

wherein, THR _k For the target merchant S _k The usage parameter threshold before adjustment.

It is understood that the dynamic adjustment of the usage parameter threshold values in steps A1 to A4 may be performed at the end of each adjustment period, so that the accuracy of the usage parameter threshold values may be ensured.

EXAMPLE III

Referring to fig. 4, a block diagram of a coupon dispensing apparatus in one embodiment of the present disclosure is shown, as follows.

The coupon generating module 301 is configured to obtain coupon configuration information of each target merchant, and generate at least one coupon according to the coupon configuration information.

A feature obtaining module 302, configured to obtain, for each target user and each target merchant, a user feature of the target user and an interaction feature of the target user and the target merchant.

And the usage parameter determining module 303 is configured to predict, for each target user and each coupon of each target merchant, a usage parameter of the coupon by the target user according to the user characteristic of the target user and the interaction characteristic of the target user and the target merchant.

And the coupon distribution module 304 is used for distributing each coupon to each target user according to the use parameters.

In summary, an embodiment of the present disclosure provides a device for distributing coupons, the device including: the coupon generating module is used for acquiring the coupon configuration information of each target merchant and generating at least one coupon according to the coupon configuration information; the characteristic acquisition module is used for acquiring the user characteristics of the target user and the interaction characteristics of the target user and the target merchant aiming at each target user and each target merchant; the use parameter determining module is used for predicting the use parameters of the target user on the coupons according to the user characteristics of the target user and the interaction characteristics of the target user and the target merchants aiming at each target user and each coupon of each target merchant; and the coupon distribution module is used for distributing each coupon to each target user according to the use parameters. The coupon distribution method and the system can determine the use parameters of the coupon of the user according to the user characteristics and the interaction characteristics of the user and the merchant, and distribute the coupon according to the use parameters, so that the coupon distribution accuracy is improved.

The third embodiment of the apparatus corresponds to the first embodiment of the method, and the detailed description may refer to the first embodiment, which is not repeated herein.

Example four

Referring to fig. 5, there is shown a block diagram of a coupon dispensing apparatus in another embodiment of the present disclosure, as follows.

The coupon generating module 401 is configured to obtain coupon configuration information of each target merchant, and generate at least one coupon according to the coupon configuration information.

A feature obtaining module 402, configured to obtain, for each target user and each target merchant, a user feature of the target user and an interaction feature of the target user and the target merchant.

A first matching sub-parameter determining module 403, configured to calculate, for each target user and each coupon of each target merchant, a ratio of a unit average price of the target user to a threshold value of the coupon, so as to obtain a first matching sub-parameter.

And a first matching parameter determining module 404, configured to determine, for each target user and each coupon of each target merchant, a matching parameter between the target user and the coupon according to the first matching sub-parameter.

Optionally, in another embodiment of the present disclosure, the user characteristic includes an offer-sensitive parameter, the coupon characteristic includes an offer-level parameter, and the first matching parameter determining module 404 includes:

and the second matching sub-parameter determining sub-module is used for calculating the ratio of the discount degree parameter of the discount coupon to the discount sensitive parameter of the target user aiming at each target user and each discount coupon of each target merchant to obtain a second matching sub-parameter.

And the second matching parameter determining sub-module is used for determining the matching parameters of the target user and the coupons according to the first matching sub-parameter and the second matching sub-parameter aiming at each target user and each coupon of each target merchant.

Optionally, in another embodiment of the present disclosure, the second matching parameter determining sub-module includes:

and the first matching numerical value calculating unit is used for calculating the product of the first matching sub-parameter and a preset first matching weight aiming at each target user and each coupon of each target merchant to obtain a first matching numerical value.

And the second matching numerical value calculating unit is used for calculating the product of the second matching sub-parameter and preset second matching weight aiming at each target user and each coupon of each target merchant to obtain a second matching numerical value.

And the third matching numerical value calculating unit is used for calculating the product of the discount degree parameter of the coupon and the preset third matching weight aiming at each target user and each coupon of each target merchant to obtain a third matching numerical value.

And the third matching parameter calculating unit is used for calculating the sum of the first matching value, the second matching value and the third matching value aiming at each target user and each coupon of each target merchant to obtain the matching parameters of the target user and the coupon.

And an assignment forbidding module 405, configured to forbid, for each target user, assignment of the coupon whose matching parameter is smaller than a preset matching threshold to the target user.

And the use parameter determining module 406 is configured to predict, for each target user and each coupon of each target merchant, a use parameter of the coupon by the target user according to the user characteristics of the target user and the interaction characteristics of the target user and the target merchant. Optionally, in an embodiment of the present disclosure, the above-mentioned usage parameter determining module 406 includes:

the merchant ticket characteristic obtaining sub-module 4061 is configured to obtain the merchant characteristic of the target merchant and the ticket characteristic of the coupon.

The usage probability determination submodule 4062 is configured to input the user characteristic of the target user, the interaction characteristic of the target user and the target merchant, the merchant characteristic of the target merchant, and the coupon characteristic of the coupon into a usage probability prediction model obtained through pre-training, so as to obtain a usage probability of the coupon by the target user.

And the discount degree increasing module 407 is configured to increase, according to a preset increase amount, a discount degree parameter of each coupon of each target merchant.

Optionally, in another embodiment of the present disclosure, the aforementioned benefit degree increasing module 407 includes:

and the increased parameter calculation submodule is used for calculating the sum of a preset increase and the discount degree parameter of the coupon to obtain an increased discount degree parameter.

And the second usage parameter determining submodule is used for inputting the user characteristics of the target user, the interaction characteristics of the target user and the target merchant, the merchant characteristics of the target merchant and the changed coupon characteristics into the usage probability prediction model to obtain a second usage probability of the coupon by the target user, wherein the changed coupon characteristics comprise increased coupon degree parameters.

And the usage probability increase determining submodule is used for calculating a difference value between the second usage probability and a first usage probability for each target user, wherein the first usage probability is the usage probability of the coupon before the target user increases the discount degree parameter.

And the profit determination submodule is used for calculating the product of the single average price of the target user and the difference value aiming at each target user to obtain a profit parameter.

And the cost determination submodule is used for calculating the product of the increment and the second use probability aiming at each target user to obtain a cost parameter.

And the profit index determining submodule is used for calculating the ratio of the profit parameter to the cost parameter for each target user to obtain a profit index.

And the discount degree increasing submodule is used for updating the discount degree parameter of the discount coupon into the increased discount degree parameter under the condition that the profit index is larger than a preset profit index threshold value aiming at each target user.

The first usage probability adjusting module 408 adjusts the usage probability of the coupon by each target user according to the increased preference degree parameter.

Optionally, in another embodiment of the present disclosure, the first usage probability adjusting module 408 includes:

and the first usage probability adjusting submodule is used for updating the usage probability of the target user on the coupon to be the second usage probability.

And a penalty factor determining module 409, configured to determine, for each target user, a penalty factor of the target user for the coupon according to the increase.

Optionally, in another embodiment of the present disclosure, the penalty factor determining module 408 includes:

and the penalty factor determination submodule is used for inputting the increment, the merchant characteristics of the target merchant and the coupon characteristics of the coupon into a penalty prediction model obtained by pre-training to obtain the penalty factor of the target user on the coupon, wherein the coupon characteristics are the coupon characteristics after the coupon degree parameters are increased.

And a second usage probability adjusting module 410, configured to calculate, for each target user, a product of an adjustment factor and the second usage probability to obtain a usage probability after penalty, where a sum of the adjustment factor and the penalty factor is 1.

And the coupon distribution module 411 is used for distributing each coupon to each target user according to the use parameters. Optionally, in another embodiment of the present disclosure, the coupon distribution module 411 includes:

and a maximum coupon number estimation submodule 4111, configured to estimate, for each target merchant, a maximum coupon number of the target merchant in a current coupon period.

Optionally, in another embodiment of the present disclosure, the maximum number of issued tickets estimating sub-module 4111 includes:

and the historical ticket information calculation unit is used for counting the total number of issued tickets and the number of used tickets of each target merchant in the last issuing period.

And the generation efficiency calculating unit is used for calculating the ratio of the number of the used coupons to the total number of the issued coupons for each target merchant to obtain the usage ratio.

And the coupon sending proportion calculating unit is used for calculating the ratio of the use proportion of the target merchants to the total use proportion of each target merchant to obtain an estimated coupon sending proportion, and the total use proportion is the sum of the use proportions of all the target merchants.

And the maximum coupon number calculating unit is used for calculating the product of the estimated coupon occupation ratio and the preset cellular coupon total number aiming at each target merchant to obtain the maximum coupon number of the target merchant in the current coupon period.

And a coupon distributing sub-module 4112, configured to distribute each coupon to each target user according to the maximum coupon sending number and the usage parameter.

Optionally, in another embodiment of the present disclosure, the coupon distributing sub-module 4112 includes:

the first coupon issuing element selecting unit is used for selecting the element with the largest use parameter from the use parameter matrix to obtain a coupon issuing element, and each element in the use parameter matrix comprises a target user, a target merchant, a coupon and the use parameter of the target user to the coupon.

The first coupon issuing unit is used for distributing the coupons contained in the coupon issuing element to the target users contained in the coupon issuing element when the number of issued coupons of the target merchants contained in the coupon issuing element is smaller than the maximum number of issued coupons of the target merchants, and the number of issued coupons is updated after each time of issuing.

and the use parameter threshold value determining unit is used for determining a use parameter threshold value according to the use parameter and the maximum coupon sending number aiming at each target merchant.

And the second coupon sending element selecting unit is used for selecting the element with the largest use parameter from the use parameter matrix to obtain a coupon sending element, and each element in the use parameter matrix comprises a target user, a target merchant and a coupon and the use parameter of the target user to the coupon.

And the first coupon issuing unit is used for distributing the coupons contained in the coupon issuing elements to the target users contained in the target elements when the use parameters are larger than or equal to the use parameter threshold of the target merchant.

Optionally, in another embodiment of the present disclosure, for the above usage parameter threshold, the usage parameter threshold may be adjusted according to the following modules:

and the actual coupon issuing number counting module is used for counting the actual coupon issuing number of each target merchant in the last adjusting period, wherein the last adjusting period is a sub-period in the current coupon issuing period.

And the actual coupon issuing ratio calculation module is used for calculating the ratio of the actual coupon issuing number to the actual cellular coupon issuing number for each target merchant to obtain the actual coupon issuing ratio, and the actual cellular coupon issuing number is the sum of the actual coupon issuing numbers of the target merchants in the last adjustment period.

And the threshold adjusting parameter calculating module is used for calculating the ratio of the actual coupon sending ratio to the estimated coupon sending ratio for each target merchant to obtain a threshold adjusting parameter.

And the use parameter threshold value adjusting module is used for calculating the product of the threshold value adjusting parameter and the use parameter threshold value aiming at each target merchant to obtain the adjusted use parameter threshold value.

In summary, an embodiment of the present disclosure provides a device for distributing coupons, the device including: the system comprises a coupon generating module, a coupon processing module and a coupon processing module, wherein the coupon generating module is used for acquiring coupon configuration information of each target merchant and generating at least one coupon according to the coupon configuration information; the characteristic acquisition module is used for acquiring the user characteristics of the target user and the interaction characteristics of the target user and the target merchant aiming at each target user and each target merchant; the usage parameter determining module is used for predicting usage parameters of the coupons of the target users according to the user characteristics of the target users and the interaction characteristics of the target users and the target merchants aiming at each target user and each coupon of each target merchant; and the coupon distribution module is used for distributing each coupon to each target user according to the use parameters. The coupon distribution method and the system can determine the use parameters of the coupon of the user according to the user characteristics and the interaction characteristics of the user and the merchant, and distribute the coupon according to the use parameters, so that the coupon distribution accuracy is improved.

The fourth embodiment of the apparatus corresponds to the second embodiment of the method, and the detailed description may refer to the second embodiment, which is not repeated herein.

An embodiment of the present disclosure also provides an electronic device, referring to fig. 6, including: a processor 501, a memory 502, and a computer program 5021 stored on the memory 502 and operable on the processor 501, the processor when executing the program implements the coupon distribution method of the foregoing embodiments.

Embodiments of the present disclosure also provide a readable storage medium, in which instructions, when executed by a processor of an electronic device, enable the electronic device to perform the coupon distribution method of the foregoing embodiments.

For the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and reference may be made to the partial description of the method embodiment for relevant points.

The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, embodiments of the present disclosure are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the embodiments of the present disclosure as described herein, and any descriptions of specific languages are provided above to disclose the best modes of the embodiments of the present disclosure.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the present disclosure may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the disclosure, various features of the embodiments of the disclosure are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed to reflect the intent: that is, claimed embodiments of the disclosure require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of an embodiment of this disclosure.

Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components in the embodiments may be combined into one module or unit or component, and furthermore, may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

The various component embodiments of the disclosure may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in a coupon dispensing device according to embodiments of the present disclosure. Embodiments of the present disclosure may also be implemented as an apparatus or device program for performing a portion or all of the methods described herein. Such programs implementing embodiments of the present disclosure may be stored on a computer readable medium or may be in the form of one or more signals. Such a signal may be downloaded from an internet website, or provided on a carrier signal, or provided in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit embodiments of the disclosure, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. Embodiments of the disclosure may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.

It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

The above description is only for the purpose of illustrating the preferred embodiments of the present disclosure and is not to be construed as limiting the embodiments of the present disclosure, and any modifications, equivalents, improvements and the like that are made within the spirit and principle of the embodiments of the present disclosure are intended to be included within the scope of the embodiments of the present disclosure.

The above description is only a specific implementation of the embodiments of the present disclosure, but the scope of the embodiments of the present disclosure is not limited thereto, and any person skilled in the art can easily conceive of changes or substitutions within the technical scope of the embodiments of the present disclosure, and all the changes or substitutions should be covered by the scope of the embodiments of the present disclosure. Therefore, the protection scope of the embodiments of the present disclosure shall be subject to the protection scope of the claims.

Claims

1. A method for distributing coupons, the method comprising:

aiming at each target user and each target merchant, acquiring user characteristics of the target user and interaction characteristics of the target user and the target merchant; the interactive features represent commodity purchasing intention and commodity purchasing behavior of the target user to the target merchant;

for each target user and each coupon of each target merchant, predicting the use parameters of the target user for the coupons according to the user characteristics of the target user and the interaction characteristics of the target user and the target merchant;

distributing each coupon to each target user according to the use parameters;

wherein, the user characteristics include a single average price of a historical order and offer sensitive parameters, the offer sensitive parameters are used for representing the preference degree of the user for using the coupon, the coupon characteristics include a threshold value and offer degree parameters, the offer degree parameters are used for representing the offer degree of the coupon, and after the step of obtaining the user characteristics of the target user and the interaction characteristics of the target user and the target merchant, the method further includes:

aiming at each target user and each coupon of each target merchant, calculating the ratio of the single average price of the target user to the threshold value of the coupon to obtain a first matching sub-parameter;

calculating the ratio of the discount degree parameter of the discount coupon to the discount sensitive parameter of the target user aiming at each target user and each discount coupon of each target merchant to obtain a second matching sub-parameter;

aiming at each target user and each coupon of each target merchant, determining a matching parameter of the target user and the coupon according to the first matching sub-parameter, the second matching sub-parameter and the discount degree parameter;

and for each target user, forbidding distributing the coupons with the matching parameters smaller than a preset matching threshold value to the target users.

2. The method of claim 1, wherein the usage parameter is a usage probability, and the step of predicting the usage parameter of the coupon by the target user according to the user characteristic of the target user and the interaction characteristic of the target user and the target merchant comprises:

acquiring merchant characteristics of the target merchant and coupon characteristics of the coupon;

inputting the user characteristics of the target user, the interaction characteristics of the target user and the target merchant, the merchant characteristics of the target merchant and the coupon characteristics of the coupon into a usage probability prediction model obtained through pre-training to obtain the usage probability of the coupon by the target user.

3. The method of claim 1, wherein the target merchant and target user are within a target cell area, and wherein the step of assigning each coupon to each target user based on the usage parameter comprises:

counting the total number of issued tickets and the number of used tickets of each target merchant in the last issuing period;

calculating the ratio of the number of used coupons to the total number of issued coupons for each target merchant to obtain a usage ratio;

calculating the ratio of the usage proportion of each target merchant to the total usage proportion of each target merchant to obtain an estimated coupon issuing proportion, wherein the total usage proportion is the sum of the usage proportions of the target merchants;

aiming at each target merchant, calculating the product of the estimated coupon distribution ratio and the preset cellular coupon distribution total number to obtain the maximum coupon distribution number of the target merchant in the current coupon distribution period;

and distributing each coupon to each target user according to the maximum coupon sending number and the use parameters.

4. The method of claim 3, wherein the step of assigning each coupon to each target user according to the maximum number of coupons and the usage parameter comprises:

selecting an element with the largest use parameter from a use parameter matrix to obtain a coupon sending element, wherein each element in the use parameter matrix comprises a target user, a target merchant, a coupon and a use parameter of the target user to the coupon;

and distributing the coupons contained in the coupon elements to the target users contained in the coupon elements when the number of the issued coupons of the target merchants contained in the coupon elements is less than the maximum number of the issued coupons of the target merchants, wherein the number of the issued coupons is updated after each issued coupon.

5. The method of claim 3, wherein the step of assigning each coupon to each target user according to the maximum number of coupons and the usage parameter comprises:

for each target merchant, determining a usage parameter threshold according to the usage parameter and the maximum coupon sending number;

selecting an element with the largest use parameter from a use parameter matrix to obtain a coupon sending element, wherein each element in the use parameter matrix comprises a target user, a target merchant and a coupon, and the use parameter of the target user to the coupon;

and distributing the coupons contained in the coupon elements to the target users contained in the coupon elements when the usage parameters are larger than or equal to the usage parameter threshold corresponding to the target merchants.

6. The method of claim 5, further comprising:

for each target merchant, counting the actual coupon sending number of the target merchant in the last adjustment period, wherein the last adjustment period is a sub-period in the current coupon sending period;

calculating the ratio of the actual ticket issuing number to the actual cellular ticket issuing number for each target merchant to obtain the actual ticket issuing ratio, wherein the actual cellular ticket issuing number is the sum of the actual ticket issuing numbers of the target merchants in the last adjustment period;

calculating the ratio of the actual coupon sending ratio to the estimated coupon sending ratio for each target merchant to obtain a threshold value adjusting parameter;

and calculating the product of the threshold value adjusting parameter and the use parameter threshold value aiming at each target merchant to obtain the adjusted use parameter threshold value.

7. The method of claim 1, further comprising:

for each coupon of each target merchant, increasing the coupon degree parameter according to a preset increase;

and for each target user, adjusting the use probability of the coupon by the target user according to the increased discount degree parameter.

8. The method of claim 7, wherein the step of increasing the coupon preference parameter according to a preset increase amount comprises:

calculating the sum of a preset increment and the discount degree parameter of the discount coupon to obtain an increased discount degree parameter;

for each target user, inputting the user characteristics of the target user, the interaction characteristics of the target user and the target merchant, the merchant characteristics of the target merchant and the changed coupon characteristics into the usage probability prediction model to obtain a second usage probability of the coupon by the target user, wherein the changed coupon characteristics comprise increased discount degree parameters;

calculating a difference value between the second use probability and a first use probability aiming at each target user, wherein the first use probability is the use probability of the coupon before the target user increases the discount degree parameter;

aiming at each target user, calculating the product of the single average price of the target user and the difference value to obtain a profit parameter;

calculating the product of the increment and the second use probability for each target user to obtain a cost parameter;

calculating the ratio of the profit parameter to the cost parameter for each target user to obtain a profit index;

and updating the discount degree parameter of the coupon to the increased discount degree parameter under the condition that the profit index is larger than a preset profit index threshold value for each target user.

9. The method of claim 8, wherein the step of adjusting the probability of using the coupon by the target user according to the increased preference level parameter comprises:

and updating the use probability of the target user to the coupon to be the second use probability.

10. The method of claim 9, further comprising:

for each target user, determining a penalty factor of the target user for the coupon according to the increment;

and calculating the product of an adjustment factor and the second use probability for each target user to obtain the use probability after penalty, wherein the sum of the adjustment factor and the penalty factor is 1.

11. The method of claim 10, wherein said step of determining a penalty factor for said coupon for said target user based on said increase comprises:

and inputting the increment, the merchant characteristics of the target merchant and the coupon characteristics of the coupon into a penalty prediction model obtained by pre-training to obtain a penalty factor of the target user on the coupon, wherein the coupon characteristics are the coupon characteristics after the coupon degree parameters are increased.

12. An apparatus for dispensing coupons, said apparatus comprising:

the characteristic acquisition module is used for acquiring the user characteristics of the target user and the interaction characteristics of the target user and the target merchant aiming at each target user and each target merchant; the interactive features represent commodity purchasing intention and commodity purchasing behavior of the target user to the target merchant;

the use parameter determining module is used for predicting the use parameters of the target user on the coupons according to the user characteristics of the target user and the interaction characteristics of the target user and the target merchants aiming at each target user and each coupon of each target merchant;

the coupon distribution module is used for distributing each coupon to each target user according to the use parameters;

wherein the user characteristics include a single average price of a historical order and offer sensitive parameters, the offer sensitive parameters are used for representing the preference degree of the user for using the coupon, the coupon characteristics include a threshold value and offer degree parameters, the offer degree parameters are used for representing the offer strength of the coupon, and the device further comprises:

the first matching sub-parameter module is used for calculating the ratio of the single average price of each target user to the threshold value of each coupon of each target merchant aiming at each target user to obtain a first matching sub-parameter;

the second matching sub-parameter module is used for calculating the ratio of the discount degree parameter of the discount coupon to the discount sensitive parameter of the target user aiming at each target user and each discount coupon of each target merchant to obtain a second matching sub-parameter;

the matching parameter module is used for determining the matching parameters of the target user and the coupons according to the first matching sub-parameter, the second matching sub-parameter and the discount degree parameter aiming at each target user and each coupon of each target merchant;

and the forbidding module is used for forbidding the coupons of which the matching parameters are smaller than a preset matching threshold value from being distributed to the target users.

13. An electronic device, comprising:

processor, memory and computer program stored on the memory and executable on the processor, characterized in that the processor, when executing the program, implements a method of distribution of coupons as set forth in one or more of claims 1-11.

14. A readable storage medium, wherein instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform a method of distribution of coupons as recited in one or more of method claims 1-11.