CN112613918A - Personalized coupon generation method combining data medium and large data - Google Patents
Personalized coupon generation method combining data medium and large data Download PDFInfo
- Publication number
- CN112613918A CN112613918A CN202011611123.0A CN202011611123A CN112613918A CN 112613918 A CN112613918 A CN 112613918A CN 202011611123 A CN202011611123 A CN 202011611123A CN 112613918 A CN112613918 A CN 112613918A
- Authority
- CN
- China
- Prior art keywords
- data
- coupon
- marketing
- personalized
- coupons
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000001960 triggered effect Effects 0.000 claims abstract description 5
- 239000011159 matrix material Substances 0.000 claims description 21
- 230000000694 effects Effects 0.000 claims description 14
- 238000012360 testing method Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000000354 decomposition reaction Methods 0.000 claims description 2
- 238000012795 verification Methods 0.000 claims description 2
- 235000015847 Hesperis matronalis Nutrition 0.000 claims 1
- 240000004533 Hesperis matronalis Species 0.000 claims 1
- 238000013486 operation strategy Methods 0.000 abstract description 3
- 230000035945 sensitivity Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000002860 competitive effect Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000004936 stimulating effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0224—Discounts or incentives, e.g. coupons or rebates based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for generating an individualized coupon by combining data medium and large data, which comprises the following steps: creating a personalized coupon: in the marketing system coupon template management, newly adding coupon templates, configuring coupon types into personalized coupons, and completing main configuration items: and (3) configuring a marketing task: sending the configuration data of the marketing task and the configuration data of the personalized coupon to a data center through an interface; and generating a personalized coupon: and when the condition of the marketing task is triggered, the marketing system generates the generation of the personalized coupon according to the detail data returned by the data center. According to the invention, by means of a big data algorithm engine of a data center station and the configuration of an operation strategy, personalized coupons can be designed based on the interest preference of each consumer, and the coupons suitable for personal preference commodities of each consumer are issued to each consumer.
Description
Technical Field
The invention relates to the technical field of big data technology and accurate marketing, in particular to a method for generating personalized coupons by combining big data in data.
Background
Issuing coupons is currently an effective practice in consumer marketing. The nature of the coupon is actually a tool stimulating consumption, and it and the points constitute the basic tools for daily membership marketing. The consumer uses the coupon, meaning that he can spend less money to obtain the goods or services. The merchant issues a coupon, meaning that it is possible to get a conversion, win more customers and thus obtain more profits.
But the number of manufacturers or brands applying personalized coupons maturely in the current industry is not large, and most manufacturers or brands focusing on marketing lack big data algorithm capability. At present, most of used coupons are universal full discount coupons or special types/commodity coupons, namely, coupon templates are designed by operators, and a coupon issuing system is used for issuing coupons in a unified way; or the user can select the crowd by combining with a label system and issue the coupons aiming at the generated crowd packet. At the moment, in the same marketing activity and the same crowd pack, the coupons received by each consumer are the same, and the personalized marketing of less than thousands of people is carried out. General type and specific type coupons, while promoting sales, are double-edged swords for brands.
In particular, the main disadvantages of the application of the above-mentioned general full discount/discount coupons, or special categories/commodity coupons, to marketing scenarios are as follows:
1. for loyal or sleeping old customers, one of effective means for improving the activity is to recommend the interested unpurchased goods or new goods, the universal coupon designed by the operator cannot play the role of exposing the interested goods, and the universal coupon can cause 'aesthetic fatigue' after being used for many times;
2. different consumers have different psychological expectations and discount sensitivities to commodity prices, and the general coupon which is folded and buckled by knife looks fair, so that the general coupon cannot benefit more consumers in the same profit offering space;
3. corresponding operation cost and brand injury can be brought by continuous large-scale special-field clearing, popular products are often sold in advance through general preferential activities, and clearing of the marketable products is not helped greatly while profits are sacrificed.
The main reason for the above mentioned shortcomings is that most of the system facilitators or brands that focus on marketing lack the ability of the data middlebox and big data algorithms, and most of the data middlebox facilitators do not have a perfect combination of marketing tools. Therefore, there is a need in the industry to develop a method for generating thousands of personalized coupons by combining a data center with a perfect marketing tool.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provides a method for generating a personalized coupon by combining large data in data.
The purpose of the invention is realized by the following technical scheme:
a method for generating personalized coupons by combining data of Chinese Taiwan type comprises the following steps:
creating a personalized coupon: in the marketing system coupon template management, newly adding coupon templates, configuring coupon types into personalized coupons, and completing main configuration items:
and (3) configuring a marketing task: in the marketing task management of the marketing system, a marketing task is newly added to complete the configuration of the marketing task; sending the configuration data of the marketing task and the configuration data of the personalized coupon to a data center through an interface;
and generating a personalized coupon: and when the condition of the marketing task is triggered, the marketing system generates the generation of the personalized coupon according to the detail data returned by the data center.
Preferably, the step of the detailed data returned by the data center station comprises:
s31, inputting order data, user data and commodity data into a pre-established and trained algorithm model, and outputting a score prediction value reflecting the purchasing characteristics of the user and the commodity;
s32, according to the configuration data transmitted by the configuration marketing task calling interface, filtering the score predicted value output by the algorithm model;
and S33, generating the detail data and returning the detail data to the marketing system.
Preferably, the configuration data comprises: coupon template configuration data and marketing task configuration data; wherein, the security template configuration data includes: the coupon template id, the coupon type, the personalized type, the sales promotion commodity range, the purchased commodity, the number of valid commodities, the coupon discount rate range and the coupon validity period range; the marketing task configuration data includes a marketing task id, a crowd pack id, and a marketing time.
Preferably, the detail data comprises: marketing task id, user id, commodity id, score prediction value and whether purchased.
Preferably, the representation of the established algorithmic model is:
l (X, Y) is a loss function, min L (X, Y) refers to a minimum squared error loss function; r isuiRepresenting the real value corresponding to the u row and the i column in the original matrix;
represents the product of the corresponding values of the two matrixes through matrix decomposition, and the result is the predicted value, lambda (| x) corresponding to the u-th row and the i-th columnu|2+|yu|2) Representing a regularization term, wherein lambda is a Gihonov matrix;
optimizing the formula (1) to obtain a training result matrix; step S31 includes: and (3) inputting the User data User and the commodity data Item into a formula (1) to obtain a Rating prediction value Rating representing the preference degree of the User to the commodity.
Preferably, the main configuration items in the step of creating the personalized coupon include: configuring basic information, configuring rule information and configuring a use range; the basic information comprises a security template name, a use level, whether a ticket is oriented or not, use classification and activity description; the rule information comprises the coupon category, the lowest consumption amount, the maximum issuing quantity, the personalized type, the coupon discount rate range, the highest preferential amount, whether mutually exclusive with the store sales promotion and the mutually exclusive type; the using range comprises the valid period type, the valid period range, the shop range, the brand range, the foreground category range, the sales promotion commodity range, whether the purchased commodities are contained or not and the number of valid commodities;
the configuration of the marketing task includes: configuring marketing content into a coupon, setting a coupon pushing mode and promotion time, and configuring the coupon into a personalized coupon; target groups of marketing tasks are specified.
Preferably, the target group is all members or a group package that has been generated is designated.
Preferably, after the personalized coupon is generated, the generated coupon data is stored for the verification and sale of the personalized coupon, and the coupon data comprises a coupon id, a coupon code, a user id, a commodity id, a discount rate and a validity period.
Preferably, the step of optimizing the formula (1) comprises: and optimizing the algorithm model by using the generated coupon data.
Preferably, the method for generating personalized coupons by combining data of Taida data further comprises the following steps of configuring A/B shunting personalized marketing: newly building a marketing canvas in the marketing canvas of the marketing system, selecting an A/B shunt personalized marketing template preset by the system, entering the corresponding pre-generated marketing canvas, setting marketing time and selected crowds in the marketing canvas, and setting the distribution of target crowd flow; and proportionally distributing according to the test group and the comparison group, wherein the personalized coupons are sent according to the test group, and the general coupons are sent according to the comparison group.
Compared with the prior art, the invention has the following advantages:
the method comprises the steps of firstly creating the personalized coupons and configuring marketing tasks, and when the conditions of the marketing tasks are triggered, the marketing system generates the personalized coupons according to detailed data returned by the data center. And the detail data returned by the data center station is marketing data (detail data) which is generated by the data center station based on the big data of the client and comprises a corresponding single marketing task and an individualized coupon template, so the invention can design the individualized coupon based on the interest preference of each consumer by means of a big data algorithm engine of the data center station and the configuration of an operation strategy, issue the coupon suitable for the individual preference commodity to each consumer, generate different discount strengths aiming at the profit space of the commodity and the discount sensitivity of the consumer, generate an individualized effective period range by combining the repeated purchasing cycle characteristics of the consumer, realize the issuance of thousands of special coupons in the same marketing activity, achieve the effect of individualized accurate marketing, and further solve the bottleneck and difficulty of the marketing of the universal coupon: the method specifically comprises the following steps:
1. through the personalized discount coupons, the accurate exposure of interested commodities is carried out on target people, and the repurchase rate and the commodity association rate of old customers can be effectively improved by combining preferential conditions;
2. the personalized discount is realized through the special discount coupon, the expectation of more consumers can be met, higher overall profit can be obtained under the same offer, and adverse effects such as commodity price reduction and price fight with competitive products are avoided;
3. the logic of 'finding people by goods' is realized by pushing the personalized coupons, and the commodities in the selected range are accurately recommended to the interested crowd in combination with discount, so that the aim of accurate promotion is fulfilled.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
fig. 1 is a flowchart illustrating a method for generating a personalized coupon by combining big data in data according to the present invention.
FIG. 2 is a graph of the scores missing from the sparse matrix of the present invention.
FIG. 3(a) is a process diagram of the present invention for modeling an algorithm.
FIG. 3(b) is another process diagram for modeling an algorithm of the present invention.
FIG. 3(c) is a diagram of another process for modeling an algorithm according to the present invention.
Detailed Description
The invention is further illustrated by the following figures and examples.
Referring to fig. 1, a method for generating a personalized coupon by combining big data in data, comprising:
s1, creating a personalized coupon: in the marketing system coupon template management, newly adding coupon templates, configuring coupon types into personalized coupons, and completing main configuration items: the main configuration items include: configuring basic information, configuring rule information and configuring a use range; the basic information comprises a security template name, a use level, whether a ticket is oriented or not, use classification and activity description; the rule information comprises a coupon category (discount coupon), a minimum consumption amount, a maximum issuing amount, a personalized type, a coupon discount rate range, a maximum preferential amount, whether mutually exclusive with store sales promotion and a mutually exclusive type; the use range comprises the valid period type, the valid period range, the shop range, the brand range, the foreground category range, the sales promotion range, the purchased commodity and the number of valid commodities.
S2, configuring a marketing task: in the marketing task management of the marketing system, newly adding a marketing task, completing basic information configuration, namely configuring marketing content into a coupon, and setting a coupon pushing mode and popularization time; and configures the coupon into the personalized coupon created in step S1; target crowds of the marketing task are appointed, and the configuration of the marketing task is completed; sending the configuration data of the marketing task and the configuration data (main configuration items) of the personalized coupon to a data center station through an interface; the target group is all members or the group package which is generated is designated.
As another possible embodiment, the method for generating personalized coupons in combination with the data-in-data-taiwan data comprises the following steps: newly building a marketing canvas in the marketing canvas of the marketing system, selecting an A/B shunt personalized marketing template preset by the system, entering the corresponding pre-generated marketing canvas, setting marketing time and selected crowds in the marketing canvas, and setting the distribution of target crowd flow; and allocating the proportions according to the test group and the comparison group, wherein the comparison group transmits the universal coupon according to the personalized coupon created in the test group transmission step S1. And clicking a storage button to complete the configuration of the A/B shunting personalized marketing.
It should be noted that the configured marketing task is active marketing (directly executed according to conditions), and the configured a/B split personalized marketing is differentiated marketing according to logic judgment (a/B split).
S3, generating the personalized coupon: and when the condition of the marketing task is triggered (time or event), the marketing system generates the generation of the personalized coupon according to the detail data returned by the data center. And meanwhile, the generated coupon data is stored and is used for verifying and selling the personalized coupons, and the coupon data comprises a coupon id, a coupon code, a user id, a commodity id, a discount rate and a valid period. The detail data includes: marketing task id, user id, commodity id, score prediction value and whether purchased.
The step of detail data returned by the data center station comprises the following steps:
s31, inputting order data, user data and commodity data into a pre-established and trained algorithm model, and outputting a score prediction value reflecting the purchasing characteristics of the user and the commodity;
the relationship between the user and the commodity can be abstracted into the following triples: < User, Item, Rating >. The Rating is the score of the user on the commodity purchasing behavior and represents the preference degree of the user on the commodity.
The algorithm is a model-based recommendation algorithm. The basic idea is that modeling decomposes a sparse matrix to evaluate the values of missing items, so as to obtain a basic training model. New user and item data may then be evaluated against this model. The algorithm uses an alternating least squares method to calculate the missing term. The alternating least squares method is developed on the basis of the least squares method.
Assuming a batch of User data comprising m users and n items, a Rating matrix is defined, wherein the elements represent the scores of the ith Item by the u-th User. (scoring criteria: number of times user u purchased item i).
The user is unlikely to purchase all of the items, and the R matrix is then deemed to be a sparse matrix. The scores missing in the matrix, also called missing items, are shown in FIG. 2.
Assuming that there are several associated dimensions between the user and the merchandise (such as user age, gender, education level, appearance of the merchandise, price, etc.), only the R matrix needs to be projected onto these dimensions. The mathematical representation of this projection is:
in general, the value of k is much smaller than the values of n and m, so as to achieve the purpose of data dimension reduction, as shown in fig. 3 (a).
In fact, these association dimensions need not be explicitly defined, but only need to be assumed to exist, and are therefore also referred to herein as late factors. Typical values of k are generally 10-100.
This method may be referred to as a Probabilistic Matrix Factorization (PMF) algorithm. The algorithm is an application of PMF in numerical calculation.
In order to make the low rank matrices X and Y as close to R as possible, the following squared error loss function needs to be minimized:
considering the stability problem of the matrix, using Tikhonov regularization, the above equation becomes:
wherein:
l (X, Y) is a loss function used for estimating the inconsistency of the predicted value f (X) of the model and the true value Y, and a square error loss function is used; min L (X, Y) refers to the minimum squared error loss function; r isuiRepresenting the true value corresponding to the ith row and ith column in the original matrix, namely the true value of Y stated above;
represents the product of corresponding values of two matrixes decomposed by the matrixes, and the result is a predicted value corresponding to the u row and the i column, namely the predicted value f (X) mentioned above;
λ(|xu|2+|yu|2) Representing the regularization term, least squares solution can result in over-or under-fitting, usually with regularization. The most common regularization methods are: the method is characterized in that the Chehonov regularization is to introduce a regularization operator to convert an ill-posed problem into a posed problem.
In the formula, lambda is a Gihonov matrix (Tikhonov matrix)
(|xu|2+|yu|2) For L2 regularization (to prevent overfitting), reference is made to the L2 paradigm:
the formula (1) is a formula expression of the established algorithm model, and the generated coupon data is adopted to optimize the algorithm model to obtain a training result matrix; during prediction, the User data User and the commodity data Item are input into the formula (1), and a score prediction value Rating representing the preference degree of the User to the commodity is obtained, as shown in fig. 3 (b).
Also, the matrices X and Y can be used to compare the similarity between different users (or items), as shown in FIG. 3 (c):
according to the finally obtained total score predicted value of the User Item and the Rating, the score predicted value Rating can be used for the personalized design of the applicable commodity range of the coupon, the effect that the coupon is distributed to each User is achieved, the applicable commodity range of the coupon falls on the n commodities with the highest preference degree of the User, and meanwhile, the coupon strategy is matched, and the effect of accurate marketing is achieved.
S32, according to the configuration data transmitted by the configuration marketing task calling interface, filtering the score predicted value output by the algorithm model; and the data (score predicted value) after condition filtering corresponds to a single marketing task and a personalized coupon template, is stored in a file form and is returned to a marketing system for generating and distributing the personalized coupon. The configuration data includes: coupon template configuration data and marketing task configuration data; wherein, the security template configuration data includes: the coupon template id, the coupon type, the personalized type, the sales promotion commodity range, the purchased commodity, the number of valid commodities, the coupon discount rate range and the coupon validity period range; the marketing task configuration data includes a marketing task id, a crowd pack id, and a marketing time.
And S33, generating the detail data and returning the detail data to the marketing system.
The invention designs the personalized coupon based on the interest preference of each consumer by means of a big data algorithm engine of a data center station and the configuration of the operation strategy of an operation system, issues the coupon suitable for personal preference commodities to each consumer, generates different preferential strength according to the profit space of the commodities and the discount sensitivity of the consumers, generates the personalized effective period range by combining the repeated purchase cycle characteristic of the consumers, and achieves the effect of personalized accurate marketing:
1. the drainage effect is improved: through a big data algorithm, the individual requirements of consumers are mined, commodities which accord with the preference of the consumers are accurately pushed for the consumers at a specific time, the purchase conversion rate and the drainage effect are improved in cooperation with discount, the capability of the brands for understanding the consumers is reflected, and the recognition degree and the viscosity of the brands by the consumers are improved;
2. and (3) sales promotion: under the condition that the quantity of commodity SKUs is large, a consumer cannot find interested commodities with insufficient exposure in limited contact, and commodities at the long tail position can be accurately exposed to the consumer with buying desire through personalized marketing and a commodity strategy, so that the whole sales is promoted;
3. and (3) the profit amount is improved: the discount strength of the coupon can be designed in an individualized way by combining the data of the profit rate of the commodity and the discount sensitivity of the consumer, and the method is different from the conventional forms of full-field general use/full reduction, commodity price reduction and the like, can effectively avoid price fight with the competitive products and damage to brands, optimizes the offering structure, and obtains higher overall profit under the same promotion strength;
4. and (3) improving the rate of repurchase: the sending time and the validity period of the coupons are individually designed by combining the purchase period of the consumer and the latest purchase time, so that the periodic loss of the consumer can be reduced, and the overall repurchase rate is improved.
The above-mentioned embodiments are preferred embodiments of the present invention, and the present invention is not limited thereto, and any other modifications or equivalent substitutions that do not depart from the technical spirit of the present invention are included in the scope of the present invention.
Claims (10)
1. A method for generating personalized coupons by combining data with Chinese Taiwan data is characterized by comprising the following steps:
creating a personalized coupon: in the marketing system coupon template management, newly adding coupon templates, configuring coupon types into personalized coupons, and completing main configuration items:
and (3) configuring a marketing task: in the marketing task management of the marketing system, a marketing task is newly added to complete the configuration of the marketing task; sending the configuration data of the marketing task and the configuration data of the personalized coupon to a data center through an interface;
and generating a personalized coupon: and when the condition of the marketing task is triggered, the marketing system generates the generation of the personalized coupon according to the detail data returned by the data center.
2. The method for generating personalized coupons in combination with secondary data in a data center as claimed in claim 1, wherein the step of returning detailed data from the secondary data center comprises:
s31, inputting order data, user data and commodity data into a pre-established and trained algorithm model, and outputting a score prediction value reflecting the purchasing characteristics of the user and the commodity;
s32, according to the configuration data transmitted by the configuration marketing task calling interface, filtering the score predicted value output by the algorithm model;
and S33, generating the detail data and returning the detail data to the marketing system.
3. The method of claim 2, wherein configuring data comprises: coupon template configuration data and marketing task configuration data; wherein, the security template configuration data includes: the coupon template id, the coupon type, the personalized type, the sales promotion commodity range, the purchased commodity, the number of valid commodities, the coupon discount rate range and the coupon validity period range; the marketing task configuration data includes a marketing task id, a crowd pack id, and a marketing time.
4. The method for generating personalized coupons in combination with secondary data in a data network as claimed in claim 1, wherein said detail data comprises: marketing task id, user id, commodity id, score prediction value and whether purchased.
5. The method for generating personalized coupons in combination with secondary data in accordance with claim 2, wherein said algorithmic model is established as represented by:
l (X, Y) is a loss function, min L (X, Y) refers to a minimum squared error loss function; r isuiRepresenting the real value corresponding to the u row and the i column in the original matrix;
represents the product of the corresponding values of the two matrixes through matrix decomposition, and the result is the predicted value, lambda (| x) corresponding to the u-th row and the i-th columnu|2+|yu|2) Representing a regularization term, wherein lambda is a Gihonov matrix;
optimizing the formula (1) to obtain a training result matrix;
step S31 includes: and (3) inputting the User data User and the commodity data Item into a formula (1) to obtain a Rating prediction value Rating representing the preference degree of the User to the commodity.
6. The method for generating personalized coupons in combination with damask data in claim 1, wherein the main configuration items in the step of creating personalized coupons include: configuring basic information, configuring rule information and configuring a use range;
the basic information comprises a security template name, a use level, whether a ticket is oriented or not, use classification and activity description; the rule information comprises the coupon category, the lowest consumption amount, the maximum issuing quantity, the personalized type, the coupon discount rate range, the highest preferential amount, whether mutually exclusive with the store sales promotion and the mutually exclusive type; the using range comprises the valid period type, the valid period range, the shop range, the brand range, the foreground category range, the sales promotion commodity range, whether the purchased commodities are contained or not and the number of valid commodities;
the configuration of the marketing task includes: configuring marketing content into a coupon, setting a coupon pushing mode and promotion time, and configuring the coupon into a personalized coupon; target groups of marketing tasks are specified.
7. The method of claim 6, wherein the target group is all members or a group of groups that have been generated are designated.
8. The method for generating personalized coupons in combination with the data center-size data as recited in claim 5, further comprising saving the generated coupon data after generating the personalized coupons for the verification and sale of the personalized coupons, wherein the coupon data comprises coupon id, coupon code, user id, commodity id, discount rate and validity period.
9. The method for generating personalized coupons in combination with secondary data in a data network as claimed in claim 8, wherein the step of optimizing equation (1) comprises: and optimizing the algorithm model by using the generated coupon data.
10. The method for generating personalized coupons in combination with data center size data set forth in claim 1, further comprising configuring a/B offload personalized marketing: newly building a marketing canvas in the marketing canvas of the marketing system, selecting an A/B shunt personalized marketing template preset by the system, entering the corresponding pre-generated marketing canvas, setting marketing time and selected crowds in the marketing canvas, and setting the distribution of target crowd flow; and proportionally distributing according to the test group and the comparison group, wherein the personalized coupons are sent according to the test group, and the general coupons are sent according to the comparison group.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011611123.0A CN112613918B (en) | 2020-12-30 | 2020-12-30 | Personalized coupon generation method combining big data in data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011611123.0A CN112613918B (en) | 2020-12-30 | 2020-12-30 | Personalized coupon generation method combining big data in data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112613918A true CN112613918A (en) | 2021-04-06 |
| CN112613918B CN112613918B (en) | 2024-04-02 |
Family
ID=75249474
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011611123.0A Active CN112613918B (en) | 2020-12-30 | 2020-12-30 | Personalized coupon generation method combining big data in data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112613918B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113807888A (en) * | 2021-09-02 | 2021-12-17 | 支付宝(杭州)信息技术有限公司 | Marketing processing method and device |
| CN117035859A (en) * | 2023-08-14 | 2023-11-10 | 武汉利楚商务服务有限公司 | Intelligent releasing method and system for electronic coupons |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180253496A1 (en) * | 2017-02-28 | 2018-09-06 | Laserlike Inc. | Interest embedding vectors |
| CN110335075A (en) * | 2019-06-30 | 2019-10-15 | 苏宁消费金融有限公司 | Intelligent marketing system and its working method suitable for the consumer finance |
| CN111667305A (en) * | 2020-05-24 | 2020-09-15 | 杭州云徙科技有限公司 | Digital middle station system, construction method and application method |
| CN111768239A (en) * | 2020-06-29 | 2020-10-13 | 腾讯科技（深圳）有限公司 | Property recommendation method, device, system, server and storage medium |
-
2020
- 2020-12-30 CN CN202011611123.0A patent/CN112613918B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180253496A1 (en) * | 2017-02-28 | 2018-09-06 | Laserlike Inc. | Interest embedding vectors |
| CN110335075A (en) * | 2019-06-30 | 2019-10-15 | 苏宁消费金融有限公司 | Intelligent marketing system and its working method suitable for the consumer finance |
| CN111667305A (en) * | 2020-05-24 | 2020-09-15 | 杭州云徙科技有限公司 | Digital middle station system, construction method and application method |
| CN111768239A (en) * | 2020-06-29 | 2020-10-13 | 腾讯科技（深圳）有限公司 | Property recommendation method, device, system, server and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113807888A (en) * | 2021-09-02 | 2021-12-17 | 支付宝(杭州)信息技术有限公司 | Marketing processing method and device |
| CN117035859A (en) * | 2023-08-14 | 2023-11-10 | 武汉利楚商务服务有限公司 | Intelligent releasing method and system for electronic coupons |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112613918B (en) | 2024-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109034915B (en) | Artificial intelligent electronic commerce system capable of using digital assets or points as transaction media | |
| CN110347924A (en) | Fruits and vegetables market management system and fruit-vegetable information method for pushing | |
| US11645559B2 (en) | Methods and apparatus for generating item recommendations based on real-time inference of machine learning models | |
| US11321724B1 (en) | Product evaluation system and method of use | |
| Schultz et al. | Implementing the ‘connect the dots’ approach to marketing communication | |
| Hurtado et al. | Big Data application for E-commerce’s Logistics: A research assessment and conceptual model | |
| CN112613918A (en) | Personalized coupon generation method combining data medium and large data | |
| CN111932345A (en) | Information pushing method and device | |
| CN107146122A (en) | Data processing method and device | |
| Zhao et al. | Loyal consumers or one-time deal hunters: Repeat buyer prediction for e-commerce | |
| Hsieh et al. | More precise: Stores recommendation under O2O commerce | |
| Kopalle et al. | Dynamic pricing: Definition, implications for managers, and future research directions | |
| US11151532B2 (en) | System to facilitate exchange of data segments between data aggregators and data consumers | |
| CN110428281B (en) | Method and device for jointly determining peer-to-peer resource quantity aiming at multiple associated products | |
| Hoffmann et al. | China’s e-commerce prize | |
| Galhotra | Evolution of E-commerce In India: A Review and Its Future Scope | |
| KR102576123B1 (en) | Product marketing linkage system and method | |
| de Matta et al. | Product price alignment with seller service rating and consumer satisfaction | |
| Thakur | Trends and analysis of e-commerce market: a global perspective | |
| Hervert-Escobar et al. | Optimal pricing model based on reduction dimension: A case of study for convenience stores | |
| Carloman et al. | Bundle AI: An Application of Multiple Constraint Knapsack Problem (MCKP) Through Genetic Algorithm (GA) | |
| TWI818281B (en) | Distribution management system | |
| CN110288379A (en) | Conversion price expectation method, apparatus, storage medium and the computer equipment of advertisement | |
| Praveen et al. | A study of online shopping using machine learning techniques | |
| Chen et al. | A dynamic pricing model for e-commerce based on data mining |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |