Method and device for determining target customer group

Abstract

The invention provides a method and a device for determining a target customer group, which can be used in the financial field, the artificial intelligence technical field or other technical fields. The target customer group determination method comprises the steps that business data in a monitoring period are acquired, and the business data comprise activity development business data of each marketing activity scheme; according to the activity setting data and the activity development business data of each marketing activity scheme, determining an optimal activity marketing scheme in the marketing activity schemes; and according to the activity development business data of the optimal activity marketing scheme, determining a target customer group of the optimal activity marketing scheme, the activity development business data including customer information. According to the target customer group determination method and device provided by the invention, the operation effect is improved from two dimensions of an activity scheme and customer group screening, the marketing conversion rate is improved, and cost reduction and efficiency improvement are realized.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method and device for determining a target customer group. Background Art

[0002] Current marketing activities generally involve marketers manually setting target customer groups for preferential benefits on marketing platforms. This method relies on the experience of marketers and often results in low matching accuracy. At this time, in order to achieve higher matching accuracy, marketers need to constantly adjust the target customer groups. This process is time-consuming and labor-intensive, and the matching accuracy between the target customer groups and preferential benefits that are ultimately determined is still low. Summary of the invention

[0003] In view of the problems in the prior art, the embodiments of the present application provide a method and device for determining a target customer group, which can at least partially solve the problems in the prior art.

[0004] On the one hand, an embodiment of the present application provides a method for determining a target customer group, including:

[0005] Acquire business data within the monitoring period, wherein the business data includes activity development business data of each marketing activity plan;

[0006] Determine the best marketing plan among the marketing plans according to the activity setting data and activity business data of each marketing plan;

[0007] The target customer group of the optimal activity marketing plan is determined according to the activity development business data of the optimal activity marketing plan, wherein the activity development business data includes customer information.

[0008] In some embodiments, after determining the target customer group of the optimal activity marketing plan, the method further includes:

[0009] The activity rights and interests of the optimal activity marketing plan are pushed to the client of the target customer group.

[0010] In some embodiments, determining the optimal marketing activity plan among the marketing activity plans according to the activity setting data and activity business data of each marketing activity plan includes:

[0011] Generate evaluation index data of each marketing activity plan based on the activity setting data and activity development business data of each marketing activity plan;

[0012] Respectively bundling mutually exclusive evaluation index data in the evaluation index data of each marketing activity plan to reduce the dimension of the evaluation index data, and generating target feature data corresponding to each marketing activity plan;

[0013] According to the target characteristic data corresponding to each marketing activity plan, the optimal activity marketing plan among the marketing activity plans is determined.

[0014] In some embodiments, mutually exclusive feature bundling algorithm is used to bundle mutually exclusive evaluation indicator data in the evaluation indicator data of each marketing activity plan to reduce the dimension of the evaluation indicator data.

[0015] In some embodiments, the method further comprises:

[0016] Group customers according to their information to obtain at least two groups of customers;

[0017] Split each group of customers to obtain the executive customers and control customers in each group;

[0018] During the monitoring period, the activity rights and interests of each marketing activity plan are pushed to the client of the executing customer in turn.

[0019] In some embodiments, determining the target customer group of the optimal activity marketing plan according to the activity business data of the optimal activity marketing plan includes:

[0020] According to the activity development business data corresponding to each of the executing customers under the optimal activity marketing plan, the consumption increase probability of the executing customers in each group is calculated;

[0021] Calculate the consumption increase probability of the control customers in each group according to the business data of each of the control customers during the implementation of the optimal marketing activity plan;

[0022] The target customer group of the optimal activity marketing program is determined according to the difference between the consumption increase probability of the executing customers and the consumption increase probability of the control customers in each group of customers.

[0023] In some embodiments, during the monitoring period, sequentially pushing the activity rights of each marketing activity plan to the client of the executing customer includes:

[0024] During the monitoring period, the activity rights and interests of each marketing activity plan are pushed to the client of the executing customer according to the activity setting data of the marketing activity plan, wherein the activity setting data of each marketing activity plan includes at least one of the following information: activity start time, activity end time, number of rights and interests, denomination, validity period, applicable merchants, and applicable customer groups.

[0025] On the other hand, an embodiment of the present application provides a device for determining a target customer group, including:

[0026] An acquisition module, used to acquire business data within a monitoring period, wherein the business data includes activity development business data of each marketing activity plan;

[0027] A first determination module is used to determine the best activity marketing plan among the marketing activity plans according to the activity setting data and activity development business data of each marketing activity plan;

[0028] The second determination module is used to determine the target customer group of the optimal activity marketing plan according to the activity development business data of the optimal activity marketing plan, wherein the activity development business data includes customer information.

[0029] In some embodiments, after determining the target customer group of the optimal activity marketing plan, the method further includes:

[0030] The activity rights and interests of the optimal activity marketing plan are pushed to the client of the target customer group.

[0031] In some embodiments, the first determining module is specifically configured to:

[0032] Generate evaluation index data of each marketing activity plan based on the activity setting data and activity development business data of each marketing activity plan;

[0033] Respectively bundling mutually exclusive evaluation index data in the evaluation index data of each marketing activity plan to reduce the dimension of the evaluation index data, and generating target feature data corresponding to each marketing activity plan;

[0034] According to the target characteristic data corresponding to each marketing activity plan, the optimal activity marketing plan among the marketing activity plans is determined.

[0035] In some embodiments, mutually exclusive feature bundling algorithm is used to bundle mutually exclusive evaluation indicator data in the evaluation indicator data of each marketing activity plan to reduce the dimension of the evaluation indicator data.

[0036] In some embodiments, the apparatus further comprises:

[0037] A grouping module, used for grouping customers according to customer information to obtain at least two groups of customers;

[0038] A splitting module is used to split each group of customers to obtain the execution customers and control customers in each group of customers;

[0039] The push module is used to push the activity rights and interests of each marketing activity plan to the client of the executing customer in sequence during the monitoring period.

[0040] In some embodiments, the second determining module is specifically configured to:

[0041] According to the activity development business data corresponding to each of the executing customers under the optimal activity marketing plan, the consumption increase probability of the executing customers in each group is calculated;

[0042] Calculate the consumption increase probability of the control customers in each group according to the business data of each of the control customers during the implementation of the optimal marketing activity plan;

[0043] The target customer group of the optimal activity marketing program is determined according to the difference between the consumption increase probability of the executing customers and the consumption increase probability of the control customers in each group of customers.

[0044] In some embodiments, the push module is specifically used to:

[0045] During the monitoring period, the activity rights and interests of each marketing activity plan are pushed to the client of the executing customer according to the activity setting data of the marketing activity plan, wherein the activity setting data of each marketing activity plan includes at least one of the following information: activity start time, activity end time, number of rights and interests, denomination, validity period, applicable merchants, and applicable customer groups.

[0046] An embodiment of the present application also provides an electronic device, including 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 determining a target customer group described in any of the above embodiments are implemented.

[0047] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for determining a target customer group described in any of the above embodiments are implemented.

[0048] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the method for determining a target customer group described in any of the above embodiments are implemented.

[0049] The method and device for determining the target customer group provided by the embodiment of the present application obtains the business data within the monitoring period, wherein the business data includes the activity development business data of each marketing activity plan; determines the optimal activity marketing plan in each of the marketing activity plans according to the activity setting data and activity development business data of each marketing activity plan; determines the target customer group of the optimal activity marketing plan according to the activity development business data of the optimal activity marketing plan, wherein the activity development business data includes customer information. In this way, the target customer group of the marketing activity is determined by using computer technology instead of manually determining the target customer group of the marketing activity, which greatly improves the efficiency of identifying the target customer group; in addition, in the process of determining the target customer group, instead of identifying the target customer group of all marketing activity plans within the monitoring period, the optimal marketing activity plan is first screened out, and then the target customer group of the optimal marketing activity plan is identified, that is, only a part of the screened data is used to identify the target customer group, so that on the basis of improving the operation effect from the two dimensions of activity plan and customer group screening, the computational complexity of the entire target customer group identification process is greatly reduced, and the matching accuracy is improved. In addition, the marketing conversion rate can also be improved to achieve cost reduction and efficiency improvement. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. 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 creative work. In the drawings:

[0051] Figure 1 It is a flowchart of a method for determining a target customer group provided in one embodiment of the present application.

[0052] Figure 2 It is a partial flow chart of a method for determining a target customer group provided in one embodiment of the present application.

[0053] Figure 3 It is a partial flow chart of a method for determining a target customer group provided in one embodiment of the present application.

[0054] Figure 4 It is a partial flow chart of a method for determining a target customer group provided in one embodiment of the present application.

[0055] Figure 5 It is a flowchart of a method for determining a target customer group provided in one embodiment of the present application.

[0056] Figure 6 It is a schematic diagram of an embodiment of the present application that splits collected features into continuous features and discrete features according to feature attributes.

[0057] Figure 7 It is a schematic diagram of the correlation coefficient between features calculated according to an embodiment of the present application.

[0058] Figure 8 It is a schematic diagram of the result of sorting and coloring features according to an embodiment of the present application.

[0059] Fig. 9 It is a schematic diagram of the result after bundling features according to an embodiment of the present application.

[0060] Fig.10 It is a schematic diagram of classification results after classifying customers according to an embodiment of the present application.

[0061] Fig.11 It is a structural diagram of a device for determining a target customer group provided in one embodiment of the present application.

[0062] Fig.12 It is a schematic diagram of the physical structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. Here, the illustrative embodiments of the present application and their descriptions are used to explain the present application, but are not intended to limit the present application. It should be noted that, in the absence of conflict, the embodiments in the present application and the features in the embodiments can be arbitrarily arranged with each other.

[0064] The terms “first”, “second”, etc. used in this document do not specifically refer to an order or sequence, nor are they used to limit this application. They are only used to distinguish elements or operations described with the same technical terms.

[0065] The words “include,” “including,” “have,” “contain,” etc. used in this document are open-ended terms, meaning including but not limited to.

[0066] As used herein, "and / or" includes any and all permutations of the items described.

[0067] The acquisition, storage, use, and processing of data in the technical solutions of each embodiment of the present application comply with the relevant provisions of national laws and regulations.

[0068] The execution subject of the method for determining the target customer group provided in the embodiment of the present application includes but is not limited to a computer.

[0069] Figure 1 is a flow chart of a method for determining a target customer group provided in an embodiment of the present application. Figure 1 As shown, the method for determining the target customer group provided in the embodiment of the present application includes:

[0070] S101, acquiring business data within a monitoring period, wherein the business data includes activity development business data of each marketing activity plan;

[0071] In step S101, within the monitoring cycle, the marketing platform can carry out marketing activities according to the activity data set by the marketing personnel. Each setting of activity data is equivalent to setting up a marketing activity plan. Within the monitoring, multiple marketing activity plans are set, and corresponding to each marketing activity plan, the business data during the execution of the marketing activity plan is obtained.

[0072] S102, determining the best marketing activity plan among the marketing activity plans according to the activity setting data and activity development business data of each marketing activity plan;

[0073] In step S102, by comparing the activity setting data and the activity business data, the optimal activity effect is identified according to the business logic, and the activity marketing plan with the optimal activity effect is the optimal activity marketing plan.

[0074] S103. Determine the target customer group of the optimal activity marketing plan based on the activity development business data of the optimal activity marketing plan, wherein the activity development business data includes customer information.

[0075] In step S103, based on the activity development business data of the optimal activity marketing plan, it can be determined which customers have the best response to the optimal activity marketing plan, and the customer group with the best response is the target customer group of the optimal activity marketing plan.

[0076] The method for determining the target customer group provided in the present application obtains business data within a monitoring period, wherein the business data includes activity development business data of each marketing activity plan; determines the optimal activity marketing plan among the marketing activity plans based on the activity setting data and activity development business data of each marketing activity plan; determines the target customer group of the optimal activity marketing plan based on the activity development business data of the optimal activity marketing plan, wherein the activity development business data includes customer information. In this way, computer technology is used instead of manual determination of the target customer group for marketing activities, which greatly improves the efficiency of identifying the target customer group. In addition, in the process of determining the target customer group, instead of identifying the target customer group of all marketing activity plans within the monitoring period, the optimal marketing activity plan is first screened out, and then the target customer group of the optimal marketing activity plan is identified. That is to say, only a part of the screened data is used to identify the target customer group. In this way, on the basis of improving the operational effect from the two dimensions of activity plan and customer group screening, the computational complexity of the entire target customer group identification process is greatly reduced, and the matching accuracy is improved. In addition, the marketing conversion rate can also be improved to achieve cost reduction and efficiency improvement. In some embodiments, after determining the target customer group of the optimal activity marketing plan, the method also includes: pushing the activity rights and interests of the optimal activity marketing plan to the client of the target customer group.

[0077] Specifically, the target customer group of the optimal marketing campaign refers to a customer group with certain characteristics. After determining the target customer group of the optimal marketing campaign, as long as the customer has this characteristic, the customer can be considered to belong to the target customer group of the optimal marketing campaign.

[0078] like Figure 2 As shown, in some embodiments, determining the optimal activity marketing plan among the marketing activity plans according to the activity setting data and activity business data of each marketing activity plan includes:

[0079] S1021. Generate evaluation index data of each marketing activity plan according to the activity setting data and activity development business data of each marketing activity plan;

[0080] In step S1021, the activity effect of the marketing activity plan can be evaluated according to some evaluation indicators, and these evaluation indicators can be calculated according to the activity setting data and activity development business data of the marketing activity plan.

[0081] S1022, respectively bundling mutually exclusive evaluation index data in the evaluation index data of each marketing activity plan to reduce the dimension of the evaluation index data, and generating target feature data corresponding to each marketing activity plan;

[0082] In step S1022, when there are many activity effect evaluation indicators, feature dimensionality reduction can be achieved by bundling mutually exclusive features, which can overcome the information loss problem caused by traditional dimensionality reduction methods.

[0083] S1023. Determine the optimal marketing plan among the marketing plan based on the target characteristic data corresponding to each marketing plan.

[0084] In step S1023, the features after dimensionality reduction are compared to obtain the optimal marketing campaign plan.

[0085] In some embodiments, mutually exclusive feature bundling algorithm is used to bundle mutually exclusive evaluation indicator data in the evaluation indicator data of each marketing activity plan to reduce the dimension of the evaluation indicator data.

[0086] like Figure 3 As shown, in some embodiments, the method further includes:

[0087] S104, grouping customers according to customer information to obtain at least two groups of customers;

[0088] In step S104, customers with similar characteristics are grouped into one group based on the customer information, thereby obtaining at least two groups of customers.

[0089] S105, splitting each group of customers to obtain the execution customers and control customers in each group of customers;

[0090] In step S105, the same group of customers have similar characteristics, so for each group of customers, the group of customers is divided into execution customers and control customers, and the number of execution customers and control customers in each group of customers is substantially equal.

[0091] S106. During the monitoring period, the activity rights and interests of each marketing activity plan are pushed to the client of the executing customer in sequence.

[0092] In step S106, during the monitoring period, the activity rights of each marketing activity plan are pushed in sequence, that is, the activity rights of one marketing activity plan are pushed to the client of the executing customer first, and after the marketing activity is completed, the activity rights of another marketing activity plan are pushed to the client of the executing customer, and so on, until the push of the activity rights of all marketing activity plans is completed. In addition, the executing customer refers to the executing customer in all groups.

[0093] like Figure 4 As shown, in some embodiments, determining the target customer group of the optimal activity marketing plan according to the activity business data of the optimal activity marketing plan includes:

[0094] S1031, calculating the consumption increase probability of the executing customers in each group according to the activity development business data corresponding to each executing customer under the optimal activity marketing plan;

[0095] In step S1031, the consumption increase probability of the executing customers in each group may be calculated with reference to the principle of the Uplift model.

[0096] S1032, calculating the consumption increase probability of the control customers in each group according to the business data of each of the control customers during the implementation of the optimal activity marketing plan;

[0097] In step S1032, during the implementation of the optimal activity marketing plan, the activity rights of the optimal activity marketing plan are not pushed to the control customers in each group, but this does not mean that the control customers do not participate in consumption. Therefore, the business data of each of the control customers during the implementation of the optimal activity marketing plan is obtained, and the consumption increase probability of the control customers in each group of customers is calculated. The consumption increase probability of the control customers in each group can be calculated with reference to the principle of the Uplift model.

[0098] S1033. Determine the target customer group of the optimal activity marketing plan according to the difference between the consumption increase probability of the executing customers and the consumption increase probability of the control customers in each group of customers.

[0099] In step S1033, the larger the difference is, the more positive the response of the group of customers to the optimal marketing campaign is. Therefore, the target customer group of the optimal marketing campaign can be determined based on the group of customers with the largest difference.

[0100] In some embodiments, pushing the activity rights of each marketing campaign plan to the client of the executing customer in sequence during the monitoring period includes: pushing the activity rights of each marketing campaign plan to the client of the executing customer according to the activity setting data of each marketing campaign plan during the monitoring period, wherein the activity setting data of each marketing campaign plan includes at least one of the following information: activity start time, activity end time, number of rights, denomination, validity period, applicable merchants, and applicable customer groups.

[0101] In order to better understand the present application, the method for determining the target customer group provided by the present application is described in detail below through a specific embodiment.

[0102] This embodiment provides a device for determining a target customer group, including an activity planning module, a marketing module, a data collection module, and a data analysis module;

[0103] The activity planning module is used to set activity data through marketing personnel and send the activity data to the marketing module;

[0104] The marketing module includes a marketing platform, and the marketing module is used to transmit activity data of the marketing platform to the data collection module;

[0105] The data collection module is used to collect activity setting data, activity order data, consumption order data, and customer information data, and provide them to the data analysis module in a unified manner;

[0106] The data analysis module is used to analyze the data provided by the data acquisition module and output the prediction results to the activity planning module;

[0107] The prediction model is trained and optimized continuously in a sequential cycle.

[0108] like Figure 5 As shown, the steps include the following:

[0109] S1: Marketing personnel set key activity data, including activity start time, number of benefits, denomination, validity period, applicable merchants, applicable customer groups and other activity information;

[0110] S2: The marketing platform stores activity setting data and activity business data, and transmits them to the data collection module at the end of each day;

[0111] S3: The data collection module collects activity setting data, activity order data, customer behavior data, and customer basic information data, and feeds it back to the data analysis module;

[0112] S4: The analysis module compares the activity setting data and activity order data, identifies the optimal activity effect according to the business logic, and performs model analysis on the activity order data, customer behavior data, and basic information data to predict the rights and interests of the adapted customer group.

[0113] The key data set for the activity in step S1 includes but is not limited to the following information:

[0114] 1. Equity denomination X: the value of the red envelope, a positive number greater than 0;

[0115] 2. Number of rights Y: corresponds to the number of red envelope values, which is a positive integer greater than 0;

[0116] 3. Red envelope usage threshold: that is, the red envelope usage conditions, which can only be used when the order amount is greater than or equal to T;

[0117] 4. Total activity budget: total activity funds. Generally, total budget = number of rights × par value;

[0118] 5. Activity day budget: daily activity expenses;

[0119] 6. Activity duration T: the number of days the activity lasts;

[0120] 7. Number of merchants targeted by the activity;

[0121] 8. Number of users targeted by the activity.

[0122] The activity order data set involved in step S2 includes but is not limited to:

[0123] Activity type, activity ID number, customer number, record status, media type, merchant number, product type, transaction type, transaction date, transaction amount, transaction currency, equity denomination, equity write-off time, total activity equity write-off amount, total activity usage budget, etc.

[0124] The customer behavior and basic information data set in step S3 includes but is not limited to the following information:

[0125] Customer behavior information: product activation time, agreement signing status, daily average current assets, monthly average credit card repayments, customer visits, customer orders, customer order amounts, whether customers have enjoyed benefits, etc.

[0126] Customer basic information: age, gender, industry type, marital status, educational background, salary, housing situation, etc.

[0127] The activity effect evaluation indicator set in step S4 includes but is not limited to the following:

[0128] 1) Activity resource write-off: expressed as total equity used / total activity budget;

[0129] 2) Daily average activity resource write-off: total daily equity write-off / activity day budget;

[0130] 3) Activity resource write-off scale: the total amount of activity write-off rights;

[0131] 4) Daily scale of activity resource write-offs: daily average of activity write-offs;

[0132] 5) Total order amount driven by activities: indicates the total order amount that is eligible for equity acquisition / use;

[0133] 6) Number of orders driven by activities: indicates the number of orders completed during the activity period;

[0134] 7) Customer participation in the event: indicates the number of customers who successfully placed orders during the event period.

[0135] 8) Merchant participation in the event: indicates the number of merchants with orders during the event period.

[0136] The activity effect evaluation index set in step S4 collects a large number of activity effect evaluation indicators. By bundling mutually exclusive features to achieve feature dimensionality reduction, the information loss problem caused by traditional dimensionality reduction methods can be overcome, making the model prediction more accurate.

[0137] 1) Assume that 4 features x1, x2, x3, and x4 are collected and divided into two categories: continuous features and discrete features according to the feature attributes. The continuous feature variables x1x2 are binned at equal intervals to form y1 and y2. Figure 6 shown.

[0138] 2) Calculate the conflict ratio (non-mutually exclusive ratio) of the four features x3, x4, y1, and y2. When two features are non-mutually exclusive and take non-zero values ​​at the same time, they are considered to be in conflict. The larger the conflict ratio, the lower the degree of mutual exclusion. That is, calculate the correlation coefficient between the features. The calculation results are as follows: Figure 7 As shown, the value 0.428 represents the conflict ratio between x4 and x3.

[0139] 3) Sort and color the features, connect them according to the conflict situation, calculate the sum of the conflicting values, and color them according to the results. Assuming the system sets the max_conflict_rate to 0.3, if the conflict ratio between (y2, x4) and (y1, y2) is less than 0.3, no connection will be made. y1 has the most connections, so it is colored red. The number of connections between x3 and y2 is the same, but the conflict ratio of x3 is higher than that of y2, so x3 is colored yellow and y2 is colored blue. x4 has the least connections, so it is colored light blue. See Figure 8 .

[0140] 4) Bundle the features. From the above analysis, we know that x4 has the least number of connections and the (x4, y2) conflict ratio is less than 0.3, so x4 and y2 are bundled, and y2 is used as the main feature. When bundling, consider the later feature restoration. The value range of the y2 main feature is [0,1], and the maximum offset is 1. All non-zero values ​​of x4 plus the offset are added to y2 to obtain the bundled feature value. See Fig. 9 .

[0141] 5) Compare the features after dimensionality reduction to obtain the optimal activity plan.

[0142] The customer group screening method in step S4 is implemented in this solution with the help of the Uplift model. The specific logic is as follows:

[0143] The Uplift model is a method for modeling the incremental benefits of specific interventions. It is mainly used to predict the increase in transaction willingness promoted by equity activities, that is, the increment (Uplift), and to identify users who can be truly impressed by equity activities. By using the characteristics and historical data of customers before the equity is issued, the Uplift model is constructed to predict the increase in consumption of each customer after receiving the equity, and then the customer groups with higher prediction results are verified to confirm their sensitivity to equity activities, and finally the sensitive customer groups are listed as preferential / equity target customers. This embodiment mainly explores sensitive type I population and avoids antipathetic type IV population. See Fig.10 :

[0144] ⅠSensitive type: if you give them rights, they will be promoted; if you don’t give them rights, they will not be promoted;

[0145] Ⅱ Loyal type: Whether or not they are given equity, they will increase their assets;

[0146] III Zombie type: assets will not be increased whether equity is given or not;

[0147] IV. Antipathetic type: No improvement if rights are given, improvement if no rights are given.

[0148] This embodiment uses the Class Transformation Method for measurement. The label transformation model can connect the data of the experimental group and the control group, and directly predict the Uplift score, which is the difference between the probability of consumption increase in the execution group and the probability of consumption increase in the control group. Let Q represent whether the rights are issued, X represents the customer characteristics, and Y=1 represents the customer consumption increase. The Uplift model can calculate P(Y=1|X, Q), the probability of consumption increase due to rights. The specific process is as follows:

[0149] First, define a variable G∈{T,C}, G=T means intervention, i.e., the implementation group, G=C means no intervention, i.e., the control group. The uplift score can be expressed as:

[0150] Uplift score = P(Y = 1|X, G = T) - P(Y = 1|X, G = C) = Pt(Y = 1|X) - Pc(Y = 1|X) = probability of consumption increase in the execution group - probability of consumption increase in the control group;

[0151] In order to uniformly represent the situation where both the execution group and the control group have improved their assets (Y = 1), we define another variable Z, Z∈{0,1}:

[0152]

[0153] When the customer is in the execution group (sign-up activity) and the customer finally improves the asset, Z = 1;

[0154] When the customer is in the control group (not enrolled in the activity) and the customer ultimately does not increase assets, Z = 1;

[0155] When the customer is in the execution group (signing up for an activity) and the customer does not ultimately upgrade assets, Z = 0;

[0156] When the customer is in the control group (not enrolled in the campaign) and the customer eventually increases assets, Z=0.

[0157] The sample sizes of the execution group and the control group are set to be the same, so P(G=T) and P(G=C)=0.5, that is, the probability of a customer being assigned to the execution group and the control group is equal.

[0158] Therefore, Uplift Score = Pt(Y = 1|X) - Pc(Y = 1|X) = 2P(Z = 1|X) - 1, and the goal is transformed from predicting Uplift Score to predicting P(Z = 1 | Xi). Finally, the Qini curve is introduced to evaluate the Uplift model.

[0159] This embodiment obtains the corresponding business data within the monitoring period from the system background, and performs correlation analysis on the marketing activity data and customer information data, extracts the key indicators of the activity effect, optimizes the activity strategy setting, provides the optimal rights and interests deployment strategy, and screens sensitive customer groups at the same time, that is, prioritizes the allocation of higher rights and interests for sensitive customer groups, allocates medium rights and interests for moderately sensitive customer groups, and allocates lower or no rights and interests for low-sensitive customer groups. Through the above method, computer technology is used instead of manual determination of the target customer group of the marketing activity, which greatly improves the efficiency of identifying the target customer group; in addition, in the process of determining the target customer group, instead of identifying the target customer group of all marketing activity plans within the monitoring period, the optimal marketing activity plan is first screened out, and then the target customer group of the optimal marketing activity plan is identified, that is, only a part of the screened data is used to identify the target customer group. In this way, on the basis of improving the operation effect from the two dimensions of activity plan and customer group screening, the computational complexity of the entire target customer group identification process is greatly reduced, and the matching accuracy is improved. In addition, the marketing conversion rate can also be improved to achieve cost reduction and efficiency improvement. Fig.11 is a schematic diagram of the structure of a device for determining a target customer group provided in an embodiment of the present application. Fig.11 As shown, the target customer group determination device provided in the embodiment of the present application includes:

[0160] An acquisition module 21 is used to acquire business data within a monitoring period, wherein the business data includes activity development business data of each marketing activity plan;

[0161] A first determination module 22 is used to determine the best activity marketing plan among the marketing activity plans according to the activity setting data and activity development business data of each marketing activity plan;

[0162] The second determination module 23 is used to determine the target customer group of the optimal activity marketing plan according to the activity development business data of the optimal activity marketing plan, wherein the activity development business data includes customer information.

[0163] The target customer group determination device provided by the present application obtains business data within the monitoring period, wherein the business data includes the activity development business data of each marketing activity plan; determines the optimal activity marketing plan in each of the marketing activity plans according to the activity setting data and activity development business data of each marketing activity plan; determines the target customer group of the optimal activity marketing plan according to the activity development business data of the optimal activity marketing plan, wherein the activity development business data includes customer information. In this way, the target customer group of the marketing activity is determined by using computer technology instead of manually determining the target customer group, which greatly improves the efficiency of identifying the target customer group; in addition, in the process of determining the target customer group, instead of identifying the target customer group of all marketing activity plans within the monitoring period, the optimal marketing activity plan is first screened out, and then the target customer group of the optimal marketing activity plan is identified, that is, only a part of the screened data is used to identify the target customer group, so that on the basis of improving the operation effect from the two dimensions of activity plan and customer group screening, the computational complexity of the entire target customer group identification process is greatly reduced, and the matching accuracy is improved. In addition, the marketing conversion rate can also be improved to achieve cost reduction and efficiency improvement. In some embodiments, after determining the target customer group of the optimal activity marketing plan, the method also includes:

[0164] The activity rights and interests of the optimal activity marketing plan are pushed to the client of the target customer group.

[0165] In some embodiments, the first determining module is specifically configured to:

[0166] Generate evaluation index data of each marketing activity plan based on the activity setting data and activity development business data of each marketing activity plan;

[0167] Respectively bundling mutually exclusive evaluation index data in the evaluation index data of each marketing activity plan to reduce the dimension of the evaluation index data, and generating target feature data corresponding to each marketing activity plan;

[0168] According to the target characteristic data corresponding to each marketing activity plan, the optimal activity marketing plan among the marketing activity plans is determined.

[0169] In some embodiments, mutually exclusive feature bundling algorithm is used to bundle mutually exclusive evaluation indicator data in the evaluation indicator data of each marketing activity plan to reduce the dimension of the evaluation indicator data.

[0170] In some embodiments, the apparatus further comprises:

[0171] A grouping module, used for grouping customers according to customer information to obtain at least two groups of customers;

[0172] A splitting module is used to split each group of customers to obtain the execution customers and control customers in each group of customers;

[0173] The push module is used to push the activity rights and interests of each marketing activity plan to the client of the executing customer in sequence during the monitoring period.

[0174] In some embodiments, the second determining module is specifically configured to:

[0175] According to the activity development business data corresponding to each of the executing customers under the optimal activity marketing plan, the consumption increase probability of the executing customers in each group is calculated;

[0176] Calculate the consumption increase probability of the control customers in each group according to the business data of each of the control customers during the implementation of the optimal marketing activity plan;

[0177] The target customer group of the optimal activity marketing program is determined according to the difference between the consumption increase probability of the executing customers and the consumption increase probability of the control customers in each group of customers.

[0178] In some embodiments, the push module is specifically used to:

[0179] During the monitoring period, the activity rights and interests of each marketing activity plan are pushed to the client of the executing customer according to the activity setting data of the marketing activity plan, wherein the activity setting data of each marketing activity plan includes at least one of the following information: activity start time, activity end time, number of rights and interests, denomination, validity period, applicable merchants, and applicable customer groups.

[0180] The embodiment of the device provided in the embodiment of the present application can be specifically used to execute the processing flow of the above-mentioned method embodiment. Its functions are not described in detail here, and reference can be made to the detailed description of the above-mentioned method embodiment.

[0181] It should be noted that the target customer group determination method and device provided in the embodiments of the present application can be used in the financial field, and can also be used in any technical field other than the financial field. The embodiments of the present application do not limit the application field of the target customer group determination method and device.

[0182] Fig.12 A schematic diagram of the physical structure of an electronic device provided in an embodiment of the present application is shown in FIG. Fig.12As shown, the electronic device may include: a processor 301, a communication interface 302, a memory 303 and a communication bus 304, wherein the processor 301, the communication interface 302 and the memory 303 communicate with each other through the communication bus 304. The processor 301 may call the logic instructions in the memory 303 to execute the method described in any of the above embodiments.

[0183] In addition, the logic instructions in the above-mentioned memory 303 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.

[0184] This embodiment discloses a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the methods provided by the above-mentioned method embodiments.

[0185] This embodiment provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program enables the computer to execute the methods provided by the above-mentioned method embodiments.

[0186] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0187] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0188] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0189] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0190] In the description of this specification, the description with reference to the terms "one embodiment", "a specific embodiment", "some embodiments", "for example", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0191] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present application. It should be understood that the above description is only a specific embodiment of the present application and is not intended to limit the scope of protection of the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A method for determining a target customer group, characterized in that: include: Acquire business data within the monitoring period, wherein the business data includes activity development business data of each marketing activity plan; Determine the best marketing plan among the marketing plans according to the activity setting data and activity business data of each marketing plan; The target customer group of the optimal activity marketing plan is determined according to the activity development business data of the optimal activity marketing plan, wherein the activity development business data includes customer information.

2. The method according to claim 1, characterized in that After determining the target customer group of the optimal activity marketing plan, the method further includes: The activity rights and interests of the optimal activity marketing plan are pushed to the client of the target customer group.

3. The method according to claim 1 or 2, characterized in that: Determining the optimal marketing plan among the marketing plan according to the activity setting data and activity development business data of each marketing plan includes: Generate evaluation index data of each marketing activity plan based on the activity setting data and activity development business data of each marketing activity plan; Respectively bundling mutually exclusive evaluation index data in the evaluation index data of each marketing activity plan to reduce the dimension of the evaluation index data, and generating target feature data corresponding to each marketing activity plan; According to the target characteristic data corresponding to each marketing activity plan, the optimal activity marketing plan among the marketing activity plans is determined.

4. The method according to claim 3, characterized in that The mutually exclusive feature bundling algorithm is used to bundle the mutually exclusive evaluation index data in the evaluation index data of each marketing activity plan to reduce the dimension of the evaluation index data.

5. The method according to claim 4, characterized in that The method further comprises: Group customers according to their information to obtain at least two groups of customers; Split each group of customers to obtain the executive customers and control customers in each group; During the monitoring period, the activity rights and interests of each marketing activity plan are pushed to the client of the executing customer in turn.

6. The method according to claim 5, characterized in that Determining the target customer group of the optimal activity marketing plan according to the activity development business data of the optimal activity marketing plan includes: According to the activity development business data corresponding to each of the executing customers under the optimal activity marketing plan, the consumption increase probability of the executing customers in each group is calculated; Calculate the consumption increase probability of the control customers in each group according to the business data of each of the control customers during the implementation of the optimal marketing activity plan; The target customer group of the optimal activity marketing program is determined according to the difference between the consumption increase probability of the executing customers and the consumption increase probability of the control customers in each group of customers.

7. The method according to claim 5, characterized in that During the monitoring period, sequentially pushing the activity rights and interests of each marketing activity plan to the client of the executing customer includes: During the monitoring period, the activity rights and interests of each marketing activity plan are pushed to the client of the executing customer according to the activity setting data of the marketing activity plan, wherein the activity setting data of each marketing activity plan includes at least one of the following information: activity start time, activity end time, number of rights and interests, denomination, validity period, applicable merchants, and applicable customer groups.

8. A device for determining a target customer group, characterized in that: include: An acquisition module, used to acquire business data within a monitoring period, wherein the business data includes activity development business data of each marketing activity plan; A first determination module is used to determine the best activity marketing plan among the marketing activity plans according to the activity setting data and activity development business data of each marketing activity plan; The second determination module is used to determine the target customer group of the optimal activity marketing plan according to the activity development business data of the optimal activity marketing plan, wherein the activity development business data includes customer information.

9. 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 computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A 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 according to any one of claims 1 to 7 are implemented.

Images