A method and device for accelerating the maturation of new members based on medical big data
Through the method based on medical big data, a regression model is built and data is dynamically adjusted, which solves the problems of high maturity costs for new members and difficult to determine the validity period of coupons, and achieves the precise marketing and loyalty of new members.
Patent Information
- Application Number
- CN202010569866.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-06-20
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2040-06-20
AI Technical Summary
The existing technology has high costs in ripening new members, difficult to determine the validity period and cycle of coupons, and inability to accurately understand the differences in new members, resulting in high churn rate of new members.
Through a medical big data-based method, the basic information, label information and card opening consumption information of newly registered members are extracted from the database, the medication cycle is calculated, the regression model is constructed, the coupon denomination and validity period is determined, multiple rounds of coupon activities are carried out and dynamically adjusted. Data to achieve precise marketing.
It reduces the cost of ripening new members, improves member loyalty and pharmacy yield, ensures the rationality and accuracy of coupon push, and reduces the loss of new members.
Smart Images

Figure CN111915344B_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present invention relate to the technical field of medical data processing, and in particular to a method and device for accelerating the maturation of new members based on medical big data. Background Art
[0002] With the improvement of the public consumption level, consumption is no longer simply limited to satisfying material needs, and people are more concerned about the development of physical health. How to maintain the relationship between pharmacies and consumers and realize pharmacy revenue has always been a hot topic.
[0003] At present, membership marketing is the preferred solution for major pharmacies. Membership marketing means that enterprises develop members, provide differentiated services and precise marketing, improve customer loyalty, and increase corporate profits in the long term. Through historical data analysis, it can be found that a good membership marketing strategy can help pharmacies in the following aspects: 1. Understand customers; 2. Understand customer consumption behavior; 3. Classify members according to member information and consumption behavior, and carry out more targeted marketing and care. 4. Your own members are the best publicity media. 5. Turn promotions into discounts and care to enhance member consumption experience. 6. Improve customer loyalty. The main advantage is to cultivate many loyal customers for pharmacies, establish a long-term and stable market, and improve the competitiveness of enterprises. Small profits but quick turnover is a common feature of membership marketing pharmacies, and members generally have a time limit, during which members are customers of the pharmacy. If the pharmacy can satisfy its members, this situation may continue for a long time. Since the membership system can attract a large number of customers around the pharmacy for a long time, it is also a disguised blow to competitors.
[0004] The membership system can not only stabilize old customers, but also develop new customers. Since pharmacies that implement the membership system generally have more favorable prices than those in the same industry, they are very attractive to new customers. In addition, most membership cards are allowed to be borrowed, which also provides opportunities for new customers and greatly increases the possibility of them becoming members. At present, major pharmacies in my country have formulated a variety of marketing strategies and marketing activities. The most popular method is to send coupons, which is also a common solution for major pharmacies.
[0005] The arrival of new customers is of great significance to pharmacies. However, through the analysis of historical data, we can find a cruel fact. We often find that some customers only have one membership transaction and never come to the store again. Some of these customers happened to pass by the store during the promotion and applied for membership cards temporarily when they saw the shopping discount; some people applied for membership cards repeatedly because they got gifts for joining the membership. At present, the cost of acquiring new customers is relatively high, so it is very necessary to establish a complete and reliable marketing plan for new members.
[0006] At present, for newly registered members, the new member ripening scheme usually adopted by pharmacies is to regularly send coupons of varying denominations to newly registered members, attract newly registered members to consume, and establish a trust relationship between new members and pharmacies in the long run, so as to achieve the ripening of new members. However, this method of ripening new members is not suitable for all kinds of members, and often causes the new members attracted by pharmacies at a high cost to be lost before they become stable customers. It has the following shortcomings: 1. There are large differences between new members. New members are newly registered members. The pharmacy cannot accurately grasp their age, interest preferences, and consumption ability, and cannot understand new members well; 2. The historical data of general new members is relatively sparse, and pharmacies cannot establish a suitable algorithm model; 3. It is difficult to formulate coupons. Due to the sparsity of new members, pharmacies cannot specify coupons of appropriate denominations. In addition to the coupon denomination problem, there are also problems in determining the validity period of coupons and the coupon sending cycle. 4. The cost is high, and the coupon sending cycle and rounds are difficult to grasp. Few sending times are not effective, and frequent sending will increase marketing costs. Summary of the invention
[0007] The embodiment of the present invention provides a method and device for accelerating the maturity of new members based on medical big data, so as to solve the above-mentioned problems in the prior art.
[0008] In a first aspect, an embodiment of the present invention provides a new member ripening method based on medical big data, comprising:
[0009] S1, extracting a first data set from a pre-established database; the first data set includes member data corresponding to each newly registered member within a given period of time, and the member data includes member basic information, member tag information, and member card opening consumption information;
[0010] S2, calculating the medication cycle of each newly registered member based on the member card opening consumption information, predicting the next purchase time of each newly registered member based on the medication cycle, screening out the newly registered members whose next purchase time exceeds the current time as target members, and retaining the member data of the target members as the second data set;
[0011] S3, performing feature engineering on the member data of the second data set to obtain label data and combined feature data of the target member;
[0012] S4, constructing a regression model according to the target member's label data and combined feature data and training it to obtain a trained regression model;
[0013] S5, inputting the label data of each target member into the trained regression model, outputting the coupon denomination corresponding to each target member, and sending the coupon of the corresponding denomination to each target member.
[0014] Furthermore, the member basic information includes member ID, member points and consumption level, the member tag information includes member identity information and its corresponding physical examination report and electronic health record; the member card opening consumption information includes purchased drug ID, purchased drug name, purchased drug type, purchase time and purchase quantity.
[0015] Further, after step S2, the method further includes:
[0016] The medication cycles of each target member are clustered to obtain target members with similar medication cycles, and the coupon validity period and coupon issuance cycle are determined based on the clustered medication cycles.
[0017] Further, in step S3, the target member's label data includes the target member's gender, age, blood type, occupation, allergy history, disease type, medication cycle, medication dosage and medication time; the combined feature data includes health level, consumption level and income level.
[0018] Further, after step S5, the method further includes:
[0019] S6, recording the target member's response data to the coupon activity; the response data includes whether to respond, response time and activity evaluation; and modifying the label data and combined feature data according to the response data.
[0020] Further, after step S6, the method further includes:
[0021] S7, establish a new regression model for the responding member based on the corrected label data and combined feature data.
[0022] Furthermore, the method further comprises:
[0023] S8, repeating steps S1 to S7 multiple times, conducting multiple rounds of coupon activities, and updating the database before each round of coupon activities.
[0024] In a second aspect, an embodiment of the present invention provides a new member ripening device based on medical big data, comprising:
[0025] A data extraction module is used to extract a first data set from a pre-established database; the first data set includes member data corresponding to each newly registered member within a given period of time, and the member data includes member basic information, member tag information, and member card opening consumption information;
[0026] A data screening module, used to calculate the medication cycle of each newly registered member according to the member card opening consumption information, predict the next purchase time of each newly registered member according to the medication cycle, screen out the newly registered members whose next purchase time exceeds the current time as target members, and retain the member data of the target members as the second data set;
[0027] A feature combination module, used to perform feature engineering on the member data of the second data set to obtain label data and combined feature data of the target member;
[0028] The model training module is used to construct and train a regression model based on the target member's label data and combined feature data to obtain a trained regression model;
[0029] The coupon distribution module is used to input the label data of each target member into the trained regression model, output the coupon denomination corresponding to each target member, and send the coupon of the corresponding denomination to each target member.
[0030] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the method for accelerating the maturation of new members based on medical big data as described in the embodiment of the first aspect of the present invention are implemented.
[0031] In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for accelerating the maturation of new members based on medical big data as described in the embodiment of the first aspect of the present invention.
[0032] The new member ripening method and device based on medical big data provided by the embodiment of the present invention, in addition to recording the basic information of the newly registered members in the database, also records the member tag information, obtains the combined characteristic data of the new members, and constructs a regression model to determine the coupon denomination corresponding to the different tag data of the target members. It can ensure that the preferential strength is set within a reasonable range under the premise of quickly ripening new members, thereby reducing the marketing costs of the enterprise.
[0033] The present invention selects target members who are about to reach the medication cycle from newly registered members, and then clusters target members with similar medication cycles to determine members with similar medication cycles, and then determines the validity period of coupons and the coupon issuance cycle, solving the problem that it is difficult to reasonably determine the validity period and cycle of coupons in the prior art. The present invention conducts multiple rounds of marketing activities for newly registered members, and dynamically adjusts the new member label data and combined feature data during the activities, realizes the reasonable push and precision marketing of coupons, and ensures the profitability of pharmacies and the loyalty of members. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0035] Figure 1 A flowchart of a method for accelerating the maturation of new members based on medical big data provided by an embodiment of the present invention;
[0036] Figure 2 Another flowchart of a method for accelerating the maturation of new members based on medical big data provided by an embodiment of the present invention;
[0037] Figure 3 A structural block diagram of a new member ripening device based on medical big data provided by an embodiment of the present invention;
[0038] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0039] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0040] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0041] Figure 1 A flowchart of a new member ripening method based on medical big data provided by an embodiment of the present invention. In this application, "new member ripening" refers to establishing a trust relationship between new members and pharmacies, and improving the loyalty of new members to pharmacies. Figure 1 , the method comprising:
[0042] S1, extracting a first data set from a pre-established database; the first data set includes member data corresponding to each newly registered member within a given period of time, and the member data includes member basic information, member tag information, and member card opening consumption information.
[0043] Specifically, before executing step S1, it is necessary to first establish a member management system and a database, in which member data is updated in real time and saved in the database. The pharmacy cannot accurately grasp the age, interest preferences, and consumption capacity, and cannot understand the new members well. Then, a first data set is extracted from the database, and the first data set includes the member data corresponding to each newly registered member in a given period of time. In this embodiment, the member data includes basic member information, member tag information, and member card opening consumption information. The embodiment of the present invention establishes a member management system and a database to help subsequent analysis to grasp the age, interest preferences, consumption capacity, etc. of each newly registered member, so as to better understand the new members.
[0044] Among them, basic member information includes member ID, member points and consumption level. Member tag information includes member identity information and its corresponding physical examination report and electronic health record. Member card opening consumption information includes drug purchase ID, drug name, drug type, purchase time and purchase quantity.
[0045] Furthermore, after the first data set is extracted, the data in the first data set is cleaned, converted, filtered, and the data is structured, standardized, and vectorized to prepare for feature engineering and model training in subsequent steps.
[0046] S2, calculating the medication cycle of each newly registered member based on the member card opening consumption information, predicting the next purchase time of each newly registered member based on the medication cycle, screening out the newly registered members whose next purchase time exceeds the current time as target members, and retaining the member data of the target members as the second data set.
[0047] Specifically, the average time interval between drug purchases of each newly registered member can be calculated based on the card opening consumption information of each newly registered member, and the average time interval between drug purchases is used as the medication cycle. The next purchase time of the newly registered member can be predicted based on the latest drug purchase time of the newly registered member and the medication cycle of the newly registered member.
[0048] Furthermore, because some members' medicines are not nearly finished, coupon marketing activities for them will not be effective, and the membership data of these members will form noise that affects the subsequent model training process. Therefore, this embodiment needs to screen newly registered members who will reach the medication cycle. For newly registered members whose next purchase time is not yet at the current time, their membership data is deleted. This embodiment screens out newly registered members whose next purchase time exceeds the current time as target members, and retains the membership data of the target members as the second data set. It can be understood that if the next purchase time of the newly registered member exceeds the current time, it means that the newly registered member is about to reach the medication cycle and has a need to purchase medicines.
[0049] S3, performing feature engineering on the member data of the second data set to obtain label data and combined feature data of the target member.
[0050] Specifically, feature engineering is performed on the member data of the second data set, and the label data of the target member is extracted from the member data, including the target member's gender, age, blood type, occupation, allergy history, disease type, medication cycle, medication dosage and medication time. Furthermore, multiple features are combined to obtain combined feature data, including health level, consumption level and income level.
[0051] S4, constructing a regression model according to the target member's label data and combined feature data and training it to obtain a trained regression model.
[0052] Specifically, when constructing a regression model, the present invention adopts a method of weighted decision-making of multiple regression models to reduce the defects of the accuracy and unstable effect of the output of a single model when facing target members with different label data.
[0053] S5, inputting the label data of each target member into the trained regression model, outputting the coupon denomination corresponding to each target member, and sending the coupon of the corresponding denomination to each target member.
[0054] After the regression model training is completed, the trained regression model is used to predict the coupon denominations that each target member is interested in, and coupons are sent to each target member.
[0055] The new member acceleration method based on medical big data provided by the embodiment of the present invention records the member tag information of the newly registered member in addition to the basic member information in the database, obtains the combined feature data of the new member, and constructs a regression model to determine the coupon denomination corresponding to the different tag data of the target member. It can ensure that the discount intensity is set within a reasonable range under the premise of quickly accelerating the maturity of new members, thereby reducing the marketing costs of the enterprise.
[0056] Based on the above embodiment, after step S2, the method further includes:
[0057] The medication cycles of each target member are clustered to obtain target members with similar medication cycles, and the coupon validity period and coupon issuance cycle are determined based on the clustered medication cycles.
[0058] The embodiment of the present invention screens newly registered members who are about to reach the end of their medication cycles, clusters target members with similar medication cycles, determines members with similar medication cycles, and then determines the validity period of the coupon and the coupon issuance period, thereby solving the problem that it is difficult to reasonably determine the validity period and period of the coupon in the prior art.
[0059] Figure 2 Another flowchart of the method for accelerating the maturity of new members based on medical big data provided by an embodiment of the present invention, after step S5, the method further includes:
[0060] S6, recording the target member's response data to the coupon activity; the response data includes whether to respond, response time and activity evaluation.
[0061] According to the response data, the label data and combined feature data obtained in step S3 are corrected. Referring to the parameter negative feedback strategy of the neural network, the label data of the target member is adjusted in reverse to reduce the influence of time offset and interest offset on the regression model.
[0062] S7, establishing a new regression model for the responding member based on the corrected label data and the combined feature data. The present invention establishes different regression models for the responding members and the non-responding members.
[0063] S8, repeating steps S1 to S7 multiple times, conducting multiple rounds of coupon activities, and updating the database before each round of coupon activities.
[0064] Before each round of coupon activities, the database is updated, that is, the basic information of newly registered members, member label information, and member card opening and consumption information are updated. This is extremely important for pharmacy member marketing. It prevents the mis-issuance of coupons due to the deviation of the interests of newly registered members or the improvement of their health level, which in turn leads to the disgust of newly registered members and reduces the loyalty of newly registered members.
[0065] Repeat the above steps S1 to S7 for multiple times, and give up the coupon activities for members who do not respond to the coupon activities for multiple times, so as to reduce the marketing cost.
[0066] The embodiment of the present invention conducts multiple rounds of marketing activities for newly registered members, and dynamically adjusts new member tag data and combined feature data during the activities, thereby achieving reasonable push of coupons and precise marketing, thereby ensuring the profitability of drugstores and the loyalty of members.
[0067] Figure 3 The structural block diagram of the new member ripening device based on medical big data provided by the embodiment of the present invention is shown in FIG. Figure 3 , the device comprises:
[0068] The data extraction module 301 is used to extract a first data set from a pre-established database; the first data set includes member data corresponding to each newly registered member within a given period of time, and the member data includes member basic information, member tag information, and member card opening consumption information;
[0069] The data screening module 302 is used to calculate the medication cycle of each newly registered member based on the member card opening consumption information, predict the next purchase time of each newly registered member based on the medication cycle, and screen out the newly registered members whose next purchase time exceeds the current time as target members;
[0070] A feature combination module 303 is used to perform feature engineering on the member data of the second data set to obtain label data and combined feature data of the target member;
[0071] Model training module 304, used to construct and train a regression model based on the target member's label data and combined feature data to obtain a trained regression model;
[0072] The coupon issuing module 305 is used to input the label data of each target member into the trained regression model, output the coupon denomination corresponding to each target member, and send the coupon of the corresponding denomination to each target member.
[0073] For details on how to use the data extraction module 301, the data screening module 302, the feature combination module 303, the model training module 304 and the coupon issuance module 305 to accelerate the maturity of new members, please refer to the above method embodiment, and the embodiment of the present invention will not be repeated here.
[0074] The new member ripening device based on medical big data provided by the embodiment of the present invention records the member tag information of the newly registered member in addition to the basic member information in the database, obtains the combined characteristic data of the new member, and constructs a regression model to determine the coupon denomination corresponding to the different tag data of the target member. It can ensure that the preferential strength is set within a reasonable range under the premise of quickly ripening new members, thereby reducing the marketing cost of the enterprise.
[0075] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 4As shown, an embodiment of the present invention provides an electronic device, which may include: a processor (processor) 401, a communication interface (Communications Interface) 402, a memory (memory) 403 and a communication bus 404, wherein the processor 401, the communication interface 402, and the memory 403 complete mutual communication through the communication bus 404. The processor 401 can call the logic instructions in the memory 403 to execute the new member ripening method based on medical big data provided by the above embodiments, for example, including: S1, extracting a first data set from a pre-established database; the first data set includes member data corresponding to each newly registered member in a given period, and the member data includes member basic information, member tag information and member card opening consumption information. S2, calculating the medication cycle of each newly registered member according to the member card opening consumption information, predicting the next purchase time of each newly registered member according to the medication cycle, screening out new registered members whose next purchase time exceeds the current time as target members, clustering the medication cycles of each target member, obtaining target members with similar medication cycles, and retaining the member data of the target member as the second data set. S3, perform feature engineering on the member data of the second data set to obtain the label data and combined feature data of the target member. S4, build a regression model based on the label data and combined feature data of the target member and perform training to obtain a trained regression model. S5, input the label data of each target member into the trained regression model, output the coupon denomination corresponding to each target member, and send a coupon of the corresponding denomination to each target member.
[0076] The embodiment of the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is implemented to execute the new member ripening method based on medical big data provided by the above embodiments, for example, including: S1, extracting a first data set from a pre-established database; the first data set includes member data corresponding to each newly registered member in a given period, and the member data includes member basic information, member tag information and member card opening consumption information. S2, calculating the medication cycle of each newly registered member according to the member card opening consumption information, predicting the next purchase time of each newly registered member according to the medication cycle, screening out new registered members whose next purchase time exceeds the current time as target members, clustering the medication cycles of each target member, obtaining target members with similar medication cycles, and retaining the member data of the target members as the second data set. S3, performing feature engineering on the member data of the second data set to obtain the label data and combined feature data of the target member. S4, constructing a regression model and training it according to the label data and combined feature data of the target member to obtain the trained regression model. S5, inputting the label data of each target member into the trained regression model, outputting the coupon denomination corresponding to each target member, and sending the coupon of the corresponding denomination to each target member.
[0077] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.
[0078] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0079] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A new member ripening method based on medical big data, characterized in that: include: S1, extracting a first data set from a pre-established database; the first data set includes member data corresponding to each newly registered member within a given period of time, and the member data includes member basic information, member tag information, and member card opening consumption information; S2, calculating the medication cycle of each newly registered member based on the member card opening consumption information, predicting the next purchase time of each newly registered member based on the medication cycle, screening out the newly registered members whose next purchase time exceeds the current time as target members, and retaining the member data of the target members as the second data set; S3, performing feature engineering on the member data of the second data set to obtain label data and combined feature data of the target member; S4, construct and train the target member’s label data and combined feature data through a weighted decision method using multiple regression models to obtain a trained regression model. S5, inputting the label data of each target member into the trained regression model, outputting the coupon denomination corresponding to each target member, and sending the coupon of the corresponding denomination to each target member; After step S2, the method further comprises: Cluster the medication cycles of each target member to obtain target members with similar medication cycles, and determine the coupon validity period and coupon issuance cycle based on the clustered medication cycles; Wherein, after step S5, the method further includes: S6, recording the target member's response data to the coupon activity; the response data includes whether to respond, response time and activity evaluation; according to the response data, reversely adjusting the target member's label data through the parameter negative feedback strategy of the neural network; Correcting the label data and the combined feature data; After step S6, the method further comprises: S7, based on the corrected label data and combined feature data, new regression models are established for the responding members and the non-responding members respectively.
2. The new member ripening method based on medical big data according to claim 1 is characterized in that: The basic member information includes member ID, member points and consumption level, the member tag information includes member identity information and its corresponding physical examination report and electronic health record; the member card opening consumption information includes purchased drug ID, purchased drug name, purchased drug type, purchase time and purchase quantity.
3. The method for accelerating the maturation of new members based on medical big data according to claim 1 is characterized in that: In step S3, the target member's label data includes the target member's gender, age, blood type, occupation, allergy history, disease type, medication cycle, medication dosage and medication time; the combined feature data includes health level, consumption level and income level.
4. The new member ripening method based on medical big data according to claim 1 is characterized in that: The method further comprises: S8, repeating steps S1 to S7 multiple times, conducting multiple rounds of coupon activities, and updating the database before each round of coupon activities.
5. A new member ripening device based on medical big data, characterized in that: include: A data extraction module is used to extract a first data set from a pre-established database; the first data set includes member data corresponding to each newly registered member within a given period of time, and the member data includes member basic information, member tag information, and member card opening consumption information; A data screening module, used to calculate the medication cycle of each newly registered member according to the member card opening consumption information, predict the next purchase time of each newly registered member according to the medication cycle, screen out the newly registered members whose next purchase time exceeds the current time as target members, and retain the member data of the target members as the second data set; A feature combination module, used to perform feature engineering on the member data of the second data set to obtain label data and combined feature data of the target member; A model training module is used to construct and train the target member's label data and combined feature data through a weighted decision method of multiple regression models to obtain a trained regression model; The coupon distribution module is used to input the label data of each target member into the trained regression model, output the coupon denomination corresponding to each target member, and send the coupon of the corresponding denomination to each target member; Recording the target member's response data to the coupon activity; the response data includes whether to respond, response time and activity evaluation; according to the response data, reversely adjusting the target member's label data through the parameter negative feedback strategy of the neural network, and correcting the label data and the combined feature data; according to the corrected label data and combined feature data, establishing new regression models for responding members and non-responding members respectively; Among them, after the step of calculating the medication cycle of each newly registered member according to the member card opening consumption information, predicting the next purchase time of each newly registered member according to the medication cycle, screening out the newly registered members whose next purchase time exceeds the current time as target members, and retaining the member data of the target members as the second data set, it also includes: The medication cycles of each target member are clustered to obtain target members with similar medication cycles, and the coupon validity period and coupon issuance cycle are determined based on the clustered medication cycles.
6. An electronic 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 program, the steps of the method for accelerating the maturation of new members based on medical big data as described in any one of claims 1 to 4 are implemented.
7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for accelerating the maturation of new members based on medical big data as described in any one of claims 1 to 4 are implemented.
