Coupon push method, device, computer equipment and medium

Abstract

The embodiment of the present invention provides a coupon push method, device, computer equipment and medium, which relates to the field of Internet technology, wherein the method includes the following steps: if the push type is active push, obtain customer behavior data and customer consumption record data generated by the customer, if the push type is passive push, automatically match coupons that meet the conditions; classify customer data to generate customer data corresponding to different customer types; extract the maximum frequent keyword set from the customer data corresponding to each customer type, and generate keywords corresponding to the consumption preferences and needs of each customer type through the maximum frequent keyword set; obtain the push channel set by the merchant, match the corresponding coupons to each customer type according to the keywords corresponding to the consumption preferences and needs of each customer type, and push the coupons to the push channel. This solution improves the push efficiency of coupons.

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to a coupon push method, device, computer equipment and medium. Background Art

[0002] At present, online sales platforms have quickly entered people's lives with their advantages such as a wide range of product selection, convenient shopping experience and round-the-clock shopping opportunities. At the same time, this has also brought many challenges to merchants, especially small and medium-sized merchants. For them, attracting customers, promoting products and ensuring information security have become major issues for merchant development. At the same time, there is a situation in the current market that in order to attract customers, online sales platforms always try to issue various coupons to customers, which brings customers many unnecessary coupons, resulting in low matching and low accuracy of coupon issuance, and also wasting merchants' preferential resources. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides a coupon push method to solve the technical problems of low matching degree and low precision of coupon issuance in the prior art. The method includes:

[0004] Get the push type set by the merchant. If the push type is active, get the customer behavior data and customer consumption record data generated by the customer. If the push type is passive, after the payment is completed, get the return data of the payment system interface, automatically match the coupons that meet the conditions, and push the coupons to the payment completion interface;

[0005] The customer behavior data and customer consumption record data of all customers are used as customer data. When the amount of customer data is less than or equal to the preset sample size threshold and the proportion of customer behavior data in the customer data meets the preset ratio, the customer data is classified to generate customer data corresponding to different customer types;

[0006] Extract the maximum frequent keyword set from the customer data corresponding to each customer type, and generate keywords of consumption preferences and needs corresponding to each customer type through the maximum frequent keyword set;

[0007] Get the push channels set by the merchant, match corresponding coupons for customers of each customer type according to the keywords of consumption preferences and needs of each customer type, and push the coupons to the push channels.

[0008] The embodiment of the present invention also provides a coupon push device to solve the technical problems of low matching degree and low precision of coupon issuance in the prior art. The device includes:

[0009] The push type determination module is used to obtain the push type set by the merchant. If the push type is active push, the customer behavior data and customer consumption record data generated by the customer are obtained. If the push type is passive push, after the payment is completed, the return data of the payment system interface is obtained, and the coupons that meet the conditions are automatically matched, and the coupons are pushed to the payment completion interface;

[0010] A customer classification module is used to take the customer behavior data and customer consumption record data of all customers as customer data, and classify the customer data when the data volume of the customer data is less than or equal to the preset sample volume threshold and the proportion of the customer behavior data in the customer data meets the preset proportion, so as to generate customer data corresponding to different customer types;

[0011] A keyword extraction module is used to extract the maximum frequent keyword set from the customer data corresponding to each customer type, and generate keywords of consumption preferences and needs corresponding to each customer type through the maximum frequent keyword set;

[0012] The coupon push module is used to obtain the push channels set by the merchant, match the corresponding coupons for each customer type according to the consumption preferences and demand keywords corresponding to each customer type, and push the coupons to the push channels.

[0013] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, any of the above-mentioned coupon push methods is implemented to solve the technical problems of low matching degree and low accuracy of coupon issuance in the prior art.

[0014] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program for executing any of the above-mentioned coupon push methods to solve the technical problems of low matching degree and low accuracy of coupon issuance in the prior art.

[0015] The implementation of this invention is a legal use.

[0016] Compared with the prior art, the beneficial effects that can be achieved by at least one of the above technical solutions adopted in the embodiments of this specification include at least:

[0017] Through active and passive push, a more efficient and accurate traffic and message delivery mechanism is provided. At the same time, customers are classified and corresponding consumption preference and demand keywords are extracted for different customer types. Corresponding coupons are issued based on the keyword matching of consumption preference and demand, which is conducive to improving the matching degree and accuracy of coupon issuance, and thus effectively improving the conversion rate of coupon redemption. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 is a flow chart of a coupon push method provided by an embodiment of the present invention;

[0020] Figure 2 is a structural block diagram of a computer device provided by an embodiment of the present invention;

[0021] Figure 3 It is a structural block diagram of a coupon push device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0023] The following describes the implementation methods of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The present application can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that, in the absence of conflict, the following embodiments and the features in the embodiments can be combined with each other. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work belong to the scope of protection of the present application.

[0024] In an embodiment of the present invention, a method for pushing coupons is provided, such as Figure 1 As shown, the method includes:

[0025] Step S101: Obtain the push type set by the merchant. If the push type is active push, obtain the customer behavior data and customer consumption record data generated by the customer. If the push type is passive push, after the payment is completed, obtain the return data of the payment system interface, automatically match the coupons that meet the conditions, and push the coupons to the payment completion interface;

[0026] Step S102: taking the customer behavior data and customer consumption record data of all customers as customer data, and classifying the customer data when the data volume of the customer data is less than or equal to the preset sample volume threshold and the proportion of the customer behavior data in the customer data meets the preset proportion, to generate customer data corresponding to different customer types;

[0027] Step S103: extracting the maximum frequent keyword set from the customer data corresponding to each customer type, and generating keywords of consumption preferences and needs corresponding to each customer type through the maximum frequent keyword set;

[0028] Step S104: Obtain the push channel set by the merchant, match corresponding coupons for customers of each customer type according to the consumption preferences and demand keywords corresponding to each customer type, and push the coupons to the push channel.

[0029] In specific implementation, in order to push different coupons to different users and increase the efficiency of coupon push, the following steps are used to realize that the customer behavior data and customer consumption record data of all customers are used as customer data. When the data volume of customer data is less than or equal to the preset sample volume threshold and the proportion of customer behavior data in customer data meets the preset ratio, the customer data is classified to generate customer data corresponding to different customer types:

[0030] Preprocess the customer data, delete abnormal data in the customer data, delete the same data corresponding to the same customer ID, and generate a preprocessed data set, where the customer ID is a unique ID corresponding to each customer; if the data volume of the preprocessed data set is greater than the preset sample size threshold, delete the data in the preprocessed data set until the data volume of the preprocessed data set is less than or equal to the preset sample size threshold, and generate an adjusted data set; set the total number of customer types, and randomly select the personal data of a total number of customers from the adjusted data set as the initial data center point set, where the customer behavior data and customer consumption record data of the same customer are the customer's personal data; traverse all data points in the adjusted data set except the initial data center point There is personal data, and the distance between each customer's personal data and each initial data center point in the initial data center point set is calculated respectively, and the personal data is divided into the initial data center point with the closest distance, and multiple initial clusters are generated, and the distance mean of all personal data in the initial cluster is calculated, and the position where the distance mean is located is used as the iterative data center point, and the difference distance from the initial data center point to the iterative data center point is calculated, and the iterative data center point is repeatedly obtained until the difference distance is less than a preset distance threshold, and the iterative data center point is used as the final data center point and a final cluster corresponding to each personal data is generated; all personal data in the final cluster corresponding to each final data center point are divided into customer data corresponding to the same customer type.

[0031] Specifically, user behavior data refers to the action data generated by users during business interactions, such as online or offline purchases, browsing, comments, etc. User transaction data refers to the relevant data generated after users complete payment, such as order amount, quantity, type, etc.

[0032] In specific implementation, in order to reduce the amount of customer data by reducing the proportion of behavioral data in customer data (i.e., the weight of browsing behavior is lower than that of purchasing behavior), the following steps are performed to achieve that if the amount of data in the preprocessed data set is greater than the preset sample size threshold, the data in the preprocessed data set is deleted until the amount of data in the preprocessed data set is less than or equal to the preset sample size threshold, thereby generating an adjusted data set:

[0033] Perform the following operations until the data volume of the adjusted data set is less than or equal to the preset sample size threshold: take the customer behavior data corresponding to the customer identifier as the first data item, and take the customer consumption record data corresponding to the customer identifier as the second data item; respectively set the first data item weight corresponding to the first data item and the second data item weight corresponding to the second data item, wherein the first data item weight is less than the second data item weight; delete the data in the preprocessed data set until the proportion of the customer behavior data corresponding to the same customer identifier in the preprocessed data set and the proportion of the customer consumption record data in the preprocessed data set respectively meet the first data weight and the second data weight, and generate an adjusted data set.

[0034] Specifically, the sum of the first data item weight and the second data item weight is 100%. The first data item weight and the second data item weight are used to reduce the proportion of behavioral data in customer data and increase the proportion of purchasing behavior in customer data, so as to improve the push efficiency of coupons and increase the usage rate of coupons.

[0035] In specific implementation, the amount of customer data can also be reduced by batch sampling. For example, if the amount of data in the preprocessed data set is greater than a preset sample size threshold, the data in the preprocessed data set is deleted until the amount of data in the preprocessed data set is less than or equal to the preset sample size threshold, thereby generating an adjusted data set through the following steps:

[0036] Perform the following operations until the data volume of the adjusted data set is less than or equal to the preset sample size threshold: set the batch sample size, and select the personal data of the batch sample size customers from the adjusted data set through random sampling without playback to form a sampling data set; when the data volume of the sampling data set is less than or equal to the preset sample size threshold and the proportion of customer behavior data in the sampling data set meets the preset ratio, stop random sampling and use the sampling data set as the adjusted data set.

[0037] Specifically, since customer behavior data and customer consumption record data are usually large in volume, the data volume needs to be reduced, and batch sampling can quickly and effectively reduce the data volume.

[0038] In specific implementation, in order to determine the initial data center point, the customer data is classified, and the personal data of a total number of customers are randomly selected from the adjusted data set as the initial data center point through the following steps:

[0039] Randomly select the personal data of one customer from the adjusted data set as the initial sample center; loop the following steps until a total number of customer data are selected as the initial data center points, and generate an initial data center point set: calculate the distance between the initial sample center and each personal data in the adjusted data set except the initial sample center; based on the distance, use weighted probability distribution to select the personal data of the customer corresponding to the maximum distance as the new data center point, save the initial sample center to the initial data center point set, and use the new data center point as the initial sample center.

[0040] In specific implementation, in order to extract different consumption preferences and needs for different user types, the following steps are used to extract the maximum frequent keyword set from the customer data corresponding to each customer type, and generate the keywords of consumption preferences and needs corresponding to each customer type through the maximum frequent keyword set:

[0041] Taking each customer type as a unit, the following steps are repeated until no new candidate keywords can be generated (i.e., only one set of candidate keywords remains), and the generated candidate set is used as the maximum frequent keyword set, and the candidate keywords with the largest number of occurrences in the maximum frequent keyword set are used as keywords for consumer preferences and needs: the number of occurrences of candidate keywords in the customer data corresponding to each of the customer types is counted, and a candidate set is generated by combining the candidate keywords and the number of occurrences corresponding to the candidate keywords, wherein the candidate keywords are the minimum consumer objects and / or behavior objects; a minimum frequency is set, and candidate keywords with a number of occurrences lower than the minimum frequency in the candidate set are deleted, and the remaining candidate keywords are combined in pairs according to the number of occurrences corresponding to the candidate keywords to generate a new set of candidate keywords.

[0042] Specifically, by extracting consumption preferences and demands from each user category, the accuracy of extracting consumption preferences and demands can be further improved, thereby improving the accuracy and precision of coupon push, which is conducive to increasing the efficiency of coupon use.

[0043] In specific implementation, in order to effectively push appropriate coupons after matching the payment return data with the push conditions set by the merchant, the following steps are performed to obtain the return data of the payment system interface after the payment is completed, automatically match the coupons that meet the conditions, and push the coupons to the payment completion interface:

[0044] Obtain the user push conditions set by the merchant, and push coupons to the payment completion interface of customers who match the user push conditions; obtain the customer's payment data from the returned data, obtain the payment push conditions set by the merchant, and push coupons to the payment completion interface of customers whose payment data meets the payment push conditions; obtain the customer's purchase time from the returned data, obtain the purchase time conditions set by the merchant, and push coupons to the payment completion interface of customers whose purchase time meets the purchase time conditions; obtain the customer's purchase location from the returned data, obtain the purchase location conditions set by the merchant, and push coupons to the payment completion interface of customers whose purchase location meets the purchase location conditions; obtain the customer's corresponding historical purchase records from the database, and push coupons to the payment completion interface of customers whose historical purchase records meet the set number of times.

[0045] In an actual implementation example, coupons are pushed using the following method:

[0046] In order to help small and medium-sized merchants operate better, the payment channel provides merchants with an electronic coupon solution. Customers (i.e. users who make purchases) can receive coupons after payment. As long as the next consumption meets the coupon usage conditions, the discount can be automatically deducted. After the customer successfully pays, the system will issue appropriate coupons to the customer based on the customer's geographical location at the time of payment or the payment merchant. Receive the merchant-configured coupon on the payment success page. After receiving the coupon, click "Use Now" to watch the relevant video account and follow the video account to receive the discount.

[0047] 1. Merchants create coupons: Merchants create coupons in the mall background and set the coupon type, acquisition method, scope of use, validity period, etc.

[0048] 2. Coupon activity configuration: Merchants create or participate in a gift-for-payment activity, and apply for, modify or cancel coupon configuration in the gift-for-payment activity. The conditions for receiving coupons in the coupon configuration cannot be all empty.

[0049] 3. Coupon issuance: The reward conditions for payment gift coupons include merchant information, member information, actual payment amount, order time, type of product purchased, geographical location, number of product purchases, number of coupons received, whether the first type of coupon issuance method is applicable, whether the second type of coupon issuance method is applicable, and the location where the coupon can be issued.

[0050] There are two types of coupon issuance methods. The first type of coupon issuance method (i.e. passive push) is applicable to the following conditions: After the customer completes the payment, the system automatically matches the coupon for the payment gift activity through the data returned by the payment system interface. Therefore, the coupon is applicable to the first type of coupon issuance method by default. When the customer meets the reward conditions of the payment gift activity, a reminder to receive the reward coupon will pop up on the payment success page, showing the available coupons. When the system detects that all conditions are met after the customer pays, the system issues the coupon; when the reward condition is partially empty, the corresponding reward condition is automatically deemed to have been met, and the reward conditions cannot be all empty.

[0051] Merchant information can be set to determine whether reward conditions are met only when the merchant's own products are purchased; after member information is set, customers need to reach a member level to meet the conditions; after the actual payment amount is set, the condition is considered to be met when the amount paid by the user exceeds the preset value; the order time can be set to a range, and after setting, the user is considered to meet the condition when purchasing during this time period, and the time can be accurate to minutes; after the purchase product category is set, the category of the goods purchased by the user is consistent with the preset product category, and the condition is considered to be met; after the geographical location is set, the user is considered to meet the condition when placing an order within the specified range. If the user has not submitted the location and this item has been set, the condition is considered not met; the number of product purchases can be set to a greater than / less than mark and a value representing the number of purchases. The user's product purchases will be stored in the background database. The condition is met when the number of user orders is greater than or less than this value; the number of coupons received can be set to determine whether to only count the same type of coupons, the greater than / less than mark, and the number of times received. The background will store the total number of times the user has received coupons and the number of times the same type of coupons have been received. When the user places an order, the system detects that the item meets the conditions for receiving, and the item passes.

[0052] The second type of coupon issuance method (active coupon issuance) is applicable to coupons configured by merchants with "Yes" in the "Whether the second type of coupon issuance method is applicable" setting; the system background groups users according to the encrypted user behavior data and consumption records provided; then analyzes the user's consumption preferences and needs for each user group; then matches the user with the corresponding coupon based on the user's consumption preferences and needs; finally, the matched coupons are sent to users through push channels such as official accounts, mini programs, and video accounts. Set the coupon issuance location (official accounts, mini programs, video accounts, etc.) in the coupon configuration. When it is set to meet the second coupon issuance method and this setting is empty, it is deemed to agree to issue coupons from any coupon issuance location. When the second coupon issuance method is met but this setting is not empty, coupons can only be issued from the set coupon issuance location.

[0053] 4. Coupon collection: When customers collect coupons, they are automatically stored in the card wallet according to the type of coupon and apply to jump to the video account or open the mini program to help customers quickly use the coupons. At the same time, when users collect coupons, the coupon information is automatically stored in the merchant database and the user's coupon collection record is updated.

[0054] 5. Jump to video account or mini program: Customers can jump to the coupon usage page by clicking to view coupon details. When customers click to use coupons, the system will automatically jump to the event video account or merchant mini program through the coupon link address stored in the background, guiding customers to follow the video account to receive prizes or guide customers to use coupons in the mini program to purchase discounted products.

[0055] 6. Coupon usage: Customers click the link in the video account to participate in the event and receive prizes, or purchase products in the mini program.

[0056] 7. Data comparison: Based on the customer's information and the data in the backend merchant information database, the system determines whether the coupon is available, and then automatically uses the appropriate coupon to obtain prizes or discounts when participating in activities and paying.

[0057] 8. Push message reminder: Coupons can be inserted into the user's card wallet. Before the coupon is about to expire, the system will send an expiration reminder notification through the message push platform.

[0058] 9. Coupon Verification: Coupons received by customers are automatically destroyed after use. When customers receive video account prizes or purchase goods with coupons, the system passes the return value of the collection interface or purchase interface to the verification interface, and then updates the database to destroy the used coupons.

[0059] The push of coupons is achieved through the following system architecture.

[0060] 1. Activity diversion module: coupons are issued through the payment completion page, and the JS-SDK interface is used to jump to the page, and customers are diverted to the activity page of the video account or mini program through the discount coupons. When customers use coupons in the video account or mini program, they can see new recommended activities or receive new coupons on the activity page to ensure user retention and bring new development ideas and marketing traffic to the industry.

[0061] 2. Merchant database module: Use a relational database to store information about discounted merchants, discounted products, discount coupons, and promotional activities to facilitate the use and maintenance of data.

[0062] 3. Coupon module: The payment gift activity is configured by the administrator or merchant in the background. The merchant applies for the creation, configuration and modification of coupons in the background. After the application is approved, the changes to the activity and coupons are synchronized to the database and take effect.

[0063] 4. Encryption module: Use the internally modified SM4 encryption algorithm to encrypt data in the business process. Database maintainers cannot directly see the customer's sensitive information, but it does not affect the actual use of the coupon function and ensures the security of customer information.

[0064] 5. Merchant comparison module: When a customer participates in an activity, the data is processed using algorithms such as association rule mining, and then the merchant information and customer information are compared with the database, and the goods are distributed if a match is found.

[0065] 6. Discount sending module: connected to the merchant payment system, the system searches based on the return value of the payment interface or merchant interface when the customer pays, and then makes a judgment based on the data in the merchant database to send coupons to customers accurately and effectively.

[0066] 7. Discount reminder module: Send messages to customers’ APP or mobile phone numbers when they receive coupons, use coupons, or when coupons are about to expire, to enhance users’ perception of discounts. When issuing coupons, if the backend finds that customers have not used a certain number of coupons, it will stop issuing coupons to reduce disturbance to customers.

[0067] 8. Coupon Verification Module: Connect with the mall’s payment system and the video account’s prize collection system, use cloud processing and QuickPass technology to quickly process a large number of coupon verification requests, and update coupon information and usage in real time.

[0068] After the customer pays, the appropriate coupon is pushed to the customer based on the return value of the payment interface or merchant interface when the user pays. The customer can receive the coupon on the payment completion page and then jump to the video account to participate in the event. The system ensures the targeted issuance of coupons through restrictions such as regions and merchants. Coupons can be inserted into the user's card wallet. Before the coupon is about to expire, the user will receive an expiration reminder notification; through the use of coupons, customers are directed to the video account to learn about the product. Through message notifications, users' perception of merchant coupon discounts is enhanced.

[0069] Coupons can be distributed not only on the payment completion page and in the video account, but also in the merchant's own scenarios (the push channels set by the merchant include: merchant mini-programs, H5 web pages, APPs, public account tweets), and in payment traffic scenarios (the push channels set by the merchant also include: nearby coupons, payment gifts, Moments, and other channels).

[0070] Combined with the powerful security and anti-fraud capabilities of the payment solution, illegal activities of black industries are prevented, and the marketing funds of merchants are protected. At the same time, merchants themselves are not responsible for storing user information, but hand over the information to the agents of the video store. Professional operators protect the data to prevent it from being stolen by hackers, so that merchants can spend their energy on their own development.

[0071] In this embodiment, a computer device is provided, such as Figure 2 As shown, it includes a memory 201, a processor 202, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, any of the above-mentioned coupon push methods is implemented.

[0072] Specifically, the computer device may be a computer terminal, a server or a similar computing device.

[0073] In this embodiment, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program for executing any of the above-mentioned coupon push methods.

[0074] Specifically, computer-readable storage media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer-readable storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable storage media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0075] Based on the same inventive concept, an embodiment of the present invention also provides a coupon push device, as described in the following embodiments. Since the principle of solving the problem by the coupon push device is similar to that of the coupon push method, the implementation of the coupon push device can refer to the implementation of the coupon push method, and the repeated parts will not be repeated. As used below, the term "unit" or "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0076] Figure 3 is a structural block diagram of a coupon push device according to an embodiment of the present invention. Figure 3As shown, it includes: a push type determination module 301, a customer classification module 302, a keyword extraction module 303 and a coupon push module 304. The structure is described below.

[0077] The push type determination module 301 is used to obtain the push type set by the merchant. If the push type is active push, the customer behavior data and customer consumption record data generated by the customer are obtained. If the push type is passive push, after the payment is completed, the return data of the payment system interface is obtained, and the coupons that meet the conditions are automatically matched, and the coupons are pushed to the payment completion interface;

[0078] A customer classification module 302 is used to take the customer behavior data and customer consumption record data of all customers as customer data, and classify the customer data when the data volume of the customer data is less than or equal to the preset sample volume threshold and the proportion of the customer behavior data in the customer data meets the preset proportion, so as to generate customer data corresponding to different customer types;

[0079] The keyword extraction module 303 is used to extract the maximum frequent keyword set from the customer data corresponding to each customer type, and generate the keywords of the consumption preference and demand corresponding to each customer type through the maximum frequent keyword set;

[0080] The coupon push module 304 is used to obtain the push channel set by the merchant, match corresponding coupons for customers of each customer type according to the consumption preferences and demand keywords corresponding to each customer type, and push the coupons to the push channel.

[0081] In one embodiment, the customer classification module includes:

[0082] An abnormal data processing unit is used to pre-process the customer data, delete abnormal data in the customer data, delete the same data corresponding to the same customer identifier, and generate a pre-processed data set, wherein the customer identifier is a unique identifier corresponding to each customer;

[0083] A data volume reduction unit is used to delete the data in the preprocessed data set until the data volume of the preprocessed data set is less than or equal to the preset sample volume threshold if the data volume of the preprocessed data set is greater than the preset sample volume threshold, thereby generating an adjusted data set;

[0084] An initial data center point setting unit is used to set the total number of customer types, and randomly select personal data of a total number of customers from the adjusted data set as the initial data center point set, wherein the customer behavior data and customer consumption record data of the same customer are used as the customer's personal data;

[0085] A final cluster division unit is used to traverse all personal data except the initial data center point in the adjusted data set, respectively calculate the distance between the personal data of each customer and each initial data center point in the initial data center point set, divide the personal data into the initial data center point with the closest distance, and generate multiple initial clusters, calculate the distance mean of all personal data in the initial cluster, take the position where the distance mean is located as the iterative data center point, calculate the difference distance from the initial data center point to the iterative data center point, repeatedly obtain the iterative data center point until the difference distance is less than a preset distance threshold, take the iterative data center point as the final data center point and generate a final cluster corresponding to each personal data;

[0086] The customer data generating unit is used to divide all personal data in the final cluster corresponding to each final data center point into customer data corresponding to the same customer type.

[0087] In one embodiment, a data volume reduction unit is used to perform the following operations until the data volume of an adjusted data set is less than or equal to a preset sample volume threshold: taking the customer behavior data corresponding to the customer identifier as the first data item, and taking the customer consumption record data corresponding to the customer identifier as the second data item; respectively setting a first data item weight corresponding to the first data item and a second data item weight corresponding to the second data item, wherein the first data item weight is less than the second data item weight; deleting data in the preprocessed data set until the proportion of the customer behavior data corresponding to the same customer identifier in the preprocessed data set and the proportion of the customer consumption record data in the preprocessed data set respectively meet the first data weight and the second data weight, thereby generating an adjusted data set.

[0088] In one embodiment, the data volume reduction unit is further used to perform the following operations until the data volume of the adjusted data set is less than or equal to a preset sample volume threshold: set the number of batch samples, and select personal data of a batch sample number of customers from the adjusted data set through random sampling without playback to form a sampling data set; when the data volume of the sampling data set is less than or equal to the preset sample volume threshold and the proportion of customer behavior data in the sampling data set meets the preset ratio, stop random sampling and use the sampling data set as the adjusted data set.

[0089] In one embodiment, the initial data center point setting unit is used to randomly select a customer data from the adjusted data set as the initial sample center; loop the following steps until a total number of customer data are selected as the initial data center points to generate the initial data center point set: calculate the distance between the initial sample center and each of the personal data in the adjusted data set except the initial sample center; based on the distance, use weighted probability distribution to select the personal data of the customer corresponding to the maximum distance as the new data center point, save the initial sample center to the initial data center point set, and use the new data center point as the initial sample center.

[0090] In one embodiment, the keyword extraction module includes:

[0091] The maximum frequent keyword set generating unit is used to loop the following steps for each customer type until no new candidate keywords can be generated (i.e., only one set of candidate keywords is left), and use the generated candidate set as the maximum frequent keyword set, and use the candidate keyword with the largest number of occurrences in the maximum frequent keyword set as the keyword of consumer preference and demand:

[0092] A candidate set generating unit, used for counting the number of occurrences of candidate keywords in the customer data corresponding to each of the customer types, and generating a candidate set with the candidate keywords and the number of occurrences corresponding to the candidate keywords, wherein the candidate keywords are minimum consumption objects and / or behavior objects;

[0093] The next level candidate keyword generation unit is used to set a minimum frequency, delete the candidate keywords whose occurrence times in the candidate set are lower than the minimum frequency, and combine the remaining candidate keywords in pairs according to the corresponding occurrence times of the candidate keywords to generate a new set of candidate keywords.

[0094] In one embodiment, the coupon push module includes:

[0095] The first push unit is used to obtain the user push conditions set by the merchant, and push the coupon to the payment completion interface of the customer matching the user push conditions;

[0096] The second push unit is used to obtain the customer's payment data from the returned data, obtain the payment push conditions set by the merchant, and push the coupon to the payment completion interface of the customer whose payment data meets the payment push conditions;

[0097] The third push unit is used to obtain the customer's purchase time from the returned data, obtain the purchase time condition set by the merchant, and push the coupon to the payment completion interface of the customer whose purchase time meets the purchase time condition;

[0098] A fourth push unit is used to obtain the customer's purchase location from the returned data, obtain the purchase location conditions set by the merchant, and push the coupon to the payment completion interface of the customer whose purchase location meets the purchase location conditions;

[0099] The fifth push unit is used to obtain the historical purchase record corresponding to the customer from the database, and push the coupon to the payment completion interface of the customer whose historical purchase record meets the set number of times.

[0100] The embodiments of the present invention achieve the following technical effects:

[0101] Through active and passive push, a more efficient and accurate traffic and message reach mechanism is provided, customers are classified, and corresponding consumption preference and demand keywords are extracted for different customer types. Corresponding coupons are issued based on the keyword matching of consumption preference and demand, which is conducive to improving the matching degree and accuracy of coupon issuance, and thus can effectively improve the conversion rate of coupon redemption; provide a broader scenario for issuing coupons, and the enrichment of traffic channels greatly increases the user range reached by merchant discounts.

[0102] Obviously, those skilled in the art should understand that the modules or steps of the above-mentioned embodiments of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the embodiments of the present invention are not limited to any specific combination of hardware and software.

[0103] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the embodiments of the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for pushing coupons, characterized in that: include: Obtain the push type set by the merchant. If the push type is active push, obtain the customer behavior data and customer consumption record data generated by the customer. If the push type is passive push, after the payment is completed, obtain the return data of the payment system interface, automatically match the coupons that meet the conditions, and push the coupons to the payment completion interface; The customer behavior data and the customer consumption record data of all customers are used as customer data, and when the data volume of the customer data is less than or equal to a preset sample volume threshold and the proportion of the customer behavior data in the customer data meets the preset proportion, the customer data is classified to generate customer data corresponding to different customer types, including: preprocessing the customer data, deleting abnormal data in the customer data, deleting identical data corresponding to the same customer identifier, and generating a preprocessed data set, wherein the customer identifier is a unique identifier corresponding to each customer; If the data volume of the preprocessed data set is greater than the preset sample volume threshold, the data in the preprocessed data set is deleted by reducing the proportion of the behavior data in the customer data until the data volume of the preprocessed data set is less than or equal to the preset sample volume threshold, and an adjusted data set is generated, wherein the user behavior data includes the user's online or offline purchases, browsing, and comments, and the user transaction data includes the order amount, quantity, and type; The total number of the customer types is set, and the personal data of the total number of customers is randomly selected from the adjusted data set as the initial data center point set, including: randomly selecting the personal data of one customer from the adjusted data set as the initial sample center; looping the following steps until the personal data of the total number of customers is selected as the initial data center point, generating the initial data center point set: calculating the distance between the initial sample center and each of the personal data in the adjusted data set except the initial sample center; according to the distance, using a weighted probability distribution to select the personal data of the customer corresponding to the maximum distance as the new data center point, saving the initial sample center to the initial data center point set, and using the new data center point as the initial sample center, wherein the customer behavior data and the customer consumption record data of the same customer are used as the customer's personal data; Traversing all the personal data except the initial data center point in the adjusted data set, respectively calculating the distance between the personal data of each customer and each initial data center point in the initial data center point set, dividing the personal data into the initial data center point with the closest distance, and generating multiple initial clusters, calculating the distance mean of all the personal data in the initial cluster, taking the position where the distance mean is located as the iterative data center point, calculating the difference distance from the initial data center point to the iterative data center point, repeatedly obtaining the iterative data center point, until the difference distance is less than a preset distance threshold, taking the iterative data center point as the final data center point and generating a final cluster corresponding to each personal data; dividing all the personal data in the final cluster corresponding to each final data center point into customer data corresponding to the same customer type; Extracting the maximum frequent keyword set from the customer data corresponding to each of the customer types respectively, and generating keywords of consumption preferences and needs corresponding to each of the customer types through the maximum frequent keyword set; Obtain the push channel set by the merchant, match corresponding coupons to customers of each customer type according to the keywords of the consumption preferences and needs corresponding to each customer type, and push the coupons to the push channel; Extracting the maximum frequent keyword set from the customer data corresponding to each of the customer types, and generating keywords of consumption preferences and needs corresponding to each of the customer types through the maximum frequent keyword set, including: Taking each customer type as a unit, the following steps are repeated until only one set of candidate keywords is left, and the generated candidate set is used as the maximum frequent keyword set, and the candidate keyword with the largest number of occurrences in the maximum frequent keyword set is used as the keyword of consumption preference and demand: Counting the number of occurrences of candidate keywords in the customer data corresponding to each of the customer types, and generating a candidate set with the candidate keywords and the number of occurrences corresponding to the candidate keywords, wherein the candidate keywords are the minimum consumption objects and / or behavior objects; A minimum frequency is set, and the candidate keywords whose occurrence times in the candidate set are lower than the minimum frequency are deleted. The remaining candidate keywords are combined in pairs according to the occurrence times corresponding to the candidate keywords to generate a new group of candidate keywords.

2. The coupon push method according to claim 1, characterized in that: If the data volume of the preprocessed data set is greater than the preset sample volume threshold, deleting the data in the preprocessed data set until the data volume of the preprocessed data set is less than or equal to the preset sample volume threshold, and generating an adjusted data set, including: Perform the following operations until the amount of data in the adjusted data set is less than or equal to the preset sample size threshold: The customer behavior data corresponding to the customer identifier is used as a first data item, and the customer consumption record data corresponding to the customer identifier is used as a second data item; respectively setting a first data item weight corresponding to the first data item and a second data item weight corresponding to the second data item, wherein the first data item weight is less than the second data item weight; Delete the data in the preprocessed data set until the proportion of the customer behavior data corresponding to the same customer identifier in the preprocessed data set and the proportion of the customer consumption record data in the preprocessed data set respectively meet the first data weight and the second data weight, thereby generating the adjusted data set.

3. The coupon push method according to claim 1, characterized in that: If the data volume of the preprocessed data set is greater than the preset sample volume threshold, deleting the data in the preprocessed data set until the data volume of the preprocessed data set is less than or equal to the preset sample volume threshold, and generating an adjusted data set, including: Perform the following operations until the amount of data in the adjusted data set is less than or equal to the preset sample size threshold: Setting a batch sample size, and selecting the personal data of the batch sample size customers from the adjusted data set through random sampling without playback to form a sampling data set; When the data volume of the sampling data set is less than or equal to the preset sample volume threshold and the proportion of the customer behavior data in the sampling data set meets the preset proportion, random sampling is stopped and the sampling data set is used as the adjusted data set.

4. The method for pushing coupons according to any one of claims 1 to 3, characterized in that: After the payment is completed, the return data of the payment system interface is obtained, the coupons that meet the conditions are automatically matched, and the coupons are pushed to the payment completion interface, including: Acquire the user push conditions set by the merchant, and push the coupon to the payment completion interface of the customer matching the user push conditions; Acquire the customer's payment data from the returned data, acquire the payment push conditions set by the merchant, and push the coupon to the payment completion interface of the customer whose payment data meets the payment push conditions; Acquire the purchase time of the customer from the returned data, acquire the purchase time condition set by the merchant, and push the coupon to the payment completion interface of the customer whose purchase time meets the purchase time condition; Acquire the customer's purchase location from the returned data, acquire the purchase location condition set by the merchant, and push the coupon to the payment completion interface of the customer whose purchase location meets the purchase location condition; The historical purchase record corresponding to the customer is obtained from the database, and the coupon is pushed to the payment completion interface of the customer whose historical purchase record meets the set number of times.

5. A coupon push device, characterized in that: include: A push type determination module is used to obtain the push type set by the merchant. If the push type is active push, the customer behavior data and customer consumption record data generated by the customer are obtained. If the push type is passive push, after the payment is completed, the return data of the payment system interface is obtained, and the coupons that meet the conditions are automatically matched, and the coupons are pushed to the payment completion interface; A customer classification module, used to take the customer behavior data and the customer consumption record data of all customers as customer data, and classify the customer data when the data volume of the customer data is less than or equal to a preset sample volume threshold and the proportion of the customer behavior data in the customer data meets a preset ratio, to generate customer data corresponding to different customer types; Customer classification module, including: An abnormal data processing unit is used to pre-process the customer data, delete abnormal data in the customer data, delete the same data corresponding to the same customer identifier, and generate a pre-processed data set, wherein the customer identifier is a unique identifier corresponding to each customer; A data volume reduction unit is used to delete the data in the preprocessed data set by reducing the proportion of the behavior data in the customer data until the data volume of the preprocessed data set is less than or equal to the preset sample volume threshold if the data volume of the preprocessed data set is greater than the preset sample volume threshold, thereby generating an adjusted data set, wherein the user behavior data includes the user's online or offline purchases, browsing, and comments, and the user transaction data includes the order amount, quantity, and type; An initial data center point setting unit is used to set the total number of customer types, and randomly select personal data of a total number of customers from the adjusted data set as the initial data center point set, wherein the customer behavior data and customer consumption record data of the same customer are used as the customer's personal data; The initial data center point setting unit is further used to randomly select a customer data from the adjusted data set as the initial sample center; loop the following steps until a total number of customer data are selected as the initial data center points to generate the initial data center point set: calculate the distance between the initial sample center and each of the personal data in the adjusted data set except the initial sample center; according to the distance, use weighted probability distribution to select the personal data of the customer corresponding to the maximum distance as the new data center point, save the initial sample center to the initial data center point set, and use the new data center point as the initial sample center; A final cluster division unit is used to traverse all personal data except the initial data center point in the adjusted data set, respectively calculate the distance between the personal data of each customer and each initial data center point in the initial data center point set, divide the personal data into the initial data center point with the closest distance, and generate multiple initial clusters, calculate the distance mean of all personal data in the initial cluster, take the position where the distance mean is located as the iterative data center point, calculate the difference distance from the initial data center point to the iterative data center point, repeatedly obtain the iterative data center point until the difference distance is less than a preset distance threshold, take the iterative data center point as the final data center point and generate a final cluster corresponding to each personal data; A customer data generating unit, used for dividing all personal data in the final cluster corresponding to each final data center point into customer data corresponding to the same customer type; A keyword extraction module, used to extract the maximum frequent keyword set from the customer data corresponding to each of the customer types, and generate keywords of consumption preferences and needs corresponding to each of the customer types through the maximum frequent keyword set; A coupon push module is used to obtain a push channel set by a merchant, match corresponding coupons to customers of each customer type according to the consumption preferences and demand keywords corresponding to each customer type, and push the coupons to the push channel; Keyword extraction module, including: The maximum frequent keyword set generating unit is used to loop the following steps for each customer type until no new candidate keywords can be generated (i.e., only one set of candidate keywords is left), and use the generated candidate set as the maximum frequent keyword set, and use the candidate keyword with the largest number of occurrences in the maximum frequent keyword set as the keyword of consumer preference and demand: A candidate set generating unit, used for counting the number of occurrences of candidate keywords in the customer data corresponding to each of the customer types, and generating a candidate set with the candidate keywords and the number of occurrences corresponding to the candidate keywords, wherein the candidate keywords are minimum consumption objects and / or behavior objects; The next level candidate keyword generation unit is used to set a minimum frequency, delete the candidate keywords whose occurrence times in the candidate set are lower than the minimum frequency, and combine the remaining candidate keywords in pairs according to the corresponding occurrence times of the candidate keywords to generate a new set of candidate keywords.

6. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the coupon pushing method according to any one of claims 1 to 4 is implemented.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program for executing the coupon push method according to any one of claims 1 to 4.

Images