Marketing campaign generation method and apparatus, computer readable storage medium, computer program product, and terminal device

Abstract

The application provides a marketing activity generation method and device, a computer readable storage medium, a computer program product and a terminal device. The marketing activity generation method comprises the following steps: obtaining user demand information, wherein the user demand information is used for indicating at least a target activity type; determining a target activity template matched with the target activity type in historical activity data, wherein the target activity template comprises a plurality of process nodes; analyzing first activity data consistent with the target activity type in the historical activity data, and generating target content of the plurality of process nodes in combination with an analysis result and the user demand information; and filling the target content of the plurality of process nodes into the plurality of process nodes to generate a target marketing activity. The application provides a scheme capable of improving the generation efficiency of the marketing activity.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, and particularly relates to a marketing activity generation method and device, a computer readable storage medium, a computer program product and a terminal device. BACKGROUND

[0002] Marketing activity configuration refers to a process of designing and setting specific marketing activity processes, content, channels and execution plans according to the marketing goals and strategies of an enterprise. It is a key link for the success of marketing activities, ensuring that the activities can accurately reach target customers and achieve the expected effect. Specifically, it can include the following steps: (1) defining activity goals; (2) defining target audiences; (3) selecting marketing channels; (4) designing activity content; (5) setting activity processes; (6) configuring automation tools; (7) testing and optimization; (8) execution and monitoring. Among them, in step (6), the marketing automation tool (such as a customer relationship management (CRM) system) can be used to configure the activity: setting trigger conditions and workflows, automatically sending emails, SMS or push notifications, tracking customer behavior and activity effects.

[0003] However, the current marketing activity configuration process is tedious and inefficient. When configuring marketing activities, users usually need to manually select and input a large amount of information, and existing systems lack automated recommendation and optimization mechanisms. This makes users need to spend a lot of time to determine configuration details, and it is easy to miss some key steps or make configuration errors. SUMMARY

[0004] The present application provides a scheme capable of improving the efficiency of marketing activity generation.

[0005] In order to achieve the above purpose, the present application provides the following technical scheme:

[0006] In a first aspect, a marketing activity generation method is provided, which is applied to a terminal device, or a chip in the terminal device, or a chip module. The marketing activity generation method comprises: obtaining user demand information, the user demand information being used to indicate at least a target activity type; determining a target activity template matched with the target activity type in historical activity data, the target activity template comprising a plurality of process nodes; analyzing first activity data consistent with the target activity type in the historical activity data, and generating target content of the plurality of process nodes in combination with an analysis result and the user demand information; filling the target content of the plurality of process nodes into the plurality of process nodes, and generating a target marketing activity.

[0007] Optionally, the analyzing the first activity data in the historical activity data consistent with the target activity type comprises: analyzing the first activity data to determine a historical evaluation index of each historical content for each process node; determining a historical content with a value of the historical evaluation index higher than a first threshold as a candidate historical content; and determining the target content of each process node according to at least the candidate historical content of each process node.

[0008] Optionally, the determining the target content of each process node according to at least the candidate historical content of each process node comprises: in response to a number of the candidate historical contents of at least one process node being multiple, determining a historical configuration preference of a user for the at least one process node in the historical activity data; and determining a candidate historical content matching the historical configuration preference of the at least one process node as the target content of the at least one process node.

[0009] Optionally, the determining the target content of each process node according to at least the candidate historical content of each process node comprises: in response to a number of the candidate historical contents of at least one process node being multiple, determining a business rule of the at least one process node; and determining a candidate historical content satisfying the business rule of the at least one process node as the target content of the at least one process node.

[0010] Optionally, the analyzing the first activity data in the historical activity data consistent with the target activity type comprises: mining a historical configuration combination for at least two process nodes in the first activity data as historical content of the at least two process nodes, the historical configuration combination having a support degree greater than a first threshold; calculating an evaluation index value of a historical marketing activity including the historical configuration combination; and determining the target content of the at least two process nodes according to a historical configuration combination in a historical marketing activity with an evaluation index value higher than a preset threshold.

[0011] Optionally, the determining the target activity template matching the target activity type in the historical activity data comprises: clustering the historical activity data according to a target configuration feature to obtain a plurality of historical activity clusters; determining a target activity cluster matching the target activity type in the historical activity clusters; selecting a target activity with a first evaluation index greater than a second threshold in the target activity cluster, the first evaluation index being used to measure an execution result of the target activity; and generating the target activity template based on the target activity.

[0012] Optionally, the marketing activity generation method further comprises: in response to receiving the configuration behavior data of the user, adjusting the content of one or more process nodes according to the configuration behavior data to determine the adjusted content of the one or more process nodes; analyzing a first historical evaluation index value of the adjusted content of each process node in the one or more process nodes and a second evaluation index value of each historical content of each process node according to the historical activity data; selecting a target historical content with a second evaluation index value higher than the first historical evaluation index value from each historical content of each process node, and pushing the target historical content to the user as an optimization suggestion.

[0013] Optionally, the user demand information comprises a screening condition of a target user, and the plurality of process nodes comprises a target user node; and the filling of the target content of the plurality of process nodes into the plurality of process nodes comprises filling the screening condition of the target user into the target user node.

[0014] In a second aspect, the application further discloses a marketing activity generation device, which comprises: an acquisition module configured to acquire user demand information, the user demand information being used to indicate at least a target activity type; a target activity template determination module configured to determine a target activity template matching the target activity type in historical activity data, the target activity template comprising a plurality of process nodes; an analysis module configured to analyze first activity data consistent with the target activity type in the historical activity data, and generate target content of the plurality of process nodes in combination with an analysis result and the user demand information; and a marketing activity generation module configured to fill the target content of the plurality of process nodes into the plurality of process nodes to generate a target marketing activity.

[0015] In a third aspect, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program, and the computer program is run by a processor to execute the method provided in the first aspect.

[0016] In a fourth aspect, a marketing activity generation device is provided, and the marketing activity generation device comprises a storage module and a processor, and the storage module stores a computer program capable of being run on the processor, and the processor runs the computer program to execute the method provided in the first aspect.

[0017] In a fifth aspect, a computer program product is provided, and the computer program product stores a computer program, and the computer program is run by a processor to execute the method provided in the first aspect.

[0018] In a sixth aspect, an embodiment of the application further provides a chip, and the chip stores a computer program, and when the computer program is executed by the chip, the steps of the above method are implemented.

[0019] In the seventh aspect, an embodiment of the present application also provides a system chip for use in a terminal, wherein the system chip includes at least one processor and an interface circuit, wherein the interface circuit and the at least one processor are interconnected through lines, and the at least one processor is used to execute instructions to execute a method of the first aspect.

[0020] Compared with the existing technology, the technical solution of this application has the following beneficial effects:

[0021] The technical solution of this application automatically generates target marketing activities by deeply mining historical activity data to determine the target activity template that matches the target activity type, as well as the target content of multiple process nodes in the target activity template. On the one hand, it can ensure the comprehensiveness and accuracy of marketing activity generation, avoiding the omission of key nodes or configuration errors; on the other hand, it simplifies the user's operation process, eliminating the need for users to manually select, enter large amounts of information, and determine configuration details, thereby improving the efficiency of marketing activity generation and reducing operational complexity. In addition, historical activity data also includes the execution results of historical marketing activities, which can provide a reference for generating marketing activities and further optimize marketing activities.

[0022] Furthermore, the technical solution of the present application can also determine the target historical content with higher evaluation index values ​​based on the user's adjustment content for one or more process nodes, combined with the first historical evaluation index value of the adjustment content analyzed by historical activity data, and the second evaluation index value of each historical content of each process node, and recommend it to the user to achieve optimization of one or more process nodes and further improve the execution effect of the marketing process. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flowchart of a marketing activity generation method provided by an embodiment of the present application;

[0024] Figure 2 This is a flowchart of another marketing campaign generation method provided by an embodiment of the present application;

[0025] Figure 3 This is a flowchart of another marketing activity generation method provided by an embodiment of the present application;

[0026] Figure 4 This is a schematic diagram of a marketing activity provided by an embodiment of the present application;

[0027] Figure 5 This is a structural diagram of another marketing activity generating device provided in an embodiment of the present application;

[0028] Figure 6 This is a hardware structure diagram of a marketing activity generation device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] As described in the background, the current configuration process of marketing activities is tedious and inefficient. When configuring a marketing activity, a user usually needs to manually select and input a large amount of information, and the existing system lacks automated recommendation and optimization mechanisms. This makes the user need to spend a lot of time to determine the configuration details, and it is easy to miss some key steps or configuration errors.

[0030] The technical scheme of the present application determines a target activity template matched with the target activity type and target content of multiple process nodes in the target activity template by deep mining of historical activity data, and automatically generates a target marketing activity. On the one hand, it can ensure the comprehensiveness and accuracy of the marketing activity generation, avoid missing key nodes or configuration errors; on the other hand, it simplifies the user's operation process, without the need for the user to manually select, input a large amount of information and determine the configuration details, thereby improving the generation efficiency of the marketing activity and reducing the operation complexity. In addition, the historical activity data also includes the execution effect of the historical marketing activity, which can provide a reference for generating the marketing activity and further optimize the marketing activity.

[0031] The process node referred to in the embodiments of the present application represents a phased target or action in a marketing activity, usually corresponding to a specific task or decision point, and multiple process nodes can be combined to form a complete marketing process.

[0032] Exemplarily, the process nodes of a live broadcast goods selling activity include: product selection → script planning → pre-warming promotion → live broadcast execution → data review → after-sales follow-up.

[0033] The historical activity data referred to in the embodiments of the present application refers to the related data of completed marketing activities, which can specifically include data of at least one dimension: activity configuration data, user behavior data, execution result data, external environment data.

[0034] The activity configuration data can include activity basic information, budget allocation method, theme and content, template information, and screening conditions (rules or parameters for targeting target users in the marketing activity). Specifically, the activity basic information can include identification (such as number), name, type (such as promotion activity, increase new user, user recall, new product promotion, member exclusive, holiday marketing (such as National Day, Spring Festival), etc.), creation time, and person in charge. The budget allocation method can include advertising investment, coupon cost, etc. The theme and content include activity copy (such as title (limited time purchase, exclusive debut), body), visual material (such as Banner picture, video link). The template information includes template identification (such as email template, SMS template). The screening conditions can specifically include: user attributes (such as age, gender, region, occupation, purchase frequency, average transaction value, time of last consumption, etc.), behavior trigger conditions (such as adding shopping cart without payment, browsing a specific product page more than three times, not logging in for the past 30 days, etc.), grouping rules (such as custom tags: “user group 1”, “user group 2”, etc., machine learning grouping: dividing user groups through clustering algorithm, etc.).

[0035] The user behavior data includes participation behavior and conversion path data. Specifically, the participation behavior includes activity page access volume, click rate, dwell time, bounce rate, coupon quantity, usage rate, and cancellation time. The conversion path data includes: full-link conversion rate from activity exposure to click to purchase; response differences of users in different channels (such as email, application program push, SMS).

[0036] The execution result data represents the actual effect data of the historical marketing activity. The execution result data includes evaluation indicators, abnormal records, and user feedback. The evaluation indicators are used to evaluate the effect of the marketing activity, or to evaluate the effect of the node content. The abnormal records specifically include: configuration errors (such as rule conflicts, budget overruns), technical failures (such as push failures, page loading timeouts); the user feedback specifically includes: direct feedback and indirect feedback. The direct feedback includes questionnaire survey scores, complaints or suggestions in customer service tickets; the indirect feedback can include social media comment sentiment analysis (such as negative keyword proportion).

[0037] The external environment data includes time factors and market competition data. The time factors can specifically include activity period (such as holiday, weekday), push time period (such as 9 am, late night). The market competition data includes contemporaneous competitor activity type, contemporaneous competitor promotion intensity (such as obtained through crawler or third-party data platform).

[0038] The configuration behavior data referred to in the embodiments of this application refers to the operational steps and decisions taken by users during the configuration of marketing activities. Specifically, it may include at least one of the following categories of data: basic activity settings, target user screening conditions, content design and channel selection, rule verification and advanced settings.

[0039] Among them, the basic settings of the activity can specifically include the activity type, such as promotion (discounts), adding new users (new user gift packages), recall (activation of dormant users), etc.; activity time planning, used to set the start and end time of the marketing activity, and the push time window (such as the email sending period); budget allocation, used to define the total budget and detailed costs (such as advertising fees, coupon amounts, and channel delivery ratios).

[0040] The filter conditions are rules or parameters used to locate target users in marketing activities.

[0041] Among them, content design and channel selection include copy design, such as title, body, and call to action (CTA) copy; personalized content, such as dynamically inserting "Dear {user name}" based on the user name; visual material configuration, such as banner images, videos, and landing page design.

[0042] Among them, rule verification and advanced settings can specifically include discount rules, such as discount intensity, discount gradient, and coupon validity period; superposition restrictions, such as "cannot be used with other discounts"; risk control can specifically include: budget warning: setting budget consumption thresholds (such as triggering reminders when reaching 80%); frequency control: limiting the number of user participation times (such as each person is limited to 1 coupon).

[0043] The evaluation indicators referred to in the embodiments of the present application may be recall rate, write-off rate, conversion rate, return on investment (ROI), gross merchandise volume (GMV), click-through rate (CTR), number of new users, repurchase rate, increase in average order value, etc.

[0044] For example, for the process node "push channel", its indicators can be recall rate and conversion rate.

[0045] For example, for the process nodes "Preferential Type" and "Preferential Rule", the indicator may be the write-off rate.

[0046] For example, for a marketing activity, the evaluation indicator may be ROI.

[0047] The configuration features referred to in the embodiments of the present application refer to features used to measure the marketing activities, which can specifically be activity type, budget, user coverage, discount strength, historical similar activity effect, and the aforementioned evaluation indexes.

[0048] Exemplarily, when predicting the success rate of the activities (i.e., binary classification: success / failure), the configuration features used include the activity type, the budget, and the user coverage.

[0049] Exemplarily, when predicting the ROI, conversion rate, and the like, the configuration features used include the discount strength and the historical similar activity effect.

[0050] The configuration combination referred to in the embodiments of the present application, which can also be referred to as a frequent item set (Frequent Itemset), refers to a combination of parameters that appears in a data set with a frequency reaching or exceeding a preset threshold.

[0051] The user data involved in the technical solutions of the present application are all obtained with authorization from the user, for example, by explicitly informing the user of the purpose, scope, and authority of the user data through an interactive interface, and obtaining valid authorization after the user actively checks the consent or completes an electronic signature.

[0052] To make the above-mentioned purposes, features, and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0053] The embodiments of the present application provide a marketing activity generation method, which refers to Figure 1 The specific steps will be described in detail below.

[0054] It can be understood that, in specific implementation, the marketing activity generation method can be realized in the form of a software program running in a processor integrated in a chip or a chip module. The method can also be realized in the form of software combined with hardware, and the present application does not make any limitation.

[0055] In step 101, user demand information is obtained, which is used to indicate at least a target activity type.

[0056] In specific implementation, the user can input the user demand information in an interactive interface to indicate the information of the marketing activity that the user wants to create. The user demand information at least includes the type of the marketing activity, i.e., the target activity type. For example, the user demand information includes that the target activity type is member recall.

[0057] In one specific embodiment, the user demand information can include the target activity type and the screening condition of the target user. The screening condition of the target user is used to determine the target user in the marketing activity.

[0058] For example, a user needs to configure a target activity type as a "member recall" activity, aiming to wake up the member users who have not consumed in the past 6 months. At this time, the target activity type is member recall, and the screening condition is the member users who have not consumed in the past 6 months.

[0059] Further, the user demand information can be partially coincident or completely consistent with the type of the configuration behavior data of the user in the marketing activity configuration and the type of the historical activity data. According to different actual application scenarios, the user demand information can include other any implementable other appropriate information, such as a budget, a budget allocation manner, a theme and content, and the like, which are not limited in the present application.

[0060] In step 102, a target activity template matching the target activity type is determined in the historical activity data, and the target activity template includes a plurality of process nodes.

[0061] In the embodiment, the historical activity data can be the related data of the completed marketing activities collected in advance and stored in a database. Specifically, the database can include a historical success case library and a historical failure case library. The historical success case library includes the data of the historical marketing activities with a high conversion rate (for example, the conversion rate is greater than a certain threshold), such as an activity theme, a screening condition, a channel, and the like. The historical failure case library is used to record the data of the historical marketing activities with a low ROI (for example, lower than a preset threshold) or a large number of user complaints (for example, higher than a preset threshold).

[0062] In a specific implementation, since the historical activity data includes the data of the historical marketing activities of various activity types, in order to ensure the accuracy of the target marketing, a target activity template matching the target activity type needs to be determined first. Specifically, at least one historical marketing activity matching the target activity type can be determined first, and then a target activity template is selected from the historical activity data corresponding to the at least one historical marketing activity. Specifically, the activity template used by the at least one historical marketing activity can be selected as the target activity template in combination with the evaluation index (for example, ROI) of the at least one historical marketing activity.

[0063] In a non-limiting embodiment, by analyzing the historical activity data in the historical success case library, a target activity template used by a historical marketing activity with a high evaluation index (for example, ROI) is selected, so as to ensure the performance of each node of the marketing activity. Please refer to Figure 2 , Figure 2 A way of determining a target activity template is shown.

[0064] In step 201, the historical activity data is clustered according to a target configuration feature, to obtain a plurality of historical activity clusters.

[0065] In this embodiment, the target configuration features used to cluster the historical activity data are related to the target activity type. In other words, the target configuration features are features used to measure marketing activities of the target activity type.

[0066] For example, if the target activity type is member recall, the target configuration feature could be recall rate. Since historical activity data includes evaluation metrics for historical marketing activities, such as recall rate, historical activity data can be clustered based on recall rate to obtain multiple historical activity clusters with different recall rates.

[0067] In step 202 , a target activity cluster matching the target activity type is determined in historical activity clusters.

[0068] Since marketing activities in a historical activity cluster may have various activity types, in order to ensure target matching, the historical activity cluster may be screened based on the target activity type to determine a target activity cluster that matches the target activity type.

[0069] In step 203, a target activity with a first evaluation index greater than a second threshold is selected from the target activity cluster, and a target activity template is generated based on the target activity. The first evaluation index is used to measure the execution result of the target activity.

[0070] In this embodiment, the target activity with the best execution result is selected by the first evaluation index, and the activity template used by the target activity can be used as the target activity template. For example, when the target activity type is member recall, the first evaluation index can be ROI.

[0071] In an optional embodiment, first activity data in the historical activity data that matches the target activity type can be clustered according to the target configuration features. In other words, the first activity data in the historical activity data can be clustered according to the recall rate to obtain multiple historical activity clusters with different recall rates. In this case, step 202 can be omitted. The target activity whose first evaluation metric is greater than the second threshold can be directly selected from the multiple historical activity clusters and a target activity template generated based on the target activity.

[0072] In a specific embodiment, the target activity template includes multiple process nodes. Taking the target activity type as member recall as an example, the target activity template includes the following process nodes:

[0073] Target user node, discount rule node, push channel node, push time node, and budget allocation node.

[0074] Continue to refer to Figure 1In step 103, the first activity data consistent with the target activity type in the historical activity data is analyzed, and the target content of the plurality of process nodes is generated in combination with the analysis result and the user demand information.

[0075] In step 104, the target content of the plurality of process nodes is filled into the plurality of process nodes to generate the target marketing activity.

[0076] The embodiment determines the target content of the plurality of process nodes in the target activity template through deep mining of the historical activity data, and automatically generates the target marketing activity.

[0077] Taking the member recall as the target activity type, the target marketing activity includes:

[0078] Target user node: members who have not consumed in the past 6 months;

[0079] Discount rule node: no threshold 20 yuan coupon (valid for 7 days);

[0080] Push channel node: short message push and application program push;

[0081] Push time node: 10 am;

[0082] Budget allocation node: the budget proportion of short message push is 30%, the budget proportion of APP push is 70%, and the total budget is 5000 yuan.

[0083] It should be pointed out that the serial numbers of the steps in the embodiment do not represent the limitation of the execution order of the steps.

[0084] In a non-limiting embodiment, in order to ensure the effect of the target content of the process node, the target content of the process node can be selected in combination with the historical evaluation index. For details, please refer to Figure 3 , Figure 3 An illustrative diagram for determining the target content of the process node is shown.

[0085] In step 301, the first activity data is analyzed to determine the historical evaluation index of each historical content for each process node.

[0086] In specific implementation, the evaluation index used by different process nodes can be different.

[0087] Exemplarily, for the process node "push channel", the index can be the recall rate.

[0088] Exemplarily, for the process nodes "discount type" and "discount rule", the index can be the cancellation rate.

[0089] In a specific implementation, the historical evaluation indicators of different historical contents of the same process node can be different. For example, the recall rate of the process node "push channel" for "short message push + application push" is 65%, the recall rate of the process node "push channel" for "short message push" is 40%, and the recall rate of the double-channel coverage of "short message push + application push" is 25% higher than that of the single-channel coverage.

[0090] For another example, the cancellation rate of the process node "benefit type" for "no threshold coupon" is 70%, the cancellation rate of the process node "benefit type" for "full-reduction coupon" is 40%, and the cancellation rate of "no threshold coupon" is 30% higher than that of "full-reduction coupon".

[0091] In one specific embodiment of step 301, historical configuration combinations of at least two process nodes in the first activity data are mined as historical contents of the at least two process nodes, and the support degree of the historical configuration combination is greater than a first threshold; and an evaluation indicator value of a historical marketing activity including the historical configuration combination is calculated. The at least two process nodes herein are process nodes in the target activity template.

[0092] Specifically, the historical configuration combination includes a combination of historical contents of at least two process nodes, for example, for the process node benefit rule node, the push channel node, and the target user node, the historical configuration combination can be "full-reduction activity + email push + target user as dormant user".

[0093] Specifically, the support degree of the historical configuration combination represents the frequency of the historical configuration appearing in the first activity data, and the calculation formula is: support degree Support(X) = number of marketing activities including the historical configuration combination / total number of marketing activities.

[0094] Further, the target content of the at least two process nodes is determined according to the historical configuration combination in the historical marketing activity whose evaluation indicator value is higher than a preset threshold. In the case where the historical content of the at least two process nodes of the historical marketing activity is the historical configuration combination, the evaluation indicator value of the marketing activity is calculated. For example, the conversion rate of historical marketing activity 1 for the historical content "full-reduction activity + email push + target user as dormant user" of three process nodes is 80%, and the average value of the conversion rates of all historical marketing activities is 40%, which means that the conversion rate of the historical content of the at least two process nodes of the marketing activity 1 as the historical configuration combination is higher. Therefore, it can be determined that the historical content "full-reduction activity + email push + target user as dormant user" of the three process nodes in the marketing activity 1 is the target content of the three process nodes.

[0095] Continuing to refer to Figure 3 In step 302, the historical content whose value of the historical evaluation indicator is higher than the first threshold is determined as the candidate historical content.

[0096] In this embodiment, historical content with a higher historical evaluation index may be selected as candidate historical content. The target content of the process node is selected from the candidate historical content of the process node.

[0097] In step 303 , the target content of each process node is determined based at least on the candidate historical content of the process node.

[0098] In a specific implementation, the historical content with the highest historical evaluation index may be selected from the candidate historical content of the process node as the target content of the process node.

[0099] In another specific embodiment, the target content of the process node may be selected from the candidate historical content of the process node in combination with other factors, such as the user's historical configuration preferences or the business rules of the process node.

[0100] In a specific embodiment of step 303 , the target content of the process node may be selected from the candidate historical content of the process node in combination with the historical configuration preference of the user.

[0101] In a specific implementation, in response to the number of candidate historical contents for at least one process node being multiple, determining the user's historical configuration preferences for the at least one process node in the historical activity data, and determining the candidate historical contents that match the historical configuration preferences for the at least one process node as the target content for the at least one process node.

[0102] Specifically, firstly, the first activity data of the user in the historical activity data is determined, and then the user's historical configuration preference for at least one process node can be determined based on the frequency of the user's historical content for at least one process node in the first activity data.

[0103] For example, for the process node push channel, the user's historical configuration preference is application push. Then, if the historical content with a high recall rate includes SMS push and application push, application push can be selected as the target content of the process node push channel.

[0104] This embodiment determines the target content of the process node in combination with the user's historical configuration preferences, which can meet the user's personalized needs.

[0105] In another specific embodiment of step 303 , the target content of the process node may be selected from the candidate historical content of the process node in combination with the business rules of the process node.

[0106] In a specific implementation, in response to the number of candidate historical contents of at least one process node being multiple, a business rule of at least one process node is determined, and candidate historical contents satisfying the business rule of at least one process node are determined as target contents of at least one process node.

[0107] This embodiment determines the target content of a process node in combination with the business rules of the process node, which can meet personalized business needs.

[0108] Specifically, different business rules can be set for different process nodes. For example, for a discount rule node, the business rule may include "new user activities must include a first-order discount." Specifically, candidate historical content for a process node can be matched against the business rules for that process node. If the candidate historical content meets the business rules for the process node, it can be determined as the target content for that process node.

[0109] In one non-limiting embodiment, after generating a preliminary targeted marketing campaign, the user can modify one or more process nodes within the preliminary targeted marketing campaign. This embodiment can automatically analyze and optimize the user's adjustments to one or more process nodes in conjunction with historical campaign data to further ensure the effectiveness of the marketing campaign.

[0110] In a specific implementation, in response to receiving the user's configuration behavior data, the content of one or more process nodes is adjusted according to the configuration behavior data to determine the adjusted content of one or more process nodes; based on the historical activity data, the first historical evaluation index value of the adjusted content of each process node in the one or more process nodes and the second evaluation index value of each historical content of each process node are analyzed.

[0111] For example, if a user wants to add phone push notifications to a push channel, the application can combine historical activity data to calculate a recall rate of 70% (the first historical evaluation index) for phone push notifications added to SMS and app push notifications, and an 80% (the second evaluation index) for email push notifications added to SMS and app push notifications.

[0112] Furthermore, target historical content whose second evaluation index value is higher than the first historical evaluation index value is selected from each historical content of each process node, and the target historical content is added to the optimization suggestion and pushed to the user.

[0113] For example, based on SMS push and application push, the recall rate of superimposed email push is 10% higher than that of superimposed phone push. Therefore, for push channel nodes, users can be advised to superimpose email push (that is, the target historical content is email push).

[0114] For example, for the discount rule node, the user wants to adjust the amount of the no-threshold coupon to 25 yuan. In combination with the target historical content, the redemption rate of the no-threshold coupon with an amount of 25 yuan is 40%, and the redemption rate of the no-threshold coupon with an amount of 30 yuan is 55%. The redemption rate of the no-threshold coupon with an amount of 30 yuan is 15% higher than that of the no-threshold coupon with an amount of 25 yuan. Therefore, for the discount rule node, the user can be suggested to set the amount of the no-threshold coupon to 30 yuan (i.e., the target historical content is the amount of the no-threshold coupon of 30 yuan).

[0115] For details, please refer to Figure 4 , Figure 4 A specific marketing activity is shown. The marketing activity includes a start node, a query filtering node, an application node, an SMS node, a coupon node, and an end node. Among them, the query filtering node accurately locates the target user from massive user or behavior data through data query and condition filtering. Taking the target activity type as a member recall as an example, the query filtering node filters out the member users who have not consumed in the past 6 months as target users.

[0116] The application node is used to issue a coupon to the target user through an application; the SMS node is used to issue a coupon to the target user through an SMS.

[0117] The coupon node is a key link specially designed for planning, issuing, redeeming, and tracking the effect of the coupon.

[0118] It should be noted that each node in the marketing activity can be adaptively set according to the actual application scene, and the present application does not limit this.

[0119] In a specific application scenario, the product form of the embodiment of the present application can be an intelligent assistant system integrated into an existing marketing CRM system. The marketing CRM system is a tool combining CRM and marketing automation, aiming to help enterprises better manage customer data, optimize marketing processes, and improve customer satisfaction.

[0120] The intelligent assistant system does not have invasiveness to the marketing CRM system, can not serve a specific module alone, can realize the automatic generation and optimization of the impact activity based on the input information of the user, and improve the generation efficiency of the marketing activity.

[0121] In a specific implementation, the user inputs user demand information by interacting with the intelligent assistant system. The intelligent assistant system can execute the steps in the foregoing embodiments, such as steps 101 to 104, to generate a target marketing activity.

[0122] For details, please refer to Figure 5 , Figure 5A marketing campaign generating device 50 is shown, and the marketing campaign generating device 50 may include:

[0123] An acquisition module 501 is used to acquire user demand information, where the user demand information is used to at least indicate a target activity type;

[0124] A target activity template determining module 502 is configured to determine a target activity template that matches the target activity type in the historical activity data, wherein the target activity template includes a plurality of process nodes;

[0125] An analysis module 503 is configured to analyze first activity data consistent with the target activity type in the historical activity data, and generate target content for multiple process nodes by combining the analysis results with user demand information;

[0126] The marketing campaign generating module 504 is configured to fill target contents of multiple process nodes into the multiple process nodes to generate target marketing campaigns.

[0127] Furthermore, the analysis module 503 may include: a first analysis unit, used to analyze the first activity data and determine the historical evaluation index for each historical content of each process node; a candidate historical content determination unit, used to determine the historical content whose value of the historical evaluation index is higher than the first threshold as the candidate historical content; and a first target content determination unit, used to determine the target content of each process node based at least on the candidate historical content of the process node.

[0128] Furthermore, the analysis module 503 may include: a second analysis unit, used to mine historical configuration combinations for at least two process nodes in the first activity data as historical content of the at least two process nodes, and the support degree of the historical configuration combination is greater than a first threshold; a calculation unit, used to calculate the evaluation index value of the historical marketing activities including the historical configuration combination; a second target content determination unit, used to determine the target content of at least two process nodes based on the historical configuration combination in the historical marketing activities whose evaluation index value is higher than a preset threshold.

[0129] Furthermore, the target activity template determination module 502 may include: a clustering unit, used to cluster historical activity data according to target configuration characteristics to obtain multiple historical activity clusters; a matching unit, used to determine a target activity cluster that matches the target activity type in the historical activity cluster; a target activity template generation unit, used to select a target activity in the target activity cluster whose first evaluation indicator is greater than a second threshold, and generate a target activity template based on the target activity, wherein the first evaluation indicator is used to measure the execution result of the target activity.

[0130] Furthermore, the marketing campaign generating device 50 may include: an adjustment content determining module for adjusting the content of one or more process nodes according to the configuration behavior data in response to receiving the configuration behavior data of the user to determine the adjustment content of the one or more process nodes;

[0131] an evaluation module for analyzing, based on historical activity data, a first historical evaluation index value of an adjustment content of each of the one or more process nodes, and a second evaluation index value of each historical content of each process node;

[0132] The suggestion module is used to select target historical content whose second evaluation index value is higher than the first historical evaluation index value from each historical content of each process node, and add the target historical content to the optimization suggestion and push it to the user.

[0133] In a specific implementation, the above-mentioned marketing activity generating device 50 may correspond to a chip with a marketing activity generating function in a terminal device, such as a system-on-a-chip (SOC), a baseband chip, etc.; or correspond to a chip module with a marketing activity generating function in a terminal device; or correspond to a chip module with a data processing function chip, or correspond to a terminal device.

[0134] For other relevant descriptions about the marketing activity generating device 50 , reference may be made to the relevant descriptions in the aforementioned embodiments, which will not be repeated here.

[0135] Regarding the various modules / units contained in the various devices and products described in the above embodiments, they can be software modules / units, hardware modules / units, or partly software modules / units and partly hardware modules / units. For example, for various devices and products applied to or integrated into a chip, the various modules / units contained therein can all be implemented in the form of hardware such as circuits, or at least part of the modules / units can be implemented in the form of software programs, which run on the processor integrated inside the chip, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuits; for various devices and products applied to or integrated into a chip module, the various modules / units contained therein can all be implemented in the form of hardware such as circuits, and different modules / units can be located in the same component of the chip module (such as a chip, circuit module, etc.) or in different components, or at least part of the modules / units can be implemented in the form of software programs. It is implemented in the form of a software program, which runs on the processor integrated inside the chip module, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuits; for various devices and products applied to or integrated in the terminal equipment, the various modules / units contained therein can be implemented in the form of hardware such as circuits, and different modules / units can be located in the same component (for example, chip, circuit module, etc.) or different components in the terminal equipment, or at least some modules / units can be implemented in the form of a software program, which runs on the processor integrated inside the terminal equipment, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuits.

[0136] The present application also discloses a storage medium, which is a computer-readable storage medium having a computer program stored thereon. When the computer program is executed, the steps of the method described in the aforementioned embodiment can be executed. The storage medium may include a read-only memory module (ROM), a random access memory module (RAM), a magnetic disk or an optical disk, etc. The storage medium may also include a non-volatile memory module or a non-transitory memory module, etc.

[0137] Please refer to Figure 6 The embodiment of the present application also provides a hardware structure diagram of a marketing activity generation device. The device includes a processor 601, a storage module 602 and a transceiver 603.

[0138] Processor 601 may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present application. Processor 601 may also include multiple CPUs, and processor 601 may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. The processor here may refer to one or more devices, circuits, or processing cores for processing data (such as computer program instructions).

[0139] The storage module 602 can be a ROM or other type of static storage device that can store static information and instructions, a RAM or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory module (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, and the present embodiment of the application does not impose any restrictions on this. The storage module 602 can exist independently (in this case, the storage module 602 can be located outside the device or inside the device), or it can be integrated with the processor 601. Among them, the storage module 602 can contain computer program code. The processor 601 is used to execute the computer program code stored in the storage module 602, thereby implementing the method provided in the embodiment of the present application.

[0140] The processor 601, storage module 602, and transceiver 603 are connected via a bus. The transceiver 603 is used to communicate with other devices or a communication network. Optionally, the transceiver 603 may include a transmitter and a receiver. The device used to implement the receiving function in the transceiver 603 can be considered a receiver, and the receiver is used to perform the receiving steps in the embodiments of the present application. The device used to implement the transmitting function in the transceiver 603 can be considered a transmitter, and the transmitter is used to perform the transmitting steps in the embodiments of the present application.

[0141] when Figure 6The shown structural schematic diagram is used for illustrating the structure of the terminal device involved in the above embodiments, the processor 601 is used for controlling and managing the actions of the terminal device, for example, the processor 601 is used for supporting the terminal device to perform the actions performed by the terminal device in other processes described in the embodiments of the present application. The storage module 602 is used for storing the program code and data of the terminal device.

[0142] The "multiple" appearing in the embodiments of the present application refers to two or more than two.

[0143] The first, second and the like appearing in the embodiments of the present application are only used for illustrative and distinguishing description objects, and there is no order, nor represent a special limitation on the number of devices in the embodiments of the present application, which cannot constitute any limitation on the embodiments of the present application.

[0144] The "connection" appearing in the embodiments of the present application refers to various connection modes such as direct connection or indirect connection, to realize the communication between devices, which is not limited in the embodiments of the present application.

[0145] The above embodiments can be realized by software, hardware, firmware or other any combination, in whole or in part. When realized by software, the above embodiments can be realized in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired or wireless mode.

[0146] It should be understood that in various embodiments of the present application, the size of the serial number of the above processes does not mean the order of execution, the execution order of the processes should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0147] In the several embodiments provided in this application, it should be understood that the disclosed methods, devices, and systems can be implemented in other ways. For example, the device embodiments described above are merely schematic; for example, the division of the units is merely a logical function division, and there may be other division methods in actual implementation; for example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection of devices or units, which may be electrical, mechanical, or other forms.

[0148] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0149] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may be physically included separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0150] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit stored in a storage medium includes a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to perform some steps of the method described in various embodiments of the present application.

[0151] Although the present application is disclosed as above, the present application is not limited thereto. Any person skilled in the art may make various changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be based on the scope defined by the claims.

Claims

1. A marketing activity generation method for an intelligent assistant system, characterized in that: The intelligent assistant system is non-invasively integrated into the marketing CRM system, and the marketing activity generation method includes: Acquiring user demand information, where the user demand information is used to at least indicate a target activity type; Determining a target activity template that matches the target activity type in the historical activity data, wherein the target activity template includes a plurality of process nodes, each process node representing a phased goal or action in the marketing activity, and the plurality of process nodes are combined to form a complete marketing process; Analyzing first activity data consistent with the target activity type in the historical activity data, and generating target content for the multiple process nodes by combining the analysis result with the user demand information; Filling the target contents of the plurality of process nodes into the plurality of process nodes to generate a target marketing campaign; The analyzing the first activity data in the historical activity data that is consistent with the target activity type, and generating the target content of the multiple process nodes in combination with the analysis result and the user demand information, includes: mining historical configuration combinations for at least two process nodes in the first activity data as historical content of the at least two process nodes, wherein the support of the historical configuration combination is greater than a first threshold, wherein a configuration combination refers to a combination of parameters whose occurrence frequency in a data set reaches or exceeds a preset threshold, the historical configuration combination includes a combination of historical content of at least two process nodes, and the support of the historical configuration combination represents the frequency of occurrence of the historical configuration combination in the first activity data; Calculating evaluation index values ​​of historical marketing activities including the historical configuration combination; The target contents of the at least two process nodes are determined according to a historical configuration combination in a historical marketing activity in which the evaluation index value is higher than a preset threshold.

2. The marketing activity generation method according to claim 1, characterized in that: The analyzing the first activity data in the historical activity data that is consistent with the target activity type includes: Analyzing the first activity data to determine historical evaluation indicators for each historical content of each process node; Determine historical content whose value of the historical evaluation index is higher than a first threshold as candidate historical content; The target content of each process node is determined based on at least the candidate historical content of the process node.

3. The marketing activity generation method according to claim 2, characterized in that: The step of determining the target content of each process node based on at least the candidate historical content of the process node includes: In response to the number of the candidate historical contents for at least one process node being multiple, determining a historical configuration preference of a user for the at least one process node in the historical activity data; Determine candidate historical content that matches the historical configuration preference of the at least one process node as the target content of the at least one process node.

4. The marketing activity generation method according to claim 2, characterized in that: The step of determining the target content of each process node based on at least the candidate historical content of the process node includes: In response to the number of the candidate historical contents of at least one process node being multiple, determining a business rule of the at least one process node; Determine candidate historical content that meets the business rules of the at least one process node as target content of the at least one process node.

5. The marketing activity generation method according to claim 1, characterized in that: The determining of a target activity template matching the target activity type in the historical activity data includes: Clustering the historical activity data according to target configuration features to obtain a plurality of historical activity clusters; Determine a target activity cluster matching the target activity type in the historical activity clusters A target activity having a first evaluation index greater than a second threshold is selected from the target activity cluster, and the target activity template is generated based on the target activity, wherein the first evaluation index is used to measure an execution result of the target activity.

6. The marketing activity generation method according to claim 1, characterized in that: Also includes: In response to receiving the configuration behavior data of the user, adjusting the content of one or more process nodes according to the configuration behavior data to determine the adjusted content of the one or more process nodes; Analyzing, based on the historical activity data, a first historical evaluation index value of an adjusted content of each of the one or more process nodes, and a second evaluation index value of each historical content of each process node; Target historical content having a second evaluation index value higher than the first historical evaluation index value in each historical content of each process node is selected, and the target historical content is added to the optimization suggestion and pushed to the user.

7. The marketing activity generation method according to claim 1, characterized in that: The user demand information includes screening conditions for target users, and the multiple process nodes include target user nodes; and filling the target contents of the multiple process nodes into the multiple process nodes includes: Fill the target user's screening conditions into the target user node.

8. A marketing activity generating device for an intelligent assistant system, characterized in that: The intelligent assistant system is non-invasively integrated into the marketing CRM system, and the marketing activity generation device includes: An acquisition module, configured to acquire user demand information, wherein the user demand information is used to at least indicate a target activity type; a target activity template determination module, configured to determine a target activity template matching the target activity type in historical activity data, wherein the target activity template includes a plurality of process nodes, each process node representing a phased goal or action in a marketing activity, and the plurality of process nodes are combined to form a complete marketing process; an analysis module, configured to analyze first activity data consistent with the target activity type in the historical activity data, and generate target content for the multiple process nodes by combining the analysis result with the user demand information; a marketing campaign generating module, configured to fill the target contents of the plurality of process nodes into the plurality of process nodes to generate a target marketing campaign; The analysis module is further configured to mine historical configuration combinations for at least two process nodes in the first activity data as historical content of the at least two process nodes, wherein the support of the historical configuration combination is greater than a first threshold, wherein a configuration combination refers to a combination of parameters whose frequency of occurrence in a data set reaches or exceeds a preset threshold, the historical configuration combination includes a combination of historical content of at least two process nodes, and the support of the historical configuration combination represents the frequency of occurrence of the historical configuration in the first activity data; Calculating evaluation index values ​​of historical marketing activities including the historical configuration combination; The target contents of the at least two process nodes are determined according to a historical configuration combination in a historical marketing activity in which the evaluation index value is higher than a preset threshold.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a computer, the steps of the marketing campaign generating method according to any one of claims 1 to 7 are executed.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a computer, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A terminal device comprising a storage module and a processor, wherein the storage module stores a computer program that can be run on the processor, characterized in that: When the processor runs the computer program, the processor performs the steps of the marketing campaign generating method according to any one of claims 1 to 7.

Images