CN113888230A

CN113888230A - Electronic coupon issuing method and device, readable storage medium and electronic equipment

Info

Publication number: CN113888230A
Application number: CN202111224524.5A
Authority: CN
Inventors: 刘鑫
Original assignee: Beijing Jingdong Century Trading Co Ltd; Beijing Wodong Tianjun Information Technology Co Ltd
Current assignee: Beijing Jingdong Century Trading Co Ltd; Beijing Wodong Tianjun Information Technology Co Ltd
Priority date: 2021-10-19
Filing date: 2021-10-19
Publication date: 2022-01-04

Abstract

The disclosure relates to the technical field of computers, and provides an electronic coupon issuing method and device, a computer readable storage medium and electronic equipment. Wherein, the method comprises the following steps: inputting the attribute characteristics of the to-be-sent electronic coupon into the coupon offline score prediction model to obtain an offline virtual score; acquiring the real-time acquisition quantity and the real-time usage quantity of the sub-coupons to be issued from the latest updating moment to the current moment; determining a real-time virtual score according to a Bayesian smooth model based on the real-time fetching amount and the real-time using amount; determining a target virtual score according to the offline virtual score and the real-time virtual score; and sequencing the electronic coupons to be issued based on the target virtual scores, and issuing the electronic coupons to be issued according to a sequencing result. According to the scheme, the accuracy of the coupon distribution can be improved based on the offline virtual score and the real-time virtual score.

Description

Electronic coupon issuing method and device, readable storage medium and electronic equipment

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a method, an apparatus, a computer-readable storage medium, and an electronic device for issuing an electronic coupon.

Background

In an e-commerce system, the delivery of coupons to users is a common practice.

In the related art, the discount strength of the coupons is mainly sorted, so that the coupons with high discount strength are delivered preferentially.

However, the coupon with the larger discount strength is not necessarily the coupon desired by the user, so the delivery mode is less accurate.

It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the present disclosure, and thus may include information that does not constitute prior art known to those of ordinary skill in the art.

Disclosure of Invention

The present disclosure aims to provide a method and an apparatus for issuing an electronic coupon, a computer-readable storage medium, and an electronic device, so as to at least improve the problem of low accuracy of coupon delivery in the related art to a certain extent.

Additional features and advantages of the disclosure will be set forth in the detailed description which follows, or in part will be obvious from the description, or may be learned by practice of the disclosure.

According to a first aspect of the present disclosure, there is provided an electronic coupon issuing method, including:

inputting the attribute characteristics of the to-be-sent electronic coupons into an offline coupon score prediction model to obtain offline virtual scores of the to-be-sent electronic coupons;

acquiring the real-time getting amount and the real-time using amount of the to-be-sent electronic coupon from the latest updating moment to the current moment;

determining a real-time virtual score of the to-be-issued electronic coupon according to a Bayesian smooth model corresponding to the to-be-issued electronic coupon based on the real-time fetching amount and the real-time usage amount;

determining a target virtual score of the to-be-sent sub-coupon according to the offline virtual score and the real-time virtual score;

and sequencing the electronic coupons to be issued based on the target virtual scores, and issuing the electronic coupons to be issued according to sequencing results.

In an exemplary embodiment of the present disclosure, based on the foregoing scheme, the acquiring a real-time getting amount and a real-time usage amount of the to-be-sent electronic coupon from a latest update time to a current time includes:

acquiring the real-time acquisition quantity and the real-time usage quantity of the to-be-issued sub-coupon from the latest updating moment corresponding to the first issuing updating period to the current moment;

the issuing the electronic coupons to be issued according to the sorting result comprises the following steps:

in a second issuing updating period corresponding to the current moment, issuing the to-be-issued sub-coupons according to the sequencing result;

the current time is an update time corresponding to the second release update cycle, and the first release update cycle includes at least one second release update cycle.

In an exemplary embodiment of the present disclosure, based on the foregoing scheme, the coupon offline prediction model is predetermined by:

acquiring attribute characteristics of the electronic coupons of which the issuance is finished and the conversion rate of the electronic coupons of which the issuance is finished;

taking the attribute characteristics of the issued electronic coupons as input samples and the conversion rates of the issued electronic coupons as optimization target values, and training a gradient lifting iterative decision tree model to obtain an off-line score prediction model of the coupons;

wherein the conversion rate of the electronic coupons having finished issuing is determined according to the ratio between the historical usage amount and the historical pickup amount of the electronic coupons having finished issuing.

In an exemplary embodiment of the present disclosure, based on the foregoing scheme, the bayesian smoothing model corresponding to the to-be-issued electronic coupon is determined by the following formula:

wherein U is the real-time usage amount of the electronic coupon to be issued from the latest updating moment corresponding to the first issuing updating period to the current moment, G is the real-time getting amount of the electronic coupon to be issued from the latest updating moment corresponding to the first issuing updating period to the current moment,

And β is a smoothing parameter in the bayesian smoothing model;

the smoothing parameters in the Bayesian smoothing model corresponding to each electronic coupon to be issued are determined in the following way:

acquiring historical real-time data of the to-be-issued sub-coupons, wherein the historical real-time data comprises the receiving amount and the usage amount of the to-be-issued sub-coupons from the updating time of each first issuing period to the updating time corresponding to each second issuing updating period in the first issuing period in the latest preset time;

and taking the historical real-time data as prior data, and obtaining a smoothing parameter in a Bayesian smoothing model corresponding to the to-be-issued electronic coupon based on moment estimation and a maximum expectation algorithm.

In an exemplary embodiment of the present disclosure, based on the foregoing scheme, the method further includes:

when the historical real-time data does not exist in the to-be-sent electronic coupon, determining that the to-be-sent electronic coupon is a new coupon;

and determining the median or average value of the smoothing parameters corresponding to other to-be-issued electronic coupons with the historical real-time data as the smoothing parameters in the Bayesian smoothing model corresponding to the new coupon.

In an exemplary embodiment of the present disclosure, based on the foregoing scheme, the sorting the pending sub-coupons based on the target virtual score includes:

determining the getting amount and the using amount of each to-be-sent sub-coupon from the latest updating moment corresponding to the first sending updating period to the current moment;

when the receiving amount is larger than a first preset threshold value and the using amount is smaller than a second preset threshold value, determining that the to-be-sent coupon is a tail coupon, otherwise, determining that the to-be-sent coupon is a normal coupon;

respectively sorting the normal coupons and the tail coupons in a descending order based on the target virtual scores to determine sorting results of the to-be-sent sub-coupons;

in the sorting result, the sorting order of the normal coupon with the smallest target virtual score is positioned before the sorting order of the tail coupon with the largest target virtual score.

In an exemplary embodiment of the present disclosure, based on the foregoing scheme, the first preset threshold and the second preset threshold are determined by:

acquiring historical real-time data of each sub-coupon to be sent so as to generate a training sample set;

carrying out unsupervised learning training on a clustering model according to the training sample set so as to carry out secondary classification on the to-be-sent electronic coupons;

determining the first preset threshold and the second preset threshold according to the classification result;

the historical real-time data comprises the receiving amount and the using amount of the to-be-issued sub-coupons from the updating time of each first issuing period to the updating time corresponding to each second issuing updating period in the first issuing period in the latest preset time.

and in a target time period from the updating time of each first release updating period to the updating time of a first second release updating period in the first release updating period, performing descending sorting on the electronic coupons to be released based on the offline virtual scores, and releasing the electronic coupons to be released in the target time period according to the sorting result.

In an exemplary embodiment of the present disclosure, based on the foregoing scheme, the determining a target virtual score of the to-be-issued sub-coupon according to the offline virtual score and the real-time virtual score includes:

determining a first product between the offline virtual score and a first preset weight;

determining a second product between the real-time virtual score and a second preset weight;

and determining the target virtual score of the to-be-issued sub-coupon according to the sum of the first product and the second product.

In an exemplary embodiment of the present disclosure, based on the foregoing scheme, the issuing the to-be-issued sub-coupon according to the sorting result includes:

and selecting the first K sub-coupons to be issued from the sub-coupons to be issued according to the descending sorting result of the target virtual scores, wherein K is a positive integer.

In an exemplary embodiment of the present disclosure, based on the foregoing, the attribute characteristics include one or more of a category of the electronic coupon, a denomination, a limit, a discount strength, a calorific value of the covered stock quantity unit, a price of the covered stock quantity unit, a category of the covered item, a brand of the covered item, and a covered shop.

According to a second aspect of the present disclosure, there is provided an electronic coupon issuing apparatus including:

the offline virtual score determining module is configured to input the attribute characteristics of the to-be-sent electronic coupons into a coupon offline score prediction model so as to obtain offline virtual scores of the to-be-sent electronic coupons;

the real-time data acquisition module is configured to acquire the real-time getting amount and the real-time using amount of the to-be-sent electronic coupon from the latest updating moment to the current moment;

the real-time virtual score determining module is configured to determine a real-time virtual score of the to-be-issued sub-coupon according to a Bayesian smooth model corresponding to the to-be-issued sub-coupon based on the real-time getting amount and the real-time usage amount;

a target virtual score determining module configured to determine a target virtual score of the to-be-issued sub-coupon according to the offline virtual score and the real-time virtual score;

and the coupon issuing module is configured to sort the electronic coupons to be issued based on the target virtual scores and issue the electronic coupons to be issued according to a sorting result.

According to a third aspect of the present disclosure, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of issuing an electronic coupon as described in the first aspect of the above embodiments.

According to a fourth aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including: a processor; and a storage device for storing one or more programs, which when executed by the one or more processors, cause the one or more processors to implement the method of issuing electronic coupons as described in the first aspect of the embodiments above.

As can be seen from the foregoing technical solutions, the method and apparatus for issuing an electronic coupon, and the computer-readable storage medium and the electronic device for implementing the method for issuing an electronic coupon in the exemplary embodiment of the disclosure have at least the following advantages and positive effects:

in the technical solution provided by some embodiments of the present disclosure, first, the attribute characteristics of the to-be-sent electronic coupon are input into a coupon offline score prediction model to obtain an offline virtual score of the to-be-sent electronic coupon, then, acquiring the real-time getting amount and the real-time using amount of the to-be-sent electronic coupon from the latest updating moment to the current moment, and based on the real-time getting amount and the real-time using amount, determining the real-time virtual score of the to-be-issued electronic coupon according to the Bayesian smooth model corresponding to the to-be-issued electronic coupon, determining a target virtual score of the to-be-issued sub-coupon according to the offline virtual score and the real-time virtual score, and finally, and sequencing the electronic coupons to be issued based on the target virtual scores, and issuing the electronic coupons to be issued according to sequencing results. Compared with the related art, the coupon issuing method and the coupon issuing system have the advantages that the coupon issuing accuracy can be improved based on the attribute characteristics of the coupons and the real-time use data of the coupons.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure. It is to be understood that the drawings in the following description are merely exemplary of the disclosure, and that other drawings may be derived from those drawings by one of ordinary skill in the art without the exercise of inventive faculty.

FIG. 1 is a flow chart diagram illustrating an electronic coupon issuing method in an exemplary embodiment of the present disclosure;

FIG. 2 is a flowchart illustrating a method for training a coupon offline score prediction model according to an exemplary embodiment of the present disclosure;

FIG. 3 illustrates a block diagram of a coupon offline prediction model training in an exemplary embodiment of the present disclosure;

FIG. 4 is a flowchart illustrating a method for determining a smoothing parameter in a Bayesian smoothing model corresponding to each to-be-issued coupon in an exemplary embodiment of the present disclosure;

FIG. 5 is a flow chart diagram illustrating a method for determining a target virtual score in an exemplary embodiment of the present disclosure;

FIG. 6 is a flowchart illustrating a method of sorting electronic coupons to be issued in an exemplary embodiment of the present disclosure;

FIG. 7 illustrates a flowchart of a method of determining a first preset threshold and a second preset threshold in an exemplary embodiment of the present disclosure;

FIG. 8 illustrates a flow chart diagram of another method of ordering coupons in an exemplary embodiment of the present disclosure;

fig. 9 is a schematic structural diagram illustrating an apparatus for issuing an electronic coupon according to an exemplary embodiment of the present disclosure;

FIG. 10 shows a schematic diagram of a computer storage medium in an exemplary embodiment of the disclosure;

fig. 11 shows a schematic structural diagram of an electronic device in an exemplary embodiment of the present disclosure.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and the like. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.

The terms "a," "an," "the," and "said" are used in this specification to denote the presence of one or more elements/components/parts/etc.; the terms "comprising" and "having" are intended to be inclusive and mean that there may be additional elements/components/etc. other than the listed elements/components/etc.; the terms "first" and "second", etc. are used merely as labels, and are not limiting on the number of their objects.

Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities.

In an electronic commerce system, the coupon delivery to the user is a common operation mode, and when the coupon is delivered, the coupon delivery is generally divided into two stages, namely recall and sorting. In the recalling stage, all the coupons in the coupon pool are preliminarily screened according to the preference of the user, and the range of releasing the coupons to the user is narrowed; in the sorting stage, the retrieved coupons are sorted, so that the coupons are issued according to the sorting result, that is, the optimal coupons are recommended for the user.

In the related technology, the sorting stage is to prioritize the coupons retrieved after recall, and the most common way is to sort according to the discount strength of the coupons, and finally select the coupon with the highest discount strength to issue.

However, since the coupon with great discount strength is not necessarily the coupon required by the user, the coupon distribution method is low in accuracy.

In the embodiments of the present disclosure, firstly, a method for issuing an electronic coupon is provided, which at least partially overcomes the above-mentioned drawbacks in the related art.

Fig. 1 is a flowchart illustrating a method for issuing an electronic coupon according to an exemplary embodiment of the present disclosure, and referring to fig. 1, the method includes:

step S110, inputting the attribute characteristics of the to-be-sent electronic coupons into a coupon offline score prediction model to obtain offline virtual scores of the to-be-sent electronic coupons;

step S120, acquiring the real-time acquisition quantity and the real-time usage quantity of the to-be-issued electronic coupon from the latest updating moment to the current moment;

step S130, based on the real-time fetching amount and the real-time usage amount, determining a real-time virtual score of the to-be-issued electronic coupon according to a Bayesian smooth model corresponding to the to-be-issued electronic coupon;

step S140, determining a target virtual score of the to-be-issued electronic coupon according to the offline virtual score and the real-time virtual score;

and S150, sequencing the electronic coupons to be issued based on the target virtual scores, and issuing the electronic coupons to be issued according to a sequencing result.

In the technical solution provided by the embodiment shown in fig. 1, first, the attribute characteristics of the to-be-issued sub-coupon are input into a coupon offline score prediction model to obtain an offline virtual score of the to-be-issued sub-coupon, then, acquiring the real-time getting amount and the real-time using amount of the to-be-sent electronic coupon from the latest updating moment to the current moment, and based on the real-time getting amount and the real-time using amount, determining the real-time virtual score of the to-be-issued electronic coupon according to the Bayesian smooth model corresponding to the to-be-issued electronic coupon, determining a target virtual score of the to-be-issued sub-coupon according to the offline virtual score and the real-time virtual score, and finally, and sequencing the electronic coupons to be issued based on the target virtual scores, and issuing the electronic coupons to be issued according to sequencing results. Compared with the related art, the coupon issuing method and the coupon issuing system have the advantages that the coupon issuing accuracy can be improved based on the attribute characteristics of the coupons and the real-time use data of the coupons.

The following detailed description of the various steps in the example shown in fig. 1:

in step S110, the attribute characteristics of the to-be-issued sub-coupon are input into a coupon offline score prediction model to obtain an offline virtual score of the to-be-issued sub-coupon.

In an exemplary embodiment, the attribute characteristics of the pending electronic coupons include one or more of a category of the electronic coupons, a denomination, a limit, a discount strength, a heating value of the covered stock quantity units, a price of the covered stock quantity units, a category of the covered goods, a brand of the covered goods, and a covered store.

The category of the electronic coupon can be understood as the category of the electronic coupon, such as a full discount coupon category, a cash coupon category and the like, and the limit of the electronic coupon can be understood as the lowest consumption amount of the coupon, such as the limit of 99 yuan, which means that when the consumption amount is 99 yuan or more, the electronic coupon can be used for making a part of payment amount, otherwise, the electronic coupon cannot be used.

For example, the attribute characteristics of the historical coupons which have finished issuing can be trained in advance to obtain the coupon offline score prediction model. Fig. 2 is a flowchart illustrating a method for training a coupon offline prediction model in an exemplary embodiment of the disclosure. Referring to fig. 2, the method may include steps S210 to S220. Wherein:

in step S210, attribute characteristics of the electronic coupon whose issuance has been ended and a conversion rate of the electronic coupon whose issuance has been ended are acquired.

For example, each electronic coupon may correspond to a start issue date and an end issue date. The start date of issuance represents a date corresponding to the first day on which the electronic coupon can be issued, and the end date of issuance represents a date corresponding to the last day on which the electronic coupon can be issued, that is, the electronic coupon will not be issued any more since the date corresponding to the last day.

In an alternative embodiment, the electronic coupons whose issuance is finished include all electronic coupons whose issuance finishing date is less than the coupon offline score prediction model training date.

For example, the attribute features of the electronic coupons which are issued before the current day are used for training daily to obtain the coupon offline score prediction model, so that the coupon offline score prediction model is updated in the unit of the "day". And then, using the coupon offline score prediction model updated on the current day for offline virtual score prediction of the pending electronic coupons on the next day.

Of course, the coupon offline prediction model may be updated in other time units, such as "week", in "month", or in any other fixed period, or may be updated at any time in an irregular period, which is not limited in this exemplary embodiment.

In another alternative embodiment, the electronic coupons that have finished being issued may include electronic coupons that have finished being issued within a historical preset time interval that is closest to the update date of the coupon offline prediction model, such as electronic coupons that have finished being issued within 60 days before the update date.

The attribute characteristics of the electronic coupon that has finished issuing are the same as those of the electronic coupon to be issued, and are not described herein again.

In an exemplary embodiment, the conversion rate of the electronic coupon of which the issuance is ended is determined according to a ratio between the historical usage amount and the historical pickup amount of the electronic coupon of which the issuance is ended, that is, the ratio between the historical total usage amount and the historical total pickup amount of the electronic coupon of which the issuance is ended is the corresponding conversion rate. For example, a coupon is issued from 7/1/2021 and ended at 7/15/2021, and the conversion rate of the coupon is the ratio between the usage amount and the pickup amount within 15 days from 7/1/2021 to 7/15/2021.

Next, in step S220, taking the attribute features of the issued electronic coupons as input samples, and taking the conversion rates of the issued electronic coupons as optimization target values, and training a gradient boosting iterative decision tree model to obtain the coupon offline score prediction model.

The gradient Boosting iterative Decision tree model can be understood as a gbdt (gradient Boosting Decision tree) model. The attribute characteristics of each issued electronic coupon can be used as input, the conversion rate of each issued electronic coupon is used as an optimization target value of the model, and the established GDBT regression model is trained to obtain the coupon offline prediction model.

Before the established GDBT model is trained by using the attribute characteristics and the conversion rate of the electronic coupons which are released, the attribute characteristics of the electronic coupons which are released can be preprocessed, and the preprocessed attribute characteristics are used for training.

For example, a table storing electronic coupons may be associated with a table storing the popularity of the inventory cells of the items covered by the electronic coupons and the prices of the items covered by the electronic coupons, thereby generating a cross-feature of the inventory cells of the covered items of the electronic coupons. Dimension reduction processing can be further performed on the categories of the commodities covered by the electronic coupons, the brands of the covered commodities and the covered shop features in an embedding mode, so that the features have correlation in a space after dimension reduction, and the prediction accuracy of the model is improved. The method for performing the dimension reduction processing on the features by using the embedding method may refer to the prior art, and is not described herein again.

After the features are preprocessed, the preprocessed attribute features, such as the category, the denomination, the limit, the discount strength, the cross feature of the stock quantity unit of the covered goods, the category of the goods covered by the electronic coupon, the brand of the covered goods, the covered store feature, the attribute features after dimension reduction processing and the conversion rate corresponding to the electronic coupon, can be used as sample data to train and obtain the coupon offline score prediction model.

For example, fig. 3 shows a frame diagram of the coupon offline prediction model training in an exemplary embodiment of the disclosure. Referring to fig. 3, the framework mainly includes three parts, which are model input features 31, model optimization objectives 32, and model outputs 33.

The model input features 31 include two major categories of coupon metadata and coupon limit sku (Stock locating Unit, i.e., the Stock Unit mentioned above) data. Specifically, the coupon metadata may include the denomination, limit, type, class, and covering shop of the coupon, and the coupon limit sku data may include cross features obtained by associating the available sku, the dynamic marketing sku, the hash sku, the heat value, the discount strength, and the table to which the price of the covered product belongs.

The model optimization objective 32 is the conversion rate corresponding to each coupon in the training sample, and the model output 32 is the offline virtual score of the coupon. And carrying out supervised learning training on the GBDT model by using the model input features 31 as input samples and the model optimization targets 32 as input sample labels to obtain a coupon offline prediction model.

Through the steps S210 to S220, the coupon offline score prediction model can be obtained through the training of the attribute characteristics of the coupon. Since the attribute features of the coupon may include multifaceted features of the coupon, not just discount strength features, it may improve the accuracy of the coupon offline virtual score prediction.

After the coupon offline score prediction model is obtained through training, the offline virtual score of the to-be-sent electronic coupon can be obtained based on the coupon offline score prediction model. Namely, after the attribute characteristics of each to-be-sent electronic coupon are input into the coupon offline score prediction model, the output value of the model is the offline virtual score of the to-be-sent electronic coupon.

With continued reference to fig. 1, in step S120, the real-time getting amount and the real-time usage amount of the to-be-issued sub-coupon from the last update time to the current time are obtained.

In an exemplary embodiment, the target virtual score of the electronic coupons to be issued may be periodically updated to select the electronic coupons currently required to be issued from all the electronic coupons to be issued.

In the present disclosure, two release update periods may be included, a first release update period and a second release update period, respectively. Wherein, the first release updating period comprises at least one second release updating period. In other words, the time interval between each update time of the second release update period is less than or equal to the time interval between each update time of the first release update period. And updating the target virtual score of the electronic coupon to be issued at the updating time corresponding to the two issuing updating periods.

For example, the first release update period interval is 8 hours, that is, 0 point, 8 point, and 16 point of each day are update times corresponding to the first release update period, and the second release update period interval is 1 hour, that is, each whole point time in each first release update period is an update time corresponding to the second release update period, for example, 1 point, 2 points, 3 points, 4 points, 5 points, 6 points, and 7 points are update times corresponding to the second release update period included in 0 point to 8 points of the first release update period.

For example, the specific implementation of step S120 may include: and acquiring the real-time acquisition amount and the real-time usage amount of the to-be-issued sub-coupon from the latest updating moment corresponding to the first issuing updating period to the current moment. And the current moment comprises an updating moment corresponding to a second release updating period in the current first release updating period.

Taking the last update time corresponding to the first release update cycle as 8 o 'clock at 7/11/2021 as an example, the current time may be 9 o' clock, 10 o 'clock, 11 o' clock, 12 o 'clock, 13 o' clock, 14 o 'clock, and 15 o' clock at 7/11/2021 respectively. Continuing with the example that the current time is respectively 9 o 'clock and 10 o' clock, when the current time is 9 o 'clock at 7/11/2021, the getting amount and the usage amount of each to-be-issued sub-coupon between 8 o' clock and 9 o 'clock can be obtained in step S120, so as to determine which electronic coupons can be issued between 9 o' clock and 10 o 'clock, and when the current time is 10 o' clock at 7/11/2021, the getting amount and the usage amount of each to-be-issued sub-coupon between 8 o 'clock and 10 o' clock can be obtained in step S120, so as to determine which electronic coupons can be issued between 10 o 'clock and 11 o' clock.

It should be noted that the update period may also include only one update period, that is, the first release update period and the second release update period may be the same, and this exemplary embodiment is not particularly limited to this.

Continuing to refer to fig. 1, next, in step S130, based on the real-time getting amount and the real-time usage amount, a real-time virtual score of the to-be-issued sub-coupon is determined according to a bayesian smoothing model corresponding to the to-be-issued sub-coupon.

In an exemplary embodiment, the bayesian smoothing model corresponding to each pending electronic coupon may be determined by the following formula:

And beta is a smoothing parameter in a Bayesian smoothing model corresponding to the to-be-issued electronic coupon.

Fig. 4 is a flowchart illustrating a method for determining a smoothing parameter in a bayesian smoothing model corresponding to each to-be-issued coupon in an exemplary embodiment of the present disclosure. Referring to fig. 4, the method may include steps S410 to S420. Wherein:

in step S410, historical real-time data of the to-be-issued sub-coupon is obtained.

In an exemplary embodiment, the historical real-time data of the to-be-issued sub-coupon includes a receiving amount and a usage amount of the to-be-issued sub-coupon from an update time of each first issue cycle to an update time corresponding to each second issue update cycle in the first issue cycle within a latest preset time.

The latest preset time can be set by self according to requirements, such as obtaining historical real-time data of the electronic coupon to be issued within 7 days in the past.

Taking the above-mentioned updating time corresponding to the first release updating period as 0 point, 8 points and 16 points of each day, the second release updating period is 1 hour apart in each first release updating period as an example, the method can obtain the amount of the withdrawal and the amount of the use in each time period corresponding to 0 point to 1 point, 0 point to 2 points, 0 point to 3 points, 0 point to 4 points, 0 point to 5 points, 0 point to 6 points, 0 point to 7 points, 8 point to 9 points, 8 point to 10 points, 8 point to 11 points, 8 point to 12 points, 8 point to 13 points, 8 point to 14 points, 8 point to 15 points, 16 point to 17 points, 16 point to 18 points, 16 point to 19 points, 16 point to 20 points, 16 point to 21 points, 16 point to 22 points and 16 point to 23 points of the to-be-issued sub-coupon every day in the last 7 days, and take the amounts as the historical real-time data of the to-be-issued sub-coupon to form a historical real-time data set.

When the first issuing updating period is the same as the second issuing updating period, the historical real-time data can be understood as the receiving amount and the using amount of the to-be-issued electronic coupons between every two adjacent updating moments within the latest preset time.

After the historical real-time data of the to-be-issued sub-coupon is obtained, in step S420, the historical real-time data is used as prior data, and based on moment estimation and a maximum expectation algorithm, a smoothing parameter in a bayesian smoothing model corresponding to the to-be-issued sub-coupon is obtained.

For example, historical real-time data in the historical real-time data set can be used as prior data, and based on the thought of moment estimation, smoothing parameters in a Bayesian smoothing model corresponding to the to-be-issued electronic coupons can be obtained

And beta, taking the initial value as the initial value in the maximum expectation algorithm, and obtaining the smoothing parameter in the Bayes smoothing model based on the thought of the maximum expectation algorithm by using historical real-time data

And beta.

For example, the amount of the obtained data and the amount of the used data from the update time of each first release cycle to the update time corresponding to each second release update cycle in the first release cycle in the last 7 days are used as a priori data. And if the corresponding acquisition quantity of each prior data is marked as G and the corresponding usage quantity is marked as U, the conversion rate corresponding to the prior data is R-U/G. The mean value of R is recorded as mean, the variance of R is recorded as var, and the initialized value is obtained according to the moment estimation

And β are respectively:

to be initialized

And β as initial values, brought into the EM (Expectation-maximization) algorithm to be updated according to the following equations (2) and (3), respectively

And beta until convergence, the final value can be obtained

And beta, the

And beta is the smoothing parameter in the Bayesian smoothing model corresponding to the to-be-issued electronic coupon. Wherein, the updating formula of the EM algorithm is as follows:

in the formulae (2) and (3),

indicating after the last update

Value, beta^oldRepresenting the beta value after the last update. G_iRepresenting the amount of extraction, U, in the ith prior data_iIndicates the amount of usage in the ith prior data, and ψ (g) indicates the Digamma function.

In an exemplary embodiment, when the historical real-time data does not exist in the to-be-issued sub-coupon, determining that the to-be-issued sub-coupon is a new coupon; and determining the median or average value of the smoothing parameters corresponding to other to-be-issued electronic coupons with the historical real-time data as the smoothing parameters in the Bayesian smoothing model corresponding to the new coupon.

For example, for some coupons to be issued, the coupons may be new coupons issued on the same day, so there is no historical real-time data in the past 7 days, and the median or average of the smoothing parameters corresponding to other coupons to be issued, which have historical real-time data in the past 7 days, may be used as the smoothing parameter in the bayesian smoothing model corresponding to the new coupons. Of course, other statistical parameters of the smoothing parameters corresponding to other to-be-issued electronic coupons may also be used as the smoothing parameters corresponding to the new coupon, which is not particularly limited in this exemplary embodiment.

In the coupon operation of e-commerce, this index of conversion rate is effective under a large data volume. Ideally, when the coupon is received in 10000 sheets and used in 100 sheets, the conversion rate of the coupon is 1%, which is effective. However, in the real-time stream, there are cases where the coupon is small in both the amount of coupon received and the amount of coupon used, for example, the coupon is received in 5 coupons and the amount of coupon used is 2 coupons, so that the calculated coupon conversion rate is 40%, but at this time, this data is mathematically invalid and does not conform to the law of large numbers, because in the law of large numbers, the frequency of random events is similar to its probability after repeated tests under the condition that the tests are not changed. However, the latter had only 5 sheets of tape, and did not satisfy the condition of "repeating the test a plurality of times".

In the present disclosure, data that does not conform to the law of large numbers can be reasonably processed by a bayesian smoothing model. In other words, for a certain coupon, even if the real-time acquisition amount and the use amount of the coupon do not conform to the law of large numbers, the acquisition amount and the use amount of the coupon are processed through the Bayesian smooth model, so that a reasonable real-time score can be obtained.

For example, through the steps S410 to S420, a bayesian smooth model corresponding to each to-be-issued sub-coupon can be determined. For each to-be-issued electronic coupon, the real-time usage amount and the real-time acquisition amount of the to-be-issued electronic coupon can be brought into the corresponding Bayesian smooth model, so that the real-time virtual score of the to-be-issued electronic coupon is obtained.

Next, in step S140, a target virtual score of the to-be-issued sub-coupon is determined according to the offline virtual score and the real-time virtual score.

For example, fig. 5 is a flowchart illustrating a method for determining a target virtual score according to an exemplary embodiment of the present disclosure. Referring to fig. 5, the method may include steps S510 to S530. Wherein, in step S510, a first product between the offline virtual score and a first preset weight is determined; in step S520, determining a second product between the real-time virtual score and a second preset weight; in step S530, a target virtual score of the pending issue sub-coupon is determined according to a sum of the first product and the second product.

For example, a first preset weight a corresponding to the offline virtual score and a second preset weight B corresponding to the real-time virtual score may be preset. And then fusing the offline virtual score and the real-time virtual score corresponding to each coupon to be issued through the following formula (4) to obtain the target virtual score.

allscoer＝A*offlinescore+B*realscore (4)

In the formula (4), offflinscore represents an offline virtual score, realcore represents a real-time virtual score, and allscore represents a target virtual score. The value of the first preset weight a and the value of the second preset weight B may be customized according to requirements, which is not particularly limited in this exemplary embodiment.

In step S150, the to-be-issued electronic coupons are sorted based on the target virtual score, and the to-be-issued electronic coupons are issued according to the sorting result.

In the present disclosure, based on the historical real-time data of the electronic coupons, a clustering model in the unsupervised learning algorithm may be constructed, so that the tail coupons in the electronic coupons to be issued may be determined based on the clustering model, so as to perform the right reduction processing on the tail coupons, and be used for sorting the electronic coupons to be issued in step S150.

Next, a specific embodiment of step S510 described above will be described with reference to fig. 6 and 7.

For example, fig. 6 is a flowchart illustrating a method for sorting electronic coupons to be issued according to an exemplary embodiment of the present disclosure, and referring to fig. 6, the method may include steps S610 to S630. Wherein:

in step S610, the amount of the electronic coupons to be issued is determined from the latest update time corresponding to the first issue update period to the current time.

For example, in step S610, for each to-be-issued sub-coupon, the amount of access and the amount of usage from the latest update time corresponding to the first issue update period to the current time are the same as those in step S120, and will not be described again here.

In step S620, when the pickup amount is greater than a first preset threshold and the usage amount is less than a second preset threshold, it is determined that the to-be-issued coupon is a tail coupon, otherwise, it is determined that the to-be-issued coupon is a normal coupon.

In an exemplary embodiment, the coupon can be understood as a pending electronic coupon that requires a subsequent sorting stage for a weight reduction process. The normal coupon can be understood as an electronic coupon which can be directly sorted according to the target virtual score in the subsequent sorting stage.

Next, a method for determining the first preset threshold and the second preset threshold in step S620 will be described with reference to fig. 7. Referring to fig. 7, the method of determining the first preset threshold value and the second preset threshold value may include steps S710 to S730. Wherein:

in step S710, historical real-time data of each pending issue electronic coupon is obtained to generate a training sample set.

In other words, the historical real-time data of each pending issue sub-coupon in step S710 is the same as the historical real-time data in step S410 described above, except that step S410 is for each pending issue sub-coupon individually, and the historical real-time data of all pending issue sub-coupons is acquired in step S710.

For example, the historical real-time data of each to-be-sent electronic coupon acquired in step S410 may be collected to generate a set, and the set is used as a training sample set.

In step S720, unsupervised learning training is performed on a clustering model according to the training sample set, so as to perform secondary classification on the to-be-sent electronic coupons.

In an exemplary embodiment, the Clustering model may include a k-means Clustering algorithm, a DBSCAN (Density-Based Spatial Clustering of Application with Noise) algorithm, and the like.

Taking the clustering model as a K-means clustering algorithm as an example, since the sub-coupons to be issued need to be divided into two types, namely normal coupons and tail coupons, the K value in the K-means algorithm is 2, and then unsupervised learning training is performed by using a training sample set based on the K-means clustering method in the prior art, and the K-means clustering process can refer to the prior art and is not described herein again.

In step S730, the first preset threshold and the second preset threshold are determined according to the classification result.

For example, after the electronic coupons to be issued are classified into two categories by the k-means clustering method, a boundary exists between the two categories of electronic coupons, the boundary corresponds to a value of the receiving amount and a value of the usage amount, the value of the receiving amount corresponding to the boundary is used as a first preset threshold, and the value of the usage amount corresponding to the boundary is used as a second preset threshold.

Through the steps S710 to S730, the first preset threshold and the second preset threshold may be determined according to the historical real-time data of the to-be-issued sub-coupons. Further, in step S620, a category label of each pending issue sub-coupon may be determined based on the first preset threshold and the second preset threshold, that is, whether the pending issue sub-coupon belongs to a tail coupon or a normal coupon.

Continuing to refer to fig. 6, in step S630, sorting the normal coupons and the tail coupons in descending order based on the target virtual score, respectively, to determine a sorting result of the to-be-sent sub-coupons;

For example, after the tail coupons and the normal coupons are determined, all the tail coupons can be sorted in a descending order based on the target virtual scores in all the tail coupons, all the normal coupons can be sorted in a descending order based on the target virtual scores in all the normal coupons, and then all the normal coupons are arranged in front of all the tail coupons, so that the right reducing processing of the tail coupons is realized.

Through the steps S610 to S630, the coupons can be ranked and optimized according to the real-time data of the coupons, and the accuracy of issuing or recommending the coupons is further improved.

After the sequencing result of the to-be-issued electronic coupon is determined, the to-be-issued electronic coupon can be issued according to the sequencing result.

Illustratively, issuing the to-be-issued sub-coupons according to the sorting result includes: and selecting the first K sub-coupons to be issued from the sub-coupons to be issued according to the descending sorting result of the target virtual scores, wherein K is a positive integer.

For example, the first K to-be-issued sub-coupons can be selected from the to-be-issued sub-coupons to be issued according to the sorting result after the tail coupons are subjected to the weight reduction processing. The value K may be customized according to user requirements, which is not particularly limited in this exemplary embodiment.

Illustratively, fig. 8 shows a flowchart of another method for sorting coupons in an exemplary embodiment of the present disclosure. Referring to fig. 8, the method may include steps S810 to S870.

In step S810, determining the offline score of the coupon;

in step S820, determining a coupon real-time score;

in step S830, fusing the coupon offline score and the coupon real-time score to determine a coupon fused score;

in step S840, obtaining coupon real-time data;

in step S850, judging whether the coupon is a tail coupon according to the real-time coupon data, if so, turning to step S860, otherwise, turning to step S870;

in step S860, decreasing the right and sorting the coupons;

in step S870, the coupons are sorted normally.

In an exemplary embodiment, the offline score in fig. 8 may be understood as the above offline virtual score, and the real-time score may be understood as the above real-time virtual score, and the real-time coupon data may include the real-time getting amount and the real-time usage amount of the to-be-sent electronic coupon from the latest update time to the current time in step S220, which is not described herein again. The fusion score may be understood as the above-described target virtual score.

In an exemplary embodiment, the issuing the to-be-issued electronic coupon according to the sorting result in step S150 includes: in a second issuing updating period corresponding to the current moment, issuing the to-be-issued sub-coupons according to the sequencing result; and the current moment is the updating moment corresponding to the second issuing updating period.

For example, if the current time is 1 point, the electronic coupon to be issued may be issued within 1 point to 2 points according to the sorting result, and if the current time is 2 points, the electronic coupon to be issued may be issued within 2 points to 3 points according to the sorting result. That is, the to-be-issued electronic coupon may be issued between two adjacent update times corresponding to the second issuing update period according to the sorting result of the target virtual score.

In another exemplary implementation manner, in a target time period from an update time of each first release update cycle to an update time of a first second release update cycle in the first release update cycle, the to-be-released e-coupons are sorted in a descending order based on the offline virtual score, so that the to-be-released e-coupons are released in the target time period according to the sorting result.

Taking the above-mentioned every 8 hours as a first release update period, and taking each integral point time in every 8 hours as the update time corresponding to the second release update period in the first release period as an example, that is, 0 point, 8 points, and 16 points of each day are the update times corresponding to the first release update period. In three hours of 0 to 1, 8 to 9 and 16 to 17 each day, each electronic coupon to be issued is only sorted by the offline virtual score, so that the coupon can be cold-started for a certain time, and meanwhile, the situation that a user who receives the coupon in the first hour is just using less coupon, so that the coupon is always given less right in the subsequent sorting and cannot be continuously released is avoided, and the accuracy of issuing the coupon is further improved.

For example, a coupon may transform poorly, which may be discounted between 1 and 8. However, since the first release update cycle is updated at 8 o 'clock, that is, at 8 o' clock, all the coupons are released again for one hour by using the offline virtual score, the coupons with reduced rights may be released again, and the coupon conversion condition is better in the one hour from 8 o 'clock to 9 o' clock and in the period from 9 o 'clock to 16 o' clock in the future, the coupon will not be reduced in rights, thereby avoiding the situation that the coupon is not recommended to be released all the time due to the bad conversion condition in the first hour and the coupon is always released because of the right reduction on the same day, and improving the rationality of the coupon release.

In another exemplary embodiment, for a coupon to be issued newly submitted on the same day, the acquisition amount and the usage amount of the coupon are both 0, and the coupon has no real-time data, so that an initial value of a target virtual score can be set, and the initial value can be an offline score calculated by a coupon offline score prediction model. In other words, new coupons without real-time data can be sorted by using the offline scores of the new coupons without any right-reducing processing, when the real-time data exist, the new coupons can be sorted according to the target virtual scores obtained by fusing the offline virtual scores and the real-time virtual scores, whether the new coupons are tail coupons can be determined according to the real-time data, whether the new coupons need to be sorted after the right-reducing processing is carried out is determined, and then the new coupons are issued according to the sorting results.

According to the method and the device, through the first issuing period and the second issuing updating period, the real-time data of the coupons can be fully considered, and the coupons are ordered and recommended in different modes at the updating moments corresponding to different issuing periods according to actual conditions, so that the accuracy and the reasonability of issuing the coupons are improved.

Those skilled in the art will appreciate that all or part of the steps implementing the above embodiments are implemented as computer programs executed by a CPU. The computer program, when executed by the CPU, performs the functions defined by the method provided by the present invention. The program may be stored in a computer readable storage medium, which may be a read-only memory, a magnetic or optical disk, or the like.

Furthermore, it should be noted that the above-mentioned figures are only schematic illustrations of the processes involved in the method according to exemplary embodiments of the invention, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.

Fig. 9 is a schematic structural diagram illustrating an apparatus for issuing an electronic coupon according to an exemplary embodiment of the present disclosure. Referring to fig. 9, the apparatus may include an offline virtual score determining module 910, a real-time data obtaining module 920, a real-time virtual score determining module 930, a target virtual score determining module 940, and a coupon dispensing module 950. Wherein:

an offline virtual score determining module 910, configured to input the attribute characteristics of the to-be-sent electronic coupon into a coupon offline score prediction model, so as to obtain an offline virtual score of the to-be-sent electronic coupon;

a real-time data obtaining module 920, configured to obtain a real-time getting amount and a real-time usage amount of the to-be-sent electronic coupon from a latest updating time to a current time;

a real-time virtual score determining module 930 configured to determine a real-time virtual score of the to-be-issued sub-coupon according to a bayesian smooth model corresponding to the to-be-issued sub-coupon based on the real-time getting amount and the real-time usage amount;

a target virtual score determining module 940, configured to determine a target virtual score of the to-be-issued sub-coupon according to the offline virtual score and the real-time virtual score;

the coupon issuing module 950 is configured to sort the to-be-issued electronic coupons based on the target virtual scores, and issue the to-be-issued electronic coupons according to a sorting result.

In some exemplary embodiments of the present disclosure, based on the foregoing embodiments, the real-time data obtaining module 920 is specifically configured to:

based on this, the coupon issuance module 950 is specifically configured to:

In some exemplary embodiments of the disclosure, based on the foregoing examples, the coupon offline prediction model is predetermined by:

In some exemplary embodiments of the present disclosure, based on the foregoing embodiments, the bayesian smoothing model corresponding to the electronic coupon to be issued is determined by the following formula:

wherein U is the to-be-issuedThe real-time usage amount of the electronic coupon from the latest updating moment corresponding to the first release updating period to the current moment, G is the real-time getting amount of the to-be-released electronic coupon from the latest updating moment corresponding to the first release updating period to the current moment,

And β is a smoothing parameter in the bayesian smoothing model;

In some exemplary embodiments of the present disclosure, based on the foregoing embodiments, the apparatus 900 further includes a new ticket smoothing parameter determination module specifically configured to: when the historical real-time data does not exist in the to-be-sent electronic coupon, determining that the to-be-sent electronic coupon is a new coupon; and determining the median or average value of the smoothing parameters corresponding to other to-be-issued electronic coupons with the historical real-time data as the smoothing parameters in the Bayesian smoothing model corresponding to the new coupon.

In some exemplary embodiments of the disclosure, based on the foregoing embodiments, the sorting the to-be-issued sub-coupons based on the target virtual score includes:

In some exemplary embodiments of the present disclosure, based on the foregoing embodiments, the first preset threshold and the second preset threshold are determined by:

In some exemplary embodiments of the present disclosure, based on the foregoing embodiments, the apparatus 900 further includes an offline distribution module, which is specifically configured to:

In some exemplary embodiments of the present disclosure, based on the foregoing embodiments, the target virtual score determining module 940 is specifically configured to:

In some exemplary embodiments of the present disclosure, based on the foregoing embodiments, the issuing the to-be-issued sub-coupon according to the sorting result includes:

In some exemplary embodiments of the present disclosure, based on the foregoing examples, the attribute characteristics include one or more of a category of the electronic coupon, a denomination, a limit, a discount strength, a calorific value of an overlaid stock quantity unit, a price of an overlaid stock quantity unit, a category of overlaid goods, a brand of overlaid goods, and an overlaid store.

The details of each unit in the above-mentioned electronic coupon issuing apparatus have been described in detail in the corresponding electronic coupon issuing method, and therefore are not described herein again.

It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.

Moreover, although the steps of the methods of the present disclosure are depicted in the drawings in a particular order, this does not require or imply that the steps must be performed in this particular order, or that all of the depicted steps must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions, etc.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

In an exemplary embodiment of the present disclosure, there is also provided a computer storage medium capable of implementing the above method. On which a program product capable of implementing the above-described method of the present specification is stored. In some possible embodiments, various aspects of the disclosure may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the steps according to various exemplary embodiments of the disclosure described in the "exemplary methods" section above of this specification, when the program product is run on the terminal device.

Referring to fig. 10, a program product 1000 for implementing the above method according to an embodiment of the present disclosure is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

A computer readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

In addition, in an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

As will be appreciated by one skilled in the art, aspects of the present disclosure may be embodied as a system, method or program product. Accordingly, various aspects of the present disclosure may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.

An electronic device 1100 according to this embodiment of the disclosure is described below with reference to fig. 11. The electronic device 1100 shown in fig. 11 is only an example and should not bring any limitations to the function and scope of use of the embodiments of the present disclosure.

As shown in fig. 11, electronic device 1100 is embodied in the form of a general purpose computing device. The components of the electronic device 1100 may include, but are not limited to: the at least one processing unit 1110, the at least one memory unit 1120, a bus 1130 connecting different system components (including the memory unit 1120 and the processing unit 1110), and a display unit 1140.

Wherein the storage unit stores program code that is executable by the processing unit 1110 to cause the processing unit 1110 to perform steps according to various exemplary embodiments of the present disclosure as described in the "exemplary methods" section above in this specification. For example, the processing unit 1110 may perform the following as shown in fig. 1: step S110, inputting the attribute characteristics of the to-be-sent electronic coupons into a coupon offline score prediction model to obtain offline virtual scores of the to-be-sent electronic coupons; step S120, acquiring the real-time acquisition quantity and the real-time usage quantity of the to-be-issued electronic coupon from the latest updating moment to the current moment; step S130, based on the real-time fetching amount and the real-time usage amount, determining a real-time virtual score of the to-be-issued sub-coupon according to a Bayesian smooth model corresponding to the to-be-issued sub-coupon, and step S140, determining a target virtual score of the to-be-issued sub-coupon according to the offline virtual score and the real-time virtual score; and S150, sequencing the electronic coupons to be issued based on the target virtual scores, and issuing the electronic coupons to be issued according to a sequencing result.

As another example, the processing unit 1110 may perform the steps shown in fig. 2 and fig. 4-8.

The storage unit 1120 may include a readable medium in the form of a volatile memory unit, such as a random access memory unit (RAM)11201 and/or a cache memory unit 11202, and may further include a read only memory unit (ROM) 11203.

Storage unit 1120 may also include a program/utility 11204 having a set (at least one) of program modules 8205, such program modules 11205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.

Bus 1130 may be representative of one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The electronic device 1100 may also communicate with one or more external devices 1200 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 1100, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 1100 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 1150. Also, the electronic device 1100 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the internet) via the network adapter 1160. As shown, the network adapter 1160 communicates with the other modules of the electronic device 1100 over the bus 1130. It should be appreciated that although not shown, other hardware and/or software modules may be used in conjunction with the electronic device 1100, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

Furthermore, the above-described figures are merely schematic illustrations of processes included in methods according to exemplary embodiments of the present disclosure, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

Claims

1. An electronic coupon issuing method, comprising:

2. The method for issuing electronic coupons according to claim 1, wherein said obtaining the real-time receiving amount and the real-time using amount of said pending electronic coupons from the latest update time to the current time comprises:

3. The method of claim 1, wherein the coupon offline prediction model is predetermined by:

4. The method for issuing electronic coupons according to claim 2, wherein said bayesian smoothing model corresponding to said electronic coupons to be issued is determined by the following formula:

And β is a smoothing parameter in the bayesian smoothing model;

5. The method of issuing electronic coupons according to claim 4, said method further comprising:

6. The method for issuing electronic coupons according to claim 2, wherein said sorting said pending issue electronic coupons based on said target virtual score comprises:

7. The electronic coupon issuance method according to claim 6, wherein the first preset threshold and the second preset threshold are determined by:

8. The method of issuing electronic coupons according to claim 2, said method further comprising:

9. The method for issuing electronic coupons according to claim 1, wherein said determining a target virtual score of said to-be-issued electronic coupon according to said offline virtual score and said real-time virtual score comprises:

10. The method for issuing electronic coupons according to claim 1, wherein said issuing said to-be-issued electronic coupons according to said sorting result comprises:

11. The electronic coupon distribution method according to any one of claims 1 to 10, wherein the attribute features include one or more of a category, a denomination, a limit, a discount strength, a calorific value of an inventory unit covered, a price of an inventory unit covered, a category of goods covered, a brand of goods covered, a shop covered of electronic coupons.

12. An electronic coupon issuing apparatus, comprising:

13. A computer-readable storage medium on which a computer program is stored, the program, when executed by a processor, implementing an electronic coupon issuing method according to any one of claims 1 to 11.

14. An electronic device, comprising:

one or more processors;

a storage device for storing one or more programs that, when executed by the one or more processors, cause the one or more processors to implement the electronic coupon issuance method according to any one of claims 1 to 11.