Marketing strategy generation method, device and electronic equipment

Abstract

The present application is applicable to the field of marketing strategy technology, and provides a marketing strategy generation method, device and electronic device, the method comprising: obtaining a marketing task, determining a target user of a life cycle corresponding to the marketing task according to the marketing task, extracting life cycle characteristics of the target user, the life cycle characteristics at least including the behavioral characteristics of the target user, matching a target strategy factor according to the life cycle characteristics of the target user, the strategy factors included in the target strategy factor are all different, wherein different strategy factors represent different strategy actions, and combining different strategy factors in the target strategy factor to obtain a marketing strategy for the target user. The present application can improve the accuracy of marketing strategy generation.

Description

Technical Field

[0001] The present application belongs to the technical field of marketing strategies, and in particular, relates to a marketing strategy generation method, device, electronic device and computer-readable storage medium. Background Art

[0002] In intelligent marketing, corresponding marketing objectives and tasks can be divided according to the user's life cycle, and marketing strategies can be constructed for users in the corresponding life cycle through these marketing objectives and tasks.

[0003] At present, although intelligent marketing is mainly based on the user portraits of different users, the specific marketing methods and strategies are generated through the experience and judgment of the operation team, which makes the generated marketing strategies inaccurate and leads to poor marketing results. Summary of the invention

[0004] The embodiments of the present application provide a marketing strategy generation method, device and electronic device, which can improve the accuracy of marketing strategy generation.

[0005] In a first aspect, an embodiment of the present application provides a marketing strategy generation method, comprising:

[0006] Acquire a marketing task, and determine a target user in a life cycle corresponding to the marketing task according to the marketing task;

[0007] Extracting life cycle characteristics of the target user; the life cycle characteristics at least include behavioral characteristics of the target user;

[0008] Matching a target policy factor according to the life cycle characteristics of the target user; the policy factors included in the target policy factor are all different, wherein different policy factors represent different policy actions;

[0009] The marketing strategy for the target user is obtained by combining different strategy factors in the target strategy factor.

[0010] Optionally, before extracting the life cycle feature of the target user, the method further includes:

[0011] A pre-constructed classification network is trained according to a user feature set of historical users to obtain a classification model; the historical users include users with successful marketing and users with failed marketing, and the user feature set of the historical users at least includes behavioral features of the historical users;

[0012] The extracting the life cycle characteristics of the target user includes:

[0013] Extracting user features of the target user and feature weights corresponding to the user features using the classification model;

[0014] A preset number of user features are selected as the life cycle features according to the feature weights.

[0015] Optionally, before matching the target policy factor according to the life cycle characteristics of the target user, the method further includes:

[0016] Constructing a strategy factor library according to the historical marketing strategies corresponding to the historical users; the strategy factor library contains all the marketing actions in the historical marketing strategies;

[0017] Constructing a mapping relationship according to the user feature set of the historical user and the policy factor library; the mapping relationship is used to map the user features in the user feature set to the policy factors in the policy factor library;

[0018] The matching of the target strategy factor according to the life cycle characteristics of the target user includes:

[0019] Based on the mapping relationship, a policy factor that is mapped to the lifecycle feature and is different from the policy factor library is matched as the target policy factor.

[0020] Optionally, after obtaining the classification model, the method further includes:

[0021] The classification model is used to perform a strategy analysis on the target user to obtain a strategy analysis result, wherein the strategy analysis result includes a probability of successful marketing to the target user.

[0022] Optionally, after combining different strategy factors in the target strategy factors to obtain the marketing strategy for the target user, the method further includes:

[0023] Conducting a strategic evaluation of said marketing strategy;

[0024] The marketing strategy is updated using the result of the strategy evaluation to obtain an updated marketing strategy.

[0025] Optionally, the performing a strategy evaluation on the marketing strategy includes:

[0026] Determine the factor weights of different strategic factors in the marketing strategy for the target user; the factor weights represent the importance of the corresponding strategic factors in the marketing strategy;

[0027] The strategy score of the marketing strategy is calculated according to the factor weights, and the strategy score is used to perform a strategy evaluation on the marketing strategy.

[0028] Optionally, the updating the marketing strategy by using the result of the strategy evaluation to obtain an updated marketing strategy includes:

[0029] When the strategy score does not meet the preset score requirement, continuously adjusting the strategy factors in the marketing strategy and calculating the strategy score of the adjusted marketing strategy;

[0030] When the strategy score of the adjusted marketing strategy meets the preset score requirement, the adjusted marketing strategy is used as the updated marketing strategy.

[0031] In a second aspect, an embodiment of the present application provides a marketing strategy generating device, including:

[0032] A task acquisition module, used to acquire marketing tasks and determine target users in a life cycle corresponding to the marketing tasks according to the marketing tasks;

[0033] A feature extraction module, used to extract life cycle features of the target user; the life cycle features at least include behavioral features of the target user;

[0034] A factor matching module, used for matching a target policy factor according to the life cycle characteristics of the target user; the policy factors included in the target policy factor are all different, wherein different policy factors represent different policy actions;

[0035] The strategy generation module is used to combine different strategy factors in the target strategy factors to obtain the marketing strategy for the target user.

[0036] In a third aspect, an embodiment of the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the marketing strategy generation method described in the first aspect when executing the computer program.

[0037] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the marketing strategy generation method described in the first aspect are implemented.

[0038] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on an electronic device, the electronic device executes the marketing strategy generation method described in any one of the first aspects above.

[0039] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0040] This application utilizes the life cycle characteristics of the target user to match the target strategy factor, and obtains the marketing strategy for the target user by combining different strategy factors in the target strategy factor, which can improve the accuracy of the marketing strategy generation. Specifically, the target user of the corresponding life cycle is determined through the marketing task, and the life cycle characteristics of the above target user are extracted, and different strategy factors are matched according to the life cycle characteristics of the above target user. Since the above life cycle characteristics at least include the behavioral characteristics of the target user, it means that different strategy factors can be matched based on user behavior, and the strategy factors correspond to strategy actions, that is, the strategy actions in the marketing strategy obtained by combining strategy factors can correspond to the user behavior of the target user, and the generation of the marketing strategy does not rely on human subjective judgment, so the accuracy of the marketing strategy generation can be improved; at the same time, since the strategy factors included in the target strategy factor are different, the flexibility of the marketing strategy generation can be improved based on the different combinations of strategy factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0042] Figure 1 It is a flowchart of a marketing strategy generation method provided by an embodiment of the present application;

[0043] Figure 2 It is a structural schematic diagram of a marketing strategy generating device provided in an embodiment of the present application;

[0044] Figure 3 is a structural schematic diagram of a marketing strategy generating device provided by another embodiment of the present application;

[0045] Figure 4 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0047] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0048] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0049] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0050] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0051] In intelligent marketing, taking shopping platforms as an example, different users can be divided into different life cycles according to their complete shopping cycle on the shopping platform, including: newcomer period, climbing period, mature period, silent period, etc. Users in different life cycles are generally divided according to their consumption capacity, activity, etc. For example, the consumption capacity and activity of mature users are higher than those of users in other life cycles. The marketing goals of users in different life cycles are obviously different. For example, intelligent marketing is carried out for newcomer period users so that they can quickly transition to the climbing period or mature period; while intelligent marketing is carried out for silent period users to improve their activity so that users can return to the mature period, etc. (i.e. "awaken" silent period users). This means that different marketing strategies are needed for different users in different life cycles. Although marketing can be carried out according to the user portraits of different users in actual marketing, the specific marketing methods and strategies are generated through the experience judgment of the operation team, which is relatively subjective; at the same time, users in the same life cycle will also be different. For example, the low-active high-value group in the mature period and the high-active high-value group in the mature period, the operation team often finds it difficult to make accurate judgments based on experience, which makes the generated marketing strategies inaccurate and leads to poor marketing results.

[0052] In order to improve the accuracy of marketing strategy generation, the present application provides a marketing strategy generation method based on strategy factors.

[0053] Figure 1 A flowchart of a marketing strategy generation method provided by an embodiment of the present application is shown, and the details are as follows:

[0054] S1. Obtain a marketing task, and determine the target user of the corresponding life cycle of the marketing task according to the marketing task.

[0055] In the embodiment of the present application, the above-mentioned marketing tasks refer to tasks used to construct different marketing goals, and the above-mentioned marketing goals include one or more of new user acquisition goals, activation goals, awakening goals, etc., wherein the above-mentioned new user acquisition goals are used to acquire more new users; the above-mentioned activation goals are used to increase the activity of low-active users; and the above-mentioned awakening goals are used to awaken users in the dormant period. Corresponding to different marketing goals, the above-mentioned marketing tasks can be new user acquisition target tasks, activation target tasks, and awakening target tasks, and the target users of the corresponding life cycle can be accurately acquired through the above-mentioned marketing tasks.

[0056] In some embodiments, assuming that in the field of supermarkets or shopping platforms, the above-mentioned new customer acquisition target tasks, activation target tasks, and awakening target tasks can select a certain number of users from the corresponding life cycle as target users; or, in order to improve the accuracy of the determined target users, target users can be found through clustering and the like. For example, for mature users, clustering can be used to obtain groups of people with different levels of activity (such as group A, group B, etc.), and the low-activity groups are selected from them as target users.

[0057] S2. Extracting life cycle characteristics of the target user; the life cycle characteristics at least include behavioral characteristics of the target user.

[0058] In the embodiment of the present application, the above life cycle features can be extracted based on the user features generated by the shopping behavior of the above target user during the entire shopping cycle, such as all user features of the target user after registering on the shopping platform APP, including behavioral features (such as the number of clicks, etc.), product features (such as product name, etc.), order features (such as order volume, etc.), coupon features (such as consumption coupon type), user interaction features (such as user interaction through APP), reach features (such as the number of reaches), etc. At the same time, when the user is shopping, the behavioral features generated by the user's shopping behavior can best reflect the user's product preferences and shopping tendencies. Therefore, by at least selecting the behavioral features of the target user as the life cycle features, the real shopping information of the target user during the entire shopping cycle can be better reflected.

[0059] In some embodiments, the above-mentioned life cycle characteristics may include behavioral characteristics, and one or more of product characteristics, order characteristics, reach characteristics, etc.

[0060] S3. Matching target policy factors according to the life cycle characteristics of the target user; the policy factors included in the target policy factors are all different, wherein different policy factors represent different policy actions.

[0061] In an embodiment of the present application, the above-mentioned target policy factors are candidate policy factors matched according to the life cycle characteristics of the target user, including different policy factors, wherein different policy factors represent different types of policy actions. For example, the types of the above-mentioned policy factors may include: discount factors (such as first-order discounts), preferential factors (such as issuing new coupons), contact channel factors (such as APP push, SMS push, etc.) and contact content factors (such as product recommendations, coupon push, etc.). By matching different policy factors with the life cycle characteristics of the target user, the diversity of the matched policy actions can be improved.

[0062] S4. Combining different strategy factors in the above target strategy factors to obtain the marketing strategy for the above target users.

[0063] In the embodiment of the present application, different strategy factors in the combined target strategy factors refer to combining a specified number of strategy factors in a preset combination order. Since the order and number of strategy actions in the marketing strategy will affect the marketing effect, more diverse and accurate marketing strategies can be obtained by combining different strategy factors.

[0064] This application utilizes the life cycle characteristics of the target user to match the target strategy factor, and obtains the marketing strategy for the target user by combining different strategy factors in the target strategy factor, which can improve the accuracy of the marketing strategy generation. Specifically, the target user of the corresponding life cycle is determined through the marketing task, and the life cycle characteristics of the above target user are extracted, and different strategy factors are matched according to the life cycle characteristics of the above target user. Since the above life cycle characteristics at least include the behavioral characteristics of the target user, it means that different strategy factors can be matched based on user behavior, and the strategy factors correspond to strategy actions, that is, the strategy actions in the marketing strategy obtained by combining strategy factors can correspond to the user behavior of the target user, and the generation of the marketing strategy does not rely on human subjective judgment, so the accuracy of the marketing strategy generation can be improved; at the same time, since the strategy factors included in the target strategy factor are different, the flexibility of the marketing strategy generation can be improved based on the different combinations of strategy factors.

[0065] In another optional embodiment of the present application, before extracting the life cycle characteristics of the target user, the method further includes:

[0066] A pre-constructed classification network is trained according to a user feature set of historical users to obtain a classification model; the historical users include users with successful marketing and users with failed marketing, and the user feature set of the historical users at least includes the behavioral features of the historical users.

[0067] In some embodiments, the above-mentioned historical users refer to users who have been marketed using marketing actions, including users with successful marketing and users with failed marketing. The above-mentioned classification model is used to classify different user characteristics of users, and corresponds to the above-mentioned marketing tasks. For example, the classification model corresponding to the activation target task is the activation model. Assuming that the marketing task is the activation target task, the above-mentioned classification model is the activation model. When training the activation model, for inactive users who have been marketed using marketing actions in history, if they become active users after a certain observation time point, they are users with successful marketing; if they do not become active users after a certain observation time point, they are users with failed marketing. The user characteristics of users with successful marketing are used as positive samples, and the user characteristics of users with failed marketing are used as negative samples. The corresponding activation model is obtained by training with positive and negative samples.

[0068] In some embodiments, the above-mentioned classification model can be one of a logistic regression model (LR), a support vector machine model (SVM), a random forest model (RF) and an extreme gradient boosting model (XGBoost).

[0069] Correspondingly, the above-mentioned extraction of the life cycle characteristics of the above-mentioned target user includes:

[0070] Extracting user features of the target user and feature weights corresponding to the user features using the classification model;

[0071] A preset number of user features are selected as the life cycle features according to the feature weights.

[0072] In some embodiments, since the above-mentioned classification model is trained based on users with successful marketing and users with failed marketing, the above-mentioned classification model can output user characteristics of target users according to the importance of marketing success, wherein the above-mentioned importance is positively correlated with the above-mentioned feature weight, and then selecting a preset number of user characteristics as life cycle characteristics through feature weights can more accurately find characteristics related to marketing success.

[0073] In some embodiments, for example, user features output by the activation model and the corresponding feature weights include: recent click count (100), order volume (90), reach channel (80), reach time (60), etc., where X in (X) is the corresponding feature weight. If the life cycle features are selected according to the feature weight being greater than 70, the selected life cycle features include recent click count, order volume, and reach channel.

[0074] In another optional embodiment of the present application, before matching the target policy factor according to the life cycle characteristics of the target user, the following method is further included:

[0075] Building a strategy factor library according to the historical marketing strategies corresponding to the above historical users; the above strategy factor library contains all the marketing actions in the above historical marketing strategies;

[0076] A mapping relationship is constructed based on the user feature set of the above historical users and the above policy factor library; the above mapping relationship is used to map the user features in the above user feature set to the policy factors in the above policy factor library.

[0077] In some embodiments, the above-mentioned strategy factor library includes all strategy actions in the historical marketing strategies used for historical users within a preset time, and the above-mentioned strategy actions are used as corresponding strategy factors. The above-mentioned mapping relationship reflects the corresponding relationship between user characteristics and strategy factors, and the corresponding relationship includes one-to-one correspondence and many-to-one correspondence, that is, a user characteristic can correspond to one strategy factor or to multiple strategy factors.

[0078] In an optional embodiment of the present application, for the above-mentioned mapping relationship, the user characteristics can be taken as the result and the strategy factors can be taken as the cause, and a mapping relationship can be constructed for the user characteristics and strategy factors that are established from the cause to the result relationship. For different user characteristics, mapping can be performed according to different methods. For business common sense categories, including: touch time characteristics, click behavior characteristics, etc., the following causal relationship can be obtained: touch time characteristics <-- the number of times the consumer coupons are touched <-- the consumer coupon push, the number of times the consumer coupons are touched <-- the consumer coupon push, the number of APP clicks <-- SMS reminders / product recommendations, that is, "touch time characteristics" can be mapped with "consumer coupon push", "the number of times the consumer coupons are touched" can be mapped with "consumer coupon push", and "APP clicks" can be mapped with "SMS reminders / product recommendations"; for the association analysis category, the following causal relationship can be obtained: order volume <--product discount strength / points gift strength, etc., that is, "order characteristics" can be mapped with "product discount factors"; for the association analysis category, the following causal relationship can be obtained: the number of repurchases <---repurchase product recommendations, thereby constructing the corresponding mapping relationship.

[0079] Correspondingly, the target strategy factors are matched according to the life cycle characteristics of the target user, including:

[0080] Based on the above mapping relationship, a different strategy factor that is mapped to the above life cycle characteristics is matched from the above strategy factor library as the above target strategy factor.

[0081] In some embodiments, by utilizing the above mapping relationship, at least two different policy factors mapped to the lifecycle characteristics are matched from the policy factor library, so as to obtain a policy action that better matches the target user.

[0082] In another optional embodiment of the present application, after obtaining the classification model, the method further includes:

[0083] The classification model is used to perform a strategy analysis on the target users to obtain a strategy analysis result, wherein the strategy analysis result includes a probability of successful marketing to the target users.

[0084] In other embodiments, since the above-mentioned classification model is trained based on users with successful marketing and users with unsuccessful marketing, the above-mentioned classification model can be used to obtain strategic analysis results of target users, including the probability of successful marketing of target users. By performing strategic analysis on target users based on the probability of successful marketing of target users, marketing can be abandoned for target users with lower probabilities, thereby reducing the waste of marketing resources.

[0085] In another optional embodiment of the present application, after combining different strategy factors in the target strategy factors to obtain the marketing strategy for the target user, the following steps are further included:

[0086] Conduct strategic evaluation of the above marketing strategies;

[0087] The above marketing strategy is updated using the result of the above strategy evaluation to obtain an updated marketing strategy.

[0088] In some embodiments, since different strategic factors combined in a marketing strategy will produce different marketing effects, the marketing strategy can be continuously optimized and the marketing effect can be improved by performing a strategic evaluation on the marketing strategy and updating the marketing strategy using the results of the strategic evaluation.

[0089] In the embodiment of the present application, the above-mentioned strategic evaluation of the above-mentioned marketing strategy includes:

[0090] Determine the factor weights of different strategic factors in the above marketing strategy to the above target users; the above factor weights represent the importance of the corresponding strategic factors in the above marketing strategy;

[0091] The strategy score of the above marketing strategy is calculated according to the above factor weights, and the above marketing strategy is evaluated using the above strategy score.

[0092] In some embodiments, by quantifying the importance of different strategy factors in the marketing strategy, that is, obtaining the factor weights of different strategy factors to the target user, the marketing strategy can be better evaluated through the calculated strategy score.

[0093] In an optional embodiment of the present application, the factor weights of different strategic factors in the marketing strategy for the above-mentioned target users can be determined based on the strategic model. The above-mentioned strategic model can be a linear model, which is used to obtain the importance of each strategic factor in the marketing strategy. For example, the strategic model is trained by taking users who use all target strategic factors and have successful marketing as positive samples, and other users who use part of the target strategic factors and have successful marketing as negative samples. At the same time, a corresponding factor model is established for each type of strategic factor in the above-mentioned marketing strategy, and the factor model is used to predict the target user's feedback prediction value for a single strategic factor. For example, for the reach channel factor, including: APP reminders, SMS reminders, etc., the factor model is used to predict the target population's feedback probability for different reach channel factors, and the highest probability is taken for each person, and then the average or median is taken as the target user's feedback prediction value for the reach channel factor. The training method of the above-mentioned factor model is similar to that of the classification model, which will not be repeated here.

[0094] In an optional embodiment of the present application, the strategy score can be calculated by the following formula:

[0095] Strategy score = ∑(feedback prediction value of strategy factor * factor weight of strategy factor)

[0096] In another optional embodiment of the present application, different target strategy factors can be further screened through the above-mentioned factor model, that is, the matched target strategy factors are subjected to strategy analysis through the above-mentioned factor model to obtain the target user's feedback prediction value for a single strategy factor, thereby screening out the best strategy factor combination, thereby improving the accuracy of marketing strategy generation.

[0097] In the embodiment of the present application, the above-mentioned marketing strategy is updated using the result of the above-mentioned strategy evaluation to obtain the updated marketing strategy, including:

[0098] When the above strategy score does not meet the preset score requirement, continuously adjust the strategy factors in the above marketing strategy and calculate the strategy score of the adjusted marketing strategy;

[0099] Until the strategy score of the adjusted marketing strategy meets the preset score requirement, the adjusted marketing strategy is used as the updated marketing strategy.

[0100] In some embodiments, when the strategy score does not meet the preset score requirement, the strategy factors in the marketing strategy can be continuously adjusted (e.g., increased, decreased, etc.) and the strategy score of the adjusted marketing strategy can be recalculated until a marketing strategy whose strategy score meets the preset score requirement is found. Through strategy evaluation, the marketing strategy can be continuously updated to achieve iterative updates of the marketing strategy, thereby obtaining an optimized marketing strategy and improving the accuracy of the marketing strategy. At the same time, for marketing strategies with similar marketing effects (such as similar strategy scores), operators can manually intervene to select the most appropriate marketing strategy based on the factor weight of each strategy factor, taking into account the operating cost and operating difficulty, thereby achieving effective precipitation of the marketing strategy.

[0101] In some other embodiments of the present application, after obtaining the updated marketing strategy as described above, the following is further included:

[0102] The updated marketing strategy is used to perform strategy iteration.

[0103] In some embodiments, when an updated marketing strategy is obtained, the automatic update of the marketing strategy can be achieved through automatic iteration. For example, for a target user, the current marketing strategy is marketing strategy 1, and the new marketing strategy is marketing strategy 2. Automatic iteration can be performed through online ab test control, that is, the target users are divided into two groups, and marketing is performed using marketing strategy 1 and marketing strategy 2 respectively. When the marketing effect of marketing strategy 2 is higher than that of marketing strategy 1, marketing strategy 1 is updated to marketing strategy 2.

[0104] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0105] Corresponding to the marketing strategy generation method described in the above embodiment, Figure 2 A schematic diagram of the structure of a marketing strategy generating device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0106] Reference Figure 2 The device may be a marketing strategy generating device 21 , and the marketing strategy generating device 21 may include a task acquiring module 211 , a feature extracting module 212 , a factor matching module 213 and a strategy generating module 214 .

[0107] Reference Figure 2 , the marketing strategy generating device 21 comprises:

[0108] The task acquisition module 211 is used to acquire a marketing task and determine a target user of a life cycle corresponding to the marketing task according to the marketing task;

[0109] The feature extraction module 212 is used to extract the life cycle features of the target user; the life cycle features at least include the behavior features of the target user;

[0110] The factor matching module 213 is used to match the target policy factor according to the life cycle characteristics of the target user; the policy factors included in the target policy factor are all different, wherein different policy factors represent different policy actions;

[0111] The strategy generation module 214 is used to combine different strategy factors in the target strategy factors to obtain the marketing strategy for the target user.

[0112] In some other embodiments, the marketing strategy generating device 21 further includes a model training module, and the model training module is used to extract the life cycle characteristics of the target user, including:

[0113] A pre-constructed classification network is trained according to a user feature set of historical users to obtain a classification model; the historical users include users with successful marketing and users with failed marketing, and the user feature set of the historical users at least includes behavioral features of the historical users;

[0114] The extracting the life cycle characteristics of the target user includes:

[0115] Extracting user features of the target user and feature weights corresponding to the user features using the classification model;

[0116] A preset number of user features are selected as the life cycle features according to the feature weights.

[0117] In some other embodiments, the marketing strategy generating device 21 further includes a strategy factor library building module, and the strategy factor library building module is used to match the target strategy factor according to the life cycle characteristics of the target user, and further includes:

[0118] Constructing a strategy factor library according to the historical marketing strategies corresponding to the historical users; the strategy factor library contains all the marketing actions in the historical marketing strategies;

[0119] Constructing a mapping relationship according to the user feature set of the historical user and the policy factor library; the mapping relationship is used to map the user features in the user feature set to the policy factors in the policy factor library;

[0120] The matching of the target strategy factor according to the life cycle characteristics of the target user includes:

[0121] Based on the mapping relationship, a policy factor that is mapped to the lifecycle feature and is different from the policy factor library is matched as the target policy factor.

[0122] In some other embodiments, the marketing strategy generating device 21 further includes a strategy analysis module, and the strategy analysis module is used to, after obtaining the classification model, include:

[0123] The classification model is used to perform a strategy analysis on the target user to obtain a strategy analysis result, wherein the strategy analysis result includes a probability of successful marketing to the target user.

[0124] In other embodiments, Figure 3 The schematic diagram of the structure of the marketing strategy generating device 31 provided in the embodiment of the present application is shown. Figure 3 As shown, the marketing strategy generating device 31 may include a task acquiring module 311 , a feature extracting module 312 , a factor matching module 313 and a strategy generating module 314 .

[0125] In some embodiments, the marketing strategy generating device 31 further includes a strategy evaluation module 315, and the strategy evaluation module 315 is used to combine different strategy factors in the target strategy factor to obtain the marketing strategy of the target user, including:

[0126] Conducting a strategic evaluation of said marketing strategy;

[0127] The marketing strategy is updated using the result of the strategy evaluation to obtain an updated marketing strategy.

[0128] In some embodiments, the strategy evaluation module performs strategy evaluation on the marketing strategy through the following steps, including:

[0129] Determine the factor weights of different strategic factors in the marketing strategy for the target user; the factor weights represent the importance of the corresponding strategic factors in the marketing strategy;

[0130] The strategy score of the marketing strategy is calculated according to the factor weights, and the strategy score is used to perform a strategy evaluation on the marketing strategy.

[0131] In some embodiments, the strategy evaluation module updates the marketing strategy using the strategy evaluation result through the following steps to obtain an updated marketing strategy, including:

[0132] When the strategy score does not meet the preset score requirement, continuously adjusting the strategy factors in the marketing strategy and calculating the strategy score of the adjusted marketing strategy;

[0133] When the strategy score of the adjusted marketing strategy meets the preset score requirement, the adjusted marketing strategy is used as the updated marketing strategy.

[0134] In some embodiments, the marketing strategy generating device 31 further includes an iteration module 316. The iteration module 316 is used for, after obtaining the updated marketing strategy, including:

[0135] The updated marketing strategy is used to perform strategy iteration.

[0136] It should be noted that the information interaction, execution process, etc. between the devices / units are based on the same concept as the method embodiments of the present application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0137] Figure 4 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 4 As shown, the electronic device 4 of this embodiment includes: at least one processor 40 ( Figure 4 The at least one processor 40 includes a memory 41 and a computer program 42 stored in the memory 41 and executable on the at least one processor 40. When the processor 40 executes the computer program 42, the steps in any of the method embodiments are implemented.

[0138] The electronic device 4 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will appreciate that Figure 4 It is only an example of the electronic device 4 and does not constitute a limitation of the electronic device 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include an input sending device, a network access device, a bus, etc.

[0139] The processor 40 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0140] In some embodiments, the memory 41 may be an internal storage unit of the electronic device 4, such as a hard disk or memory of the electronic device 4. The memory 41 may also be an external storage device of the electronic device 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 4. Further, the memory 41 may also include both an internal storage unit of the electronic device 4 and an external storage device. The memory 41 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory 41 may also be used to temporarily store data that has been sent or is to be sent.

[0141] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the functional units and modules is used as an example. In practical applications, the function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0142] An embodiment of the present application also provides a network device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps in any of the method embodiments when executing the computer program.

[0143] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the various method embodiments can be implemented.

[0144] An embodiment of the present application provides a computer program product. When the computer program product runs on an electronic device, the electronic device can implement the steps in the various method embodiments when executing the computer program product.

[0145] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the process in the embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the camera / electronic device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0146] In the embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0147] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0148] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0149] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0150] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such 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 application, and should all be included in the protection scope of the present application.

Claims

1. A marketing strategy generation method, characterized in that: include: Acquire a marketing task, and determine a target user in a life cycle corresponding to the marketing task according to the marketing task; Extracting user features of the target user and feature weights corresponding to the user features by using a classification model, and selecting a preset number of user features as the life cycle features according to the feature weights; the life cycle features at least include behavioral features of the target user; The classification model is trained based on a feature set of historical users; According to the life cycle characteristics of the target user, a target policy factor is matched from a pre-built policy factor library; the policy factor library includes a mapping relationship between user characteristics of historical users and policy factors, and the mapping relationship is used to reflect a causal relationship with the user characteristics as the result and the policy factor as the cause. The policy factors included in the target policy factor are all different, wherein different policy factors represent different policy actions; the types of the policy factors include: discount factor, preferential factor, reach channel factor, and reach content factor; Determine the feedback prediction value of the target user to the strategy factors included in the target strategy factors, combine different strategy factors in the target strategy factors according to the feedback prediction value, and obtain the marketing strategy of the target user.

2. The marketing strategy generation method according to claim 1, characterized in that: Before extracting the user features of the target user and the feature weights corresponding to the user features by using the classification model, the method further includes: The classification model is obtained by training a pre-constructed classification network according to a user feature set of historical users; the historical users include users with successful marketing and users with failed marketing, and the user feature set of historical users includes at least behavioral features of the historical users.

3. The marketing strategy generation method according to claim 2, characterized in that: Before matching the target policy factor from the pre-built policy factor library according to the life cycle characteristics of the target user, the method further includes: The strategy factor library is constructed according to the historical marketing strategies corresponding to the historical users; the strategy factor library contains all the marketing actions in the historical marketing strategies; Taking the user features in the user feature set of the historical users as the effect and the policy factors in the policy factor library as the cause, constructing the mapping relationship between the policy factors and the user features that establish a cause-to-effect relationship; the mapping relationship is used to map the user features in the user feature set to the policy factors in the policy factor library; The matching of the target policy factor from a pre-built policy factor library according to the life cycle characteristics of the target user includes: Based on the mapping relationship, a policy factor that is mapped to the lifecycle feature and is different from the policy factor library is matched as the target policy factor.

4. The marketing strategy generation method according to claim 2, characterized in that: After obtaining the classification model, the method further includes: The classification model is used to perform a strategy analysis on the target user to obtain a strategy analysis result, wherein the strategy analysis result includes a probability of successful marketing to the target user.

5. The marketing strategy generation method according to any one of claims 1 to 4, characterized in that: After determining the feedback prediction value of the target user to the strategy factor included in the target strategy factor, and combining different strategy factors in the target strategy factor according to the feedback prediction value to obtain the marketing strategy of the target user, the method further includes: Conducting a strategic evaluation of said marketing strategy; The marketing strategy is updated using the result of the strategy evaluation to obtain an updated marketing strategy.

6. The marketing strategy generation method according to claim 5, characterized in that: The strategic evaluation of the marketing strategy includes: Determine the factor weights of different strategic factors in the marketing strategy for the target user; the factor weights represent the importance of the corresponding strategic factors in the marketing strategy; The strategy score of the marketing strategy is calculated according to the factor weights, and the strategy score is used to perform a strategy evaluation on the marketing strategy.

7. The marketing strategy generation method according to claim 6, characterized in that: The step of updating the marketing strategy using the result of the strategy evaluation to obtain an updated marketing strategy includes: When the strategy score does not meet the preset score requirement, continuously adjusting the strategy factors in the marketing strategy and calculating the strategy score of the adjusted marketing strategy; When the strategy score of the adjusted marketing strategy meets the preset score requirement, the adjusted marketing strategy is used as the updated marketing strategy.

8. A marketing strategy generating device, characterized in that: include: A task acquisition module, used to acquire marketing tasks and determine target users in a life cycle corresponding to the marketing tasks according to the marketing tasks; A feature extraction module, used to extract user features of the target user and feature weights corresponding to the user features by using a classification model, and select a preset number of user features as the life cycle features according to the feature weights; the life cycle features at least include behavioral features of the target user; The classification model is trained based on a feature set of historical users; A factor matching module, used for matching target policy factors from a pre-built policy factor library according to the life cycle characteristics of the target user; the policy factor library includes a mapping relationship between user characteristics of historical users and policy factors, the mapping relationship is used to reflect the causal relationship with the user characteristics as the effect and the policy factors as the cause, the policy factors included in the target policy factors are all different, wherein different policy factors represent different policy actions; the types of policy factors include: discount factor, discount factor, reach channel factor and reach content factor; The strategy generation module is used to determine the feedback prediction value of the target user to the strategy factors included in the target strategy factors, and combine different strategy factors in the target strategy factors according to the feedback prediction value to obtain the marketing strategy for the target user.

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 method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images