User-based marketing activity processing method and device, equipment and medium

Abstract

The invention discloses a marketing activity processing method and device based on users, equipment and a medium, and relates to the technical field of data processing. According to the embodiment of the invention, the distribution attribute information of the current user is compared with the marketing activities in the form of the multi-way tree and the node coding information of the multi-way tree for representing the participation of the user, the node coding information is set on the multi-way tree, and the activity distribution relationship is searched directly through the node coding information, so that the searching efficiency is improved. And if the current user has the activity distribution relationship, performing analysis processing based on the marketing activity of the target multi-way tree corresponding to the distribution data to determine the marketing activity parameter result, thereby breaking the limitation barrier of the marketing activity, improving the traceability of the distribution data of the user, and saving the analysis cost. And if the distribution attribute information of the current user does not have the activity distribution relationship, it is indicated that the user is a new user, and a corresponding activity distribution relationship needs to be matched for the new user, so that subsequent marketing activity analysis is facilitated, and the flexibility is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a user-based marketing activity processing method, device, equipment and medium. Background Art

[0002] With the development of financial technology, the consumer finance market is becoming increasingly fierce in order to optimize user experience, improve service efficiency and risk management capabilities.

[0003] In the process of optimizing services, we need to understand the characteristics and preferences of different user groups. In the conventional process of making marketing activities, the cost of manual analysis is high, and the user's suitability for marketing activities is only simply evaluated by the amount of consumption, which leads to reduced accuracy of the evaluation and poor retrospective performance.

[0004] Therefore, how to improve the accuracy and traceability of marketing activities to save costs is an urgent problem that technical personnel in this field need to solve. Summary of the invention

[0005] The purpose of the present invention is to provide a user-based marketing activity processing method, device, equipment and medium to solve the problems of high manual analysis cost, low evaluation result accuracy and poor traceability in the conventional production of marketing activities.

[0006] In order to solve the above technical problems, the present invention provides a user-based marketing activity processing method, comprising:

[0007] Obtain the current user's diversion attribute information and the pre-built activity diversion relationship; wherein the activity diversion relationship is used to characterize the marketing activities corresponding to the multi-branch tree to which the user belongs and the multi-branch tree node coding information;

[0008] If the diversion attribute information of the current user exists in the activity diversion relationship, the diversion data corresponding to the current user is determined according to the diversion attribute information of the current user and the activity diversion relationship, and the marketing activity of the target multi-branch tree corresponding to the diversion data of the current user is analyzed and processed to obtain the marketing activity participation result of the current user;

[0009] If the diversion attribute information of the current user does not exist in the active diversion relationship, the diversion attribute information of the current user is inserted into the active diversion relationship to update the active diversion relationship.

[0010] On the one hand, the multi-branch tree construction process includes:

[0011] Obtaining each preset ratio and the corresponding priority level; wherein the sum of each preset ratio is 1;

[0012] Sort by priority level from high to low to obtain the preset proportions after sorting;

[0013] When the number of users meets the preset proportion of the first priority level, the users meeting the preset proportion of the first priority level are allocated to the group of the preset proportion of the first priority level, and the group corresponding to the preset proportion of the first priority level is closed;

[0014] Opening a preset ratio of groups of the second priority level to facilitate the entry of the remaining users, until all users are allocated to all the sorted preset ratio groups;

[0015] The node coding information is established by using the sorted cascade information corresponding to each preset ratio to construct the multi-branch tree.

[0016] On the other hand, the multi-branch tree construction process includes:

[0017] Acquire the user's attribute information; wherein the attribute information at least includes gender information, age information, channel information, province information, city information, occupation information and credit limit information;

[0018] Cascading the attribute information to determine the attribute information corresponding to each cascade;

[0019] Obtaining marketing means corresponding to the marketing activity;

[0020] Establishing a first mapping relationship between the attribute information corresponding to each of the cascades and the marketing means;

[0021] The attribute information corresponding to each of the cascades is used as a parent node, and the sub-attribute information under the attribute information corresponding to each of the cascades is used as a child node;

[0022] The parent node and the child node are identified by node coding information to establish the multi-branch tree.

[0023] On the other hand, the multi-branch tree construction process includes:

[0024] Get the various activity stages of marketing activities;

[0025] Determine the corresponding marketing means according to each stage of the activity;

[0026] Acquire the user's attribute information; wherein the attribute information at least includes gender information, age information, channel information, province information, city information, occupation information and credit limit information;

[0027] Cascading the attribute information to determine the attribute information corresponding to each cascade;

[0028] Establishing a first mapping relationship between the attribute information corresponding to each of the cascades and the marketing means;

[0029] The attribute information corresponding to each of the cascades is used as a parent node, and the sub-attribute information under the attribute information corresponding to each of the cascades is used as a child node;

[0030] The parent node and the child node are identified by node coding information to establish the multi-branch tree.

[0031] On the other hand, determining the diversion data corresponding to the current user according to the diversion attribute information of the current user and the activity diversion relationship includes:

[0032] Searching the activity diversion relationship according to the diversion attribute information of the current user to determine whether the current user exists;

[0033] If so, the data corresponding to the current user in the activity diversion relationship is used as the diversion data corresponding to the current user; wherein the diversion data is the marketing activity in which the current user participates and the node coding information of the marketing activity corresponding to the multi-branch tree.

[0034] On the other hand, analyzing and processing the marketing activities of the target multi-branch tree corresponding to the diversion data of the current user to obtain the marketing activity participation result of the current user includes:

[0035] In the case where there are multiple target multi-branch trees, checking the weight ratios corresponding to the target marketing activities to which the current user belongs in each target multi-branch tree; wherein the weight ratios are related to the node cascades where the corresponding target marketing activities are located;

[0036] If there is a target marketing activity with a weight ratio less than the first preset ratio, the target marketing activity with a weight ratio less than the first preset ratio is ignored, and the target marketing activity with a weight ratio greater than or equal to the first preset ratio is retained;

[0037] Determining the number of target marketing activities with a weight ratio greater than or equal to a first preset ratio;

[0038] If the number of target marketing activities with a weight ratio greater than or equal to the first preset ratio is 1, analyzing and processing the target marketing activities with a weight ratio greater than or equal to the first preset ratio to determine the marketing activity participation results;

[0039] If the number of target marketing activities with a weight ratio greater than or equal to the first preset ratio is not 1, then the target marketing activity with the largest weight ratio is selected from the target marketing activities with a weight ratio greater than or equal to the first preset ratio for analysis and processing to obtain the marketing activity participation results.

[0040] On the other hand, analyzing and processing the marketing activities of the target multi-branch tree corresponding to the diversion data of the current user to obtain the marketing activity participation result of the current user includes:

[0041] When there are multiple target multitrees, obtaining activity targets of influencing activities of each target multitree;

[0042] Pre-setting the influence factor of the current user participation of each target multi-branch tree according to the time sequence;

[0043] The number of target users corresponding to the current user participating in the marketing activity is determined according to the activity goal and various influencing factors.

[0044] In order to solve the above technical problems, the present invention also provides a user-based marketing activity processing device, comprising:

[0045] An acquisition module is used to acquire the current user's diversion attribute information and the pre-built activity diversion relationship; wherein the activity diversion relationship is used to characterize the marketing activities corresponding to the multi-branch tree to which the user belongs and the multi-branch tree node coding information;

[0046] A determination module, configured to determine the diversion data corresponding to the current user according to the diversion attribute information of the current user and the activity diversion relationship if the diversion attribute information of the current user exists in the activity diversion relationship, and to analyze and process the marketing activities of the target multi-branch tree corresponding to the diversion data of the current user to obtain the marketing activity participation result of the current user;

[0047] The inserting module is used for inserting the diversion attribute information of the current user into the active diversion relationship according to the diversion attribute information of the current user if the diversion attribute information of the current user does not exist in the active diversion relationship, so as to update the active diversion relationship.

[0048] In order to solve the above technical problems, the present invention further provides a user-based marketing activity processing device, comprising:

[0049] Memory for storing computer programs;

[0050] A processor is used to implement the steps of the user-based marketing activity processing method when executing the computer program.

[0051] In order to solve the above technical problems, the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the user-based marketing activity processing method are implemented.

[0052] The present invention provides a user-based marketing activity processing method, which obtains the current user's diversion attribute information and a pre-constructed activity diversion relationship; wherein the activity diversion relationship is used to characterize the marketing activity corresponding to the multi-branch tree to which the user belongs and the user's multi-branch tree node coding information coding diversion relationship; if the current user's diversion attribute information exists in the activity diversion relationship, the diversion data corresponding to the current user is determined according to the current user's diversion attribute information and the activity diversion relationship, and the marketing activity of the target multi-branch tree corresponding to the current user's diversion data is analyzed and processed to obtain the current user's marketing activity participation result; if the current user's diversion attribute information does not exist in the activity diversion relationship, the diversion attribute information of the current user is inserted into the activity diversion relationship to update the activity diversion relationship. The present invention compares the current user's diversion attribute information with the marketing activity in the form of a multi-branch tree used to characterize the user's participation and the multi-branch tree node coding information, and sets the node coding information on the multi-branch tree through the multi-branch tree, so that in the subsequent search process, there is no need to follow the multi-branch tree parent-child node data relationship, and the node coding information is directly searched in the activity diversion relationship through the node coding information to improve the search efficiency. If the current user exists in an activity diversion relationship, the diversion data of the current user is determined based on the two, and the marketing activity parameters are determined by analyzing and processing the marketing activities of the target multi-branch tree corresponding to the diversion data. Here, the marketing activities of the target multi-branch tree corresponding to the diversion data are set, and the user participates in multiple marketing activities. The analysis and processing are finally determined to determine the marketing activity participation results of the current user, break the restriction barriers of marketing activities, improve the traceability of the user's diversion data, and save analysis costs. If the diversion attribute information of the current user does not exist in an activity diversion relationship, it means that the new user needs to be matched to the corresponding activity diversion relationship to facilitate subsequent marketing activity analysis and improve flexibility.

[0053] In addition, the present invention also provides a user-based marketing activity processing device, equipment and medium, which have the same beneficial effects as the above-mentioned user-based marketing activity processing method. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0055] Figure 1 A flowchart of a user-based marketing activity processing method provided by an embodiment of the present invention;

[0056] Figure 2A schematic diagram of constructing a multi-branch tree using user attribute information provided by an embodiment of the present invention;

[0057] Figure 3 A schematic diagram of a multi-branch tree constructed based on user attribute information provided by an embodiment of the present invention;

[0058] Figure 4 A schematic diagram of a multi-branch tree constructed based on user attribute information of node coding information provided by an embodiment of the present invention;

[0059] Figure 5 A schematic diagram of a multi-branch tree constructed by user attribute information and activity stages provided by an embodiment of the present invention;

[0060] Figure 6 A schematic diagram of a multi-branch tree constructed based on user attribute information and activity stages of node coding information provided by an embodiment of the present invention;

[0061] Figure 7 A flow chart for determining diversion data corresponding to a current user provided by an embodiment of the present invention;

[0062] Figure 8 A query flow chart based on multiple target multi-trees provided by an embodiment of the present invention;

[0063] Fig. 9 A structural diagram of a user-based marketing activity processing device provided by an embodiment of the present invention;

[0064] Fig.10 A structural diagram of a user-based marketing activity processing device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0065] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] The core of the present invention is to provide a user-based marketing activity processing method, device, equipment and medium to solve the problems of high manual analysis cost, low evaluation result accuracy and poor traceability in the process of conventional marketing activity production.

[0067] In order to enable those skilled in the art to better understand the solution of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0068] Consumers' demands are becoming more and more personalized and diversified, and a single product or service is difficult to satisfy all users. Therefore, companies need to have a deeper understanding of the characteristics and preferences of different user groups in order to provide more accurate product recommendations and customized services. With the continuous improvement of financial regulatory policies, compliant operations have become the basis for the survival and development of enterprises. Companies can safely and effectively test new solutions and new products while ensuring compliance, reducing trial and error costs and potential risks. Conventional marketing activities lack a comprehensive testing plan, and the formulation of each marketing activity lacks subsequent analysis, resulting in low decision-making efficiency, low accuracy of effect evaluation, and loss of optimization opportunities. The user-based marketing activity processing method provided by the present invention can solve the above technical problems.

[0069] Figure 1 A flowchart of a user-based marketing activity processing method provided by an embodiment of the present invention, such as Figure 1 As shown, the method includes:

[0070] S11: Obtain the current user's diversion attribute information and the pre-built activity diversion relationship;

[0071] Among them, the activity diversion relationship is used to represent the marketing activities corresponding to the multi-branch tree to which the user belongs and the multi-branch tree node encoding information;

[0072] S12: Determine whether the current user's diversion attribute is within the active diversion relationship; if yes, proceed to step S13; if no, proceed to step S14;

[0073] S13: determining the diversion data corresponding to the current user according to the diversion attribute information of the current user and the activity diversion relationship, and analyzing and processing the marketing activities of the target multi-branch tree corresponding to the diversion data of the current user to obtain the marketing activity participation result of the current user;

[0074] S14: inserting the current user's diversion attribute information into the activity diversion relationship to update the activity diversion relationship.

[0075] Specifically, obtaining the current user's diversion attribute information is the user identification information for the user in the multi-tree. Different from the multi-tree node encoding information, the user identification is based on the current user's number of users, or the user's identity information, etc., which is a unique mark used to identify the user. The activity diversion relationship can be listed in a list, a table, or a database, etc., which is not limited here. Table 1 is an activity diversion relationship table. As shown in Table 1, it is used to record user activity diversion data. The diversion record table contains 3 fields, namely user identification (ID), activity ID, and node number. The user diversion result needs to be guaranteed to be immutable. After the user enters a prefix tree node, it will not change later. Therefore, after the user enters a prefix tree node, it is necessary to insert a diversion record in the database diversion record table to facilitate subsequent query of the user's diversion data. The activity diversion relationship is used to record user activity diversion data, which is used to characterize the marketing activities corresponding to the multi-tree to which the user belongs and the multi-tree node encoding information. A multi-branch tree corresponds to a marketing campaign. In order to distinguish between multiple marketing campaigns, the marketing campaign identification information is used, which has the same function as the identification of user diversion attribute information. The multi-branch tree node coding information is used to correspond to the coding information corresponding to which node the user is at based on the dependency relationship between the child node and the parent node in the multi-branch tree. Among them, the diversion tree is a prefix tree. Each node needs to contain a node code. The root node of the prefix tree is an empty node, and the prefix tree encoding starts from the second layer. It is necessary to include a list of parent node numbers and child node numbers. The entire multi-branch tree structure can be constructed based on the parent-child node information. The parent-child node numbers are used to define the hierarchical relationship of the multi-branch tree. The root node of the entire diversion tree is an empty node. The diversion rules of each marketing campaign can constitute a diversion prefix tree.

[0076] Table 1 Activity diversion relationship table

[0077]

[0078] The diversion prefix tree node needs to include a diversion plan and a marketing plan. The diversion plan is composed of regular expressions. The marketing plan refers to all marketing methods currently supported by the company's business, including message push, short message reach, intelligent outbound calls, enterprise WeChat push, rights and interests reach, etc. Business personnel can configure an independent marketing plan for each experimental group, or they can not set a marketing plan.

[0079] Corresponding to the node encoding information, capital letters are used to represent the node number. Since the number of child nodes of each parent node is unlimited, it is difficult to exhaust all nodes with 26 letters. If there are more than 26 nodes, two digits are used to represent 26*26 (676) combinations. If the conditions are still not met, it is increased to 3 digits, and so on. In order to record the number of digits of each layer of node number, it is necessary to maintain a node hierarchical digit table. Table 2 is the node hierarchical digit table. As shown in Table 2, the core fields of the node digit table include activity id, layer number and node number digits, which are used to indicate the number of digits of the node number of the current layer.

[0080] Table 2 Node stratification bit table

[0081]

[0082] If the diversion attribute of the current user exists in the activity diversion relationship, the diversion data corresponding to the current user is determined based on the diversion attribute information of the current user and the activity diversion relationship. Here, Table 1 is taken as an example, mainly by comparing the current user ID with the user ID in Table 1. If the diversion attribute of the current user exists in the activity diversion relationship, it means that the current user ID is the same as the user ID in Table 1, which means that the current user has participated in marketing activities, and the activity ID and node number in Table 1 will be used as the diversion data corresponding to the current user.

[0083] It should be noted here that the activity ID corresponding to the current user ID can be one or more, which is not limited here. If it is more than one, it means that the current user appears in multiple multi-trees, and the multiple multi-trees are used as multiple target multi-trees. Based on the principle that the analysis and processing process can only allow one user to participate in a marketing activity, it is necessary to screen and determine a target multi-tree in multiple target multi-trees, and analyze and process the marketing means of the marketing activity of the determined target multi-tree to obtain the marketing activity participation result of the current user. The screening process here can be screened by weight ratio, or the activity itself can be screened by the influence of the user, or it can be screened by direct deletion, etc., which is not limited here. The analysis and processing process here can be carried out using the algorithm corresponding to the conventional marketing activity, or it can be carried out by the algorithm redesigned for the current marketing activity, or it can be analyzed and processed based on the marketing means of the current marketing activity itself, which is not limited here and can be set according to the actual situation.

[0084] In step S14, since the diversion attribute information of the current user is not in the active diversion relationship, the current user, as a new user, needs to search layer by layer from the root node in all multi-branch trees, traverse all child nodes under the parent node, and match them one by one according to the diversion plan of the node. A child node that meets the diversion plan can be obtained, and then processed in the same way until entering the leaf node, and the leaf node result is inserted into the active diversion record table to update the active diversion relationship.

[0085] The embodiment of the present invention provides a user-based marketing activity processing method, which obtains the current user's diversion attribute information and a pre-constructed activity diversion relationship; wherein the activity diversion relationship is used to characterize the marketing activity corresponding to the multi-branch tree to which the user belongs and the user's multi-branch tree node coding information coding diversion relationship; if the current user's diversion attribute information exists in the activity diversion relationship, the diversion data corresponding to the current user is determined according to the current user's diversion attribute information and the activity diversion relationship, and the marketing activity of the target multi-branch tree corresponding to the current user's diversion data is analyzed and processed to obtain the current user's marketing activity participation result; if the current user's diversion attribute information does not exist in the activity diversion relationship, the diversion attribute information of the current user is inserted into the activity diversion relationship to update the activity diversion relationship. The present invention compares the current user's diversion attribute information with the marketing activity in the form of a multi-branch tree used to characterize the user's participation and the multi-branch tree node coding information, and sets the node coding information on the multi-branch tree through the multi-branch tree, so that in the subsequent search process, there is no need to follow the multi-branch tree parent-child node data relationship, and the node coding information is directly searched in the activity diversion relationship through the node coding information to improve the search efficiency. If the current user exists in an activity diversion relationship, the diversion data of the current user is determined based on the two, and the marketing activity parameters are determined by analyzing and processing the marketing activities of the target multi-branch tree corresponding to the diversion data. Here, the marketing activities of the target multi-branch tree corresponding to the diversion data are set, and the user participates in multiple marketing activities. The analysis and processing are finally determined to determine the marketing activity participation results of the current user, break the restriction barriers of marketing activities, improve the traceability of the user's diversion data, and save analysis costs. If the diversion attribute information of the current user does not exist in an activity diversion relationship, it means that the new user needs to be matched to the corresponding activity diversion relationship to facilitate subsequent marketing activity analysis and improve flexibility.

[0086] In some embodiments, the process of constructing a multi-branch tree includes:

[0087] Obtain each preset ratio and the corresponding priority level; wherein the sum of each preset ratio is 1;

[0088] Sort by priority level from high to low to obtain the preset proportions after sorting;

[0089] When the number of users meets the preset proportion of the first priority level, the users meeting the preset proportion of the first priority level are allocated to the group of the preset proportion of the first priority level, and the group corresponding to the preset proportion of the first priority level is closed;

[0090] Opening a preset ratio of groups of the second priority level to facilitate the entry of the remaining users, until all users are allocated to all the sorted preset ratio groups;

[0091] The sorted cascade information corresponding to each preset ratio is used to establish node coding information to construct a multi-branch tree.

[0092] Specifically, the number corresponding to the preset ratio is not limited here, and can be more than two preset ratios, etc. Taking two preset ratios (a first preset ratio and a second preset ratio) as an example, the sum of the first preset ratio and the second preset ratio is 1; the priority of the first preset ratio is greater than the priority of the second preset ratio; when the number of users meets the first preset ratio, the group corresponding to the first preset ratio is closed; the group of the second preset ratio is opened to facilitate the entry of the remaining users; the cascade information corresponding to the group of the first preset ratio and the group of the second preset ratio is used to establish node coding information to construct a multi-branch tree.

[0093] It should be noted that there is no limitation on the multi-branch tree construction process, and the diversion can be based on random ratio diversion, user attribute diversion, activity stage diversion, etc., or any combination of the above three. In this embodiment, random diversion is adopted, and random diversion means that all users are diverted according to the ratio preset by the business personnel, for example, the sum of the first preset ratio and the second preset ratio is 1, and the priority of the first preset ratio is greater than the priority of the second preset ratio.

[0094] First, calculate the first preset ratio. For example, if there are 100 people, the first preset ratio is 10%, and the second preset ratio is 90%. The first 10 users are divided into the group of the first preset ratio, and the next 90 users are divided into the group of the second preset ratio. The cascade relationship corresponding to the group of the first preset ratio and the group of the second preset ratio is used to establish node coding information, and the two-level cascade is used to distinguish them. The corresponding root node is not included in the scope of node coding information. 10% is used as node coding information A, and 90% is used as node coding information B.

[0095] The operator can customize the number of experimental groups and the diversion ratio of each experimental group. The configuration ratio of each experimental group is recorded as , first calculate the number of users in each experimental group The sum of the number of users in all experimental groups , then the real-time diversion ratio of each experimental group can be calculated .if , indicating that the current user meets the diversion conditions and is diverted to the current experimental group; if the ratios of all experimental groups are the same as the configured ratios, the first experimental group is selected as the diverted experimental group. .

[0096] The multi-branch tree established by random proportional allocation provided in this embodiment has a simple implementation process, simplifies the construction steps, and improves the construction efficiency.

[0097] In other embodiments, user attribute information refers to traffic diversion based on various attribute information of the user. Since there are multiple user attributes, the user diversion strategy also includes a series of sub-diversion strategies. The process of constructing a multi-branch tree includes:

[0098] Obtaining the user's attribute information; wherein the attribute information at least includes gender information, age information, channel information, province information, city information, occupation information and credit limit information;

[0099] Cascading the attribute information to determine the attribute information corresponding to each cascade;

[0100] Obtain marketing means corresponding to marketing activities;

[0101] Establishing a first mapping relationship between the attribute information corresponding to each level of association and the marketing means;

[0102] The attribute information corresponding to each cascade is taken as the parent node, and the sub-attribute information under the attribute information corresponding to each cascade is taken as the child node;

[0103] Parent nodes and child nodes are identified with node encoding information to establish a multi-branch tree.

[0104] Specifically, the user attribute diversion strategy includes at least seven sub-diversion strategies, namely gender diversion, age diversion, channel diversion, province diversion, city diversion, occupation diversion and quota diversion, etc. According to the user attribute diversion plan, first query the user basic service according to the user ID to obtain the corresponding attribute information of the user, and then match the specific attribute rules according to the user's attributes. If they meet the requirements, they will directly enter the current experimental group.

[0105] Figure 2 A schematic diagram of constructing a multi-branch tree through user attribute information provided by an embodiment of the present invention, such as Figure 2 As shown, the AB testing platform and the user base platform, the AB testing platform queries the user base platform to obtain user attribute information, and the user base platform returns the user attribute information to the AB testing platform; the AB testing platform determines the specific experimental group according to the attribute information.

[0106] In this embodiment, the attribute information is cascaded and classified to determine the attribute information corresponding to each cascade, that is, which attribute information is first used as the first layer, the second layer, and the Nth layer of the cascade relationship. At the same time, the marketing means corresponding to the marketing activities are also different, so it is necessary to establish a first mapping relationship between the attribute information and the marketing means, and the attribute information corresponding to each cascade is used as the parent node, and the sub-attribute information under the attribute information corresponding to each cascade is used as the child node. Each node needs to contain more than just the diversion plan and the marketing plan. Among them, the child node and the parent node are identified by the node coding information to complete the construction of the multi-branch tree.

[0107] Figure 3 A schematic diagram of a multi-branch tree constructed based on user attribute information provided by an embodiment of the present invention, such as Figure 3 As shown in the figure, the Spring Festival marketing activities require complex AB testing. The following is a detailed description of all the nodes of the left subtree of the diversion prefix tree. First, the diversion is carried out according to the user attribute age. The 18-30 age group constitutes a child node, and this group of users implements the SMS contact marketing plan; the 30-50 age group constitutes a child node, and there is no marketing plan; the 50-60 age group constitutes a child node, and there is no marketing plan. The 18-30 node contains three child nodes. Diversion is carried out according to the user attribute gender. Male customers constitute a child node, and the outbound call contact marketing plan is implemented; female users constitute a child node, and there is no marketing plan. The male node contains three child nodes. Diversion is carried out according to the user attribute channel. WeChat points constitute a child node, and the marketing plan of giving interest-free coupons is implemented; the application (Application, APP) constitutes a child node, and the marketing plan of giving interest-free coupons is implemented; Alipay constitutes a child node, and there is no marketing plan. The female node contains three sub-nodes, which are divided according to user attribute channels. WeChat constitutes a sub-node and implements the marketing plan of giving discount coupons; Alipay constitutes a sub-node, with no marketing plan; APP constitutes a sub-node, and implements the marketing plan of giving interest-free coupons. The APP node under the male node contains three sub-nodes, which are divided according to user attribute provinces. Shandong constitutes a sub-node, and implements the marketing plan of sending SMS; Hunan constitutes a sub-node, and implements the marketing plan of outbound calls; other provinces have no marketing plan.

[0108] Since the branch tree is a prefix tree, each node needs to contain a node code. Figure 4 A schematic diagram of a multi-branch tree constructed based on user attribute information of node coding information provided by an embodiment of the present invention, such as Figure 4As shown, the root node of the prefix tree is an empty node. The prefix tree encoding starts from the second layer. The encoding process of the left subtree node of the diversion prefix tree is described in detail below. The 18-30 child node is the first child node of the root node, so the prefix encoding is A; therefore, the 30-50 child node is encoded as C, and the 50-60 child node is encoded as B. The 18-30 node contains three child nodes. Since the prefix encoding must first be inherited from the parent node encoding, the male node is encoded as AA and the female node is encoded as AB. The male node contains three child nodes, which are divided according to the user attribute channel. The WeChat encoding is AAA, the APP encoding is AAB, and the Alipay encoding is AAC. The female node contains three child nodes, which are divided according to the user attribute channel. The WeChat encoding is ABA, the APP encoding is ABC, and the Alipay encoding is ABB. The APP node under the male node contains three child nodes, which are divided according to the user attribute province. The Shandong node is encoded as AACA, the Hunan node is encoded as AACB, and the other provinces are encoded as AACC.

[0109] The multi-branch tree constructed by user attribute information provided in this embodiment configures a corresponding marketing plan for each experimental group, supports diversion according to multiple user attributes, meets all current AB test diversion scenarios of consumer finance, and has sufficient flexibility and scalability. This solution supports multi-level diversion solutions. The results of the nodes in the previous layer will flow into the nodes in the next layer. The nodes in each layer are independent. The unified management and coding control of the diversion plan are achieved by constructing a diversion prefix tree. The prefix tree encoding method breaks the parent-child data dependency relationship of the multi-branch tree. Node data statistics do not need to use a bottom-up aggregation method, and the data comes directly from the leaf node data. That is, independent analysis of the data results of each diversion layer is achieved, and the efficiency of data statistics is improved, ensuring sufficient flexibility to meet the complex query scenarios of business personnel.

[0110] In some other embodiments, a multi-branch tree is constructed based on user attribute information and activity stages of marketing activities, and the corresponding multi-branch tree construction process includes:

[0111] Get the various activity stages of marketing activities;

[0112] Determine the corresponding marketing methods according to each activity stage;

[0113] Obtaining the user's attribute information; wherein the attribute information at least includes gender information, age information, channel information, province information, city information, occupation information and credit limit information;

[0114] Cascading the attribute information to determine the attribute information corresponding to each cascade;

[0115] Establishing a first mapping relationship between the attribute information corresponding to each level of association and the marketing means;

[0116] The attribute information corresponding to each cascade is taken as the parent node, and the sub-attribute information under the attribute information corresponding to each cascade is taken as the child node;

[0117] Parent nodes and child nodes are identified with node encoding information to establish a multi-branch tree.

[0118] Specifically, activity stage diversion is to implement different diversion strategies according to the different activity stages to which users belong. Activity stage diversion refers to diversion according to the activity stage. When configuring an activity, it can be divided into multiple nodes, such as the early, middle and late stages. Depending on the time when users participate in the activity, they will enter different experimental groups, thereby achieving the purpose of analyzing the activity effect in stages. Figure 5 A schematic diagram of a multi-branch tree constructed by user attribute information and activity stages provided in an embodiment of the present invention, such as Figure 5 As shown in the figure, first of all, the users are divided according to their age and activity stages. The early stage of the age group of 18-30 constitutes a sub-node, and this group of users implements the SMS contact marketing plan; the mid-stage of the age group of 30-50 constitutes a sub-node, and there is no marketing plan for app message push; the late stage of the age group of 50-60 constitutes a sub-node, and there is no marketing plan. The early stage of the 18-30 node contains three sub-nodes, which are divided according to the user attribute gender. Male customers constitute a sub-node, and the outbound call contact marketing plan is implemented; female users constitute a sub-node, and there is no marketing plan. The male node contains three sub-nodes, which are divided according to the user attribute channel. WeChat constitutes a sub-node, and the marketing plan of giving interest-free coupons is implemented; APP constitutes a sub-node, and the marketing plan of giving interest-free coupons is implemented; Alipay constitutes a sub-node, and there is no marketing plan. The female node contains three sub-nodes, which are divided according to the user attribute channel. WeChat constitutes a sub-node, and the marketing plan of giving discount coupons is implemented; Alipay constitutes a sub-node, and there is no marketing plan; APP constitutes a sub-node, and the marketing plan of giving interest-free coupons is implemented. The APP node under the male node contains three sub-nodes, which are divided according to the user attribute province. Shandong constitutes a sub-node and implements the SMS marketing plan; Hunan constitutes a sub-node and implements the outbound marketing plan; other provinces have no marketing plan.

[0119] Figure 6 A schematic diagram of a multi-branch tree constructed based on user attribute information and activity stages of node coding information provided by an embodiment of the present invention, such as Figure 6As shown in the figure, since the branch tree is a prefix tree, each node needs to contain a node code. The root node of the prefix tree is an empty node. The prefix tree coding starts from the second layer. The coding process of the left subtree node of the branch prefix tree is described in detail below. The 18-30 early child node is the first child node of the root node, so the prefix code is A; therefore, the later 30-50 child node code is C, and the 50-60 mid-term child node code is B. The 18-30 early node contains three child nodes. Since the prefix code first needs to inherit the parent node code, the male node code is AA and the female node code is AB. The male node contains three child nodes. The diversion is carried out according to the user attribute channel. The WeChat code is AAA, the APP code is AAB, and the Alipay code is AAC. The female node contains three child nodes. The diversion is carried out according to the user attribute channel. The WeChat code is ABA, the APP code is ABC, and the Alipay code is ABB. The APP node under the male node contains three child nodes, which are divided according to the user attribute province. The Shandong node code is AACA, the Hunan node code is AACB, and the other provinces are coded AACC. From top to bottom, there are five layers in total, so five records need to be stored in the node digit table, and the digits of each layer are 0, 1, 2, 3, and 4.

[0120] The multi-branch tree constructed by user attribute information and activity stages provided in this embodiment configures a corresponding marketing plan for each experimental group, supports diversion according to multiple user attributes and activity stages, meets all current AB test diversion scenarios in consumer finance, and has sufficient flexible scalability.

[0121] In some embodiments, determining the diversion data corresponding to the current user according to the diversion attribute information of the current user and the activity diversion relationship includes:

[0122] Searching in the activity diversion relationship according to the diversion attribute information of the current user to determine whether the current user exists;

[0123] If so, the data corresponding to the current user in the activity diversion relationship is used as the diversion data corresponding to the current user; wherein the diversion data is the marketing activities in which the current user participates and the node coding information of the multi-branch tree corresponding to the marketing activities.

[0124] Specifically, Figure 7 A flow chart for determining the diversion data corresponding to the current user provided by an embodiment of the present invention, such as Figure 7 As shown, including:

[0125] S21: User enters the activity;

[0126] S22: Obtaining a diversion strategy tree corresponding to the multi-branch tree according to the activity information;

[0127] S23: Check the activity diversion record table;

[0128] S24: Determine whether the record can be found; if not, proceed to step S25; if yes, end;

[0129] S25: Get the parent traffic diversion policy device, where the first one is the root node;

[0130] S26: Determine whether it is a leaf node; if so, proceed to step S27, if not, proceed to step S28;

[0131] S27: The result is written into the activity diversion record table and ends;

[0132] S28: traverse all sub-diversion policy devices;

[0133] S29: Determine whether the diversion strategy is satisfied; if so, proceed to step S30; if not, return to step S28;

[0134] S30: The current node becomes the parent node, and the process goes to step S25.

[0135] The present embodiment provides a method for determining the diversion data corresponding to the current user based on the diversion attribute information and activity diversion relationship of the current user. The diversion data of the current user is determined through a judgment process, so as to facilitate subsequent analysis and processing of the marketing activities of the target multi-branch tree corresponding to the diversion data of the current user to obtain the marketing activity participation results of the current user, thereby improving the efficiency of analysis and processing.

[0136] In some embodiments, analyzing and processing the marketing activities of the target multi-branch tree corresponding to the current user's diversion data to obtain the marketing activity participation result of the current user includes:

[0137] In the case of multiple target multitrees, check the weight ratios of the target marketing activities to which the current user belongs in each target multitree; wherein the weight ratio is related to the node cascade where the corresponding target marketing activity is located;

[0138] If there is a target marketing activity with a weight ratio less than the first preset ratio, the target marketing activity with a weight ratio less than the first preset ratio is ignored, and the target marketing activity with a weight ratio greater than or equal to the first preset ratio is retained;

[0139] Determining the number of target marketing activities with a weight ratio greater than or equal to a first preset ratio;

[0140] If the number of target marketing activities with a weight ratio greater than or equal to the first preset ratio is 1, then analyzing and processing the target marketing activities with a weight ratio greater than or equal to the first preset ratio to determine the marketing activity participation results;

[0141] If the number of target marketing activities with a weight ratio greater than or equal to the first preset ratio is not 1, then the target marketing activity with the largest weight ratio is selected from the target marketing activities with a weight ratio greater than or equal to the first preset ratio for analysis and processing to obtain the marketing activity participation results.

[0142] It should be noted that, in the case of multiple target multi-branch trees, it is necessary to select the final target multi-branch tree and then perform the above calculation. Therefore, it is necessary to check the weight ratios corresponding to the target marketing activities to which the current user belongs in each target multi-branch tree. The weight ratio at this time is related to the node cascade where the corresponding target marketing activities are located. For example, the node cascade corresponding to the current user in the first target multi-branch tree is located at the second level, the node cascade corresponding to the second target multi-branch tree is located at the third level, and the node cascade corresponding to the third target multi-branch tree is located at the fifth level. The corresponding weight ratios are gradually reduced. In this embodiment, it is necessary to ignore the target marketing activities with a weight ratio less than the first preset ratio according to the target multi-branch tree corresponding to the preset first preset ratio, and retain the target marketing activities with a weight ratio greater than or equal to the first preset ratio. When the number of target marketing activities with a weight ratio greater than or equal to the first preset ratio is 1, the target multi-branch tree is directly processed. If the number of target marketing activities with a weight ratio greater than or equal to the first preset ratio is not 1, the target marketing activity with the largest weight ratio is selected from the target marketing activities with a weight ratio greater than or equal to the first preset ratio to perform analysis and processing to obtain the marketing activity participation results.

[0143] In the marketing activities based on multiple target multi-branch trees provided in this embodiment, analysis and processing are performed based on the diversion data of the current user to determine the current user's participation results in the marketing activities, and statistical data under different diversion nodes are compared and analyzed. This is not limited to data comparison between different nodes of the same marketing activity, but also supports data comparison between different nodes under different activities.

[0144] In other embodiments, the marketing activity participation result of the current user is obtained by analyzing and processing the marketing activity of the target multi-branch tree corresponding to the diversion data of the current user, including:

[0145] When there are multiple target multitrees, obtaining activity targets of influencing activities of each target multitree;

[0146] Pre-set the influence factors corresponding to the participating users of each target multi-branch tree according to the time sequence;

[0147] Determine the target number of users corresponding to the current users participating in the marketing activity based on the activity goals and various influencing factors.

[0148] Specifically, first query the user list and process all user data in turn; query the activity record table to obtain the list of activities in which the current user participates; traverse each marketing activity to obtain the activity goal of the current activity; query the corresponding business system according to the user id and the activity goal, and you can get the completion status of the current user's activity goal; if the goal has been completed, insert the goal completion status into the user activity goal record table. Table 3 is the user activity goal record table. As shown in Table 3, the activity goal record table includes user id, activity id, node code, influence factor and activity goal, where user id, activity id, and node code are derived from the activity record table data. The influence factor represents the weight ratio of the current activity to the user, and its calculation formula is as follows, where ω represents the influence weight value of the current activity, and m represents the number of activities in which the user participates, that is, ω*m=1.

[0149] Table 3 User activity target record table

[0150]

[0151] As shown in Table 3, the activity target can be used as the number of users who apply for loans. The activity target here corresponds to a common activity target under multiple activities, and each activity maintains its own prefix multitree. The impact factor corresponding to the participating users is set according to the time sequence. The time sequence here corresponds to the time sequence of the entire timeline, not the early, middle and late stages corresponding to each activity. For example, there is only one activity 0 on November 1st, and activity 1 is started on November 5th. At this time, there are two activities on November 5th. There is only one activity 0 on November 1st, which reaches a group of users, including users 10000, 10001, 10002, 10003, 10004, and 10005, all of whom have borrowed money. Therefore, the impact factors of these 6 users corresponding to activity 0 are all 1. On November 5, both Activity 1 and Activity 0 will reach a group of users, which may include users reached on November 1, as well as newly reached users 10006 and 10007. Among the users reached on November 1, only newly reached users 10006 and 10007 are considered for deduplication. Since both activities reach them, the corresponding impact factors are averaged, and the impact factors of each activity are 0.5. At this time, users 10008 and 10009 are users independently triggered by Activity 1, and their corresponding impact factors of Activity 1 are both 1.

[0152] Therefore, in some embodiments, the influence factors corresponding to the participating users of each target multi-branch tree are set in advance according to the time sequence, including:

[0153] Get the target multi-branch trees corresponding to the current preset time;

[0154] According to the activity target and the current target multi-tree, whether it contains the current user;

[0155] If the current target multi-branch tree includes the current user's participation, then determine whether the target multi-branch tree corresponding to the previous preset time includes the current user's participation. If the target multi-branch tree corresponding to the previous preset time includes the current user's participation, then according to the deduplication principle, the current user is not set, and the influence factor of the current user of the target multi-branch tree corresponding to the previous preset time is used as the final influence factor of the current user;

[0156] If the target multi-branch tree corresponding to the previous preset time does not include the current user participation, determine whether the current user participation is included in the remaining target multi-branch trees corresponding to the current preset time; if the current user participation is included in the remaining target multi-branch trees corresponding to the current preset time, the weight obtained by averaging the number of target multi-branch trees in which the user participates corresponding to the current preset time is used as the influence factor of the current user; if the current user participation is not included in the remaining target multi-branch trees corresponding to the current preset time, the influence factor of the current user participating in the current target multi-branch tree is set to 1.

[0157] It should be noted that, a first target multi-branch tree corresponding to a first preset time is obtained; whether the current user is included is determined based on the activity target and the first target multi-branch tree; if so, the influence factor of the current user corresponding to the first target multi-branch tree is set to 1; if not, the influence factor of the current user corresponding to the first target multi-branch tree is set to 0; a second target multi-branch tree corresponding to a second preset time is obtained; whether the current user is included is determined based on the activity target and the second target multi-branch tree; if the second target multi-branch tree includes the participation of the current user, and the current user is included in the first target multi-branch tree corresponding to the first preset time, the current user is not set according to the deduplication principle; if the second target multi-branch tree includes the current user Participation, if the current user is not included in the first target multi-branch tree corresponding to the first preset time, and the current user is included in the first target multi-branch tree corresponding to the second preset time, the influence factor of the current user corresponding to the first target multi-branch tree and the influence factor of the second target multi-branch tree are averaged and set to 0.5; if the second target multi-branch tree includes the current user participation, and the first target multi-branch tree corresponding to the first preset time and the first target multi-branch tree corresponding to the second preset time do not include the current user, then the influence factor of the current user corresponding to the second target multi-branch tree is set to 1; until a certain time node is taken as the cutoff node, the influence factors of each target multi-branch tree corresponding to the user at each time node are compared.

[0158] Currently, only the influence factor of the marketing activity of the current user participating in the activity target is obtained. Analysis can also be performed based on the influence factor of the marketing activity of each user participating in the activity target, for example, statistics on the number of users who apply for loans corresponding to different node codes.

[0159] Combined with the examples in the above embodiments, activity 0 and activity 1, the parent node is A, corresponding to a province, such as Hunan Province, the child node is classified based on gender (male, female), and the corresponding child node is AA, that is, male users in Hunan Province, and AB is female users in Hunan Province. Table 4 is an activity table for applying for loans. As shown in Table 4, when the final statistics are counted, the node AA of the target activity 0 for the loan is that users 10000, 10002, 10004, and 10006 need to be counted, where the weight value of the target of user 10006 is 0.5, and the weight value of the target of others is 1, so the final result is 1+1+1+0.5 =3.5. The node AB of the target activity 0 for the loan is that users 10001, 10003, 10005, and 10007 need to be counted, where the weight value of the target of user 10007 is 0.5, and the weight value of the target of others is 1, so the final result is 1+1+1+0.5 =3.5. For the node A of target activity 0 of borrowing, users 10001, 10003, 10005, 10007, 10000, 10002, 10004, and 10006 need to be counted. The weight value of the user goals of 10006 and 10007 is 0.5, and that of others is 1. Therefore, the final result is 1+1+1+1+1+1+0.5+0.5 =7.

[0160] Table 4 Activity table for loan application

[0161]

[0162] Combined with Table 4, the impact factor here is a decimal, so the principle of being close to 1 is adopted to ensure that the final number of users counted is an integer.

[0163] Determine the number of target users corresponding to the current user participating in the marketing activity based on the activity goal and various influencing factors. Here, the current user is combined with Figure 4 The user ID can correspond to the marketing activity of the activity target, and the number of users of the child node and parent node corresponding to the node code can be clearly known. For example, user 10000 only participates in activity 0, and the corresponding node code is AB. The number of users participating in activity 0 is 3.5, which is 4 according to the principle of nearly 1; if it corresponds to node A, the number of users is 7.

[0164] Figure 8 A query flow chart based on multiple target multi-trees is provided in an embodiment of the present invention, such as Figure 8 As shown, including:

[0165] S31: Query all user lists;

[0166] S32: traverse all user data;

[0167] S33: Determine whether the user data has been traversed; if so, end; if not, proceed to step S34;

[0168] S34: Query the activity record table;

[0169] S35: Traverse all marketing activities;

[0170] S36: Determine whether the marketing activities have been traversed; if so, return to step S32; if not, proceed to step S37;

[0171] S37: Query the corresponding business system according to the user ID and the activity target, and the activity target is completed;

[0172] S38: Determine whether the target is completed, if so, proceed to step S39; if not, return to step S35;

[0173] S39: Calculate the weight value, insert it into the user activity target record table, and return to step S35.

[0174] When you need to query the statistical value of the corresponding node, you only need to query according to the activity number and node code. The specific structured query language (SQL) is as follows. In the process of AB test result statistics, the prefix tree encoding method breaks the parent-child data dependency of the multi-branch tree. The statistical data of the parent node does not need to come from the summary of all child nodes, but directly from the leaf node data.

[0175] SELECT SUM(weight) FROM activity_target_statistic_info WHEREactivity_code ='activity number' AND node_code LIKE 'node code%'.

[0176] The embodiment of the present invention provides a process for analyzing and processing the marketing activities of the target multi-branch tree corresponding to the diversion data of the current user to obtain the marketing activity participation results of the current user. Taking into account the concept of the influence factor of the activity itself on the current user, it breaks the restriction barriers of the activity. While supporting data comparison of different nodes of the same activity, it also supports data comparison of different nodes of different activities, thereby ensuring the horizontal expansion of AB testing and the flexibility of AB comparison.

[0177] The above describes in detail various embodiments corresponding to the method for processing marketing activities based on users. On this basis, the present invention also discloses a device for processing marketing activities based on users corresponding to the above method. Fig. 9FIG. 1 is a structural diagram of a user-based marketing activity processing device provided by an embodiment of the present invention. Fig. 9 As shown, the user-based marketing activity processing device includes:

[0178] The acquisition module 11 is used to acquire the current user's diversion attribute information and the pre-built activity diversion relationship; wherein the activity diversion relationship is used to characterize the marketing activity corresponding to the multi-branch tree to which the user belongs and the multi-branch tree node coding information;

[0179] The determination module 12 is used to determine the diversion data corresponding to the current user according to the diversion attribute information of the current user and the activity diversion relationship if the diversion attribute information of the current user exists in the activity diversion relationship, and to analyze and process the marketing activities of the target multi-branch tree corresponding to the diversion data of the current user to obtain the marketing activity participation result of the current user;

[0180] The inserting module 13 is used for inserting the diversion attribute information of the current user into the active diversion relationship according to the diversion attribute information of the current user if it does not exist in the active diversion relationship, so as to update the active diversion relationship.

[0181] Since the embodiments of the device part correspond to the above embodiments, please refer to the description of the embodiments of the method part for the embodiments of the device part, and will not be repeated here.

[0182] For an introduction to a user's marketing activity processing device provided by the present invention, please refer to the above method embodiment, and the present invention will not be repeated here. It has the same beneficial effects as the above user-based marketing activity processing method.

[0183] Fig.10 A structural diagram of a user-based marketing activity processing device provided by an embodiment of the present invention, such as Fig.10 As shown, the device includes:

[0184] A memory 21, used for storing computer programs;

[0185] The processor 22 is used to implement the steps of the user-based marketing activity processing method when executing the computer program.

[0186] The user-based marketing activity processing device provided in this embodiment may include but is not limited to a smart phone, a tablet computer, a laptop computer, or a desktop computer.

[0187] Among them, the processor 22 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 22 may be implemented in at least one hardware form of a digital signal processor (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 22 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a central processing unit (CPU); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 22 may be integrated with a graphics processing unit (GPU), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 22 may also include an artificial intelligence (AI) processor, which is used to process computing operations related to machine learning.

[0188] The memory 21 may include one or more computer-readable storage media, which may be non-transitory. The memory 21 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In this embodiment, the memory 21 is at least used to store the following computer program 211, wherein, after the computer program is loaded and executed by the processor 22, it can implement the relevant steps of the user-based marketing activity processing method disclosed in any of the aforementioned embodiments. In addition, the resources stored in the memory 21 may also include an operating system 212 and data 213, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system 212 may include Windows, Unix, Linux, etc. The data 213 may include, but is not limited to, data involved in the user-based marketing activity processing method, etc.

[0189] In some embodiments, the user-based marketing activity processing device may further include a display screen 23 , an input and output interface 24 , a communication interface 25 , a power supply 26 , and a communication bus 27 .

[0190] Those skilled in the art can understand that Fig.10 The structure shown in the figure does not constitute a limitation on the user-based marketing activity processing device, and may include more or less components than those shown in the figure.

[0191] The processor 22 implements the user-based marketing activity processing method provided by any of the above embodiments by calling the instructions stored in the memory 21 .

[0192] For an introduction to a user's marketing activity processing device provided by the present invention, please refer to the above method embodiment, and the present invention will not be repeated here. It has the same beneficial effects as the above user-based marketing activity processing method.

[0193] Furthermore, the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by the processor 22, the steps of the above-mentioned user-based marketing activity processing method are implemented.

[0194] It is understandable that if the method in the above embodiment 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 technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium to execute all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0195] For an introduction to a computer-readable storage medium provided by the present invention, please refer to the above method embodiment, which will not be described in detail herein. It has the same beneficial effects as the above user-based marketing activity processing method.

[0196] The above is a detailed introduction to a user-based marketing activity processing method, device, equipment and medium provided by the present invention. The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the embodiments can be referenced to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description. It should be pointed out that for ordinary technicians in this technical field, without departing from the principle of the present invention, several improvements and modifications can be made to the present invention, and these improvements and modifications also fall within the scope of protection of the present invention.

[0197] It should also be noted that, in this specification, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises", "comprising" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

Claims

1. A user-based marketing activity processing method, characterized in that: include: Obtain the current user's diversion attribute information and the pre-built activity diversion relationship; wherein the activity diversion relationship is used to characterize the marketing activities corresponding to the multi-branch tree to which the user belongs and the multi-branch tree node coding information; If the diversion attribute information of the current user exists in the activity diversion relationship, the diversion data corresponding to the current user is determined according to the diversion attribute information of the current user and the activity diversion relationship, and the marketing activity of the target multi-branch tree corresponding to the diversion data of the current user is analyzed and processed to obtain the marketing activity participation result of the current user; If the diversion attribute information of the current user does not exist in the active diversion relationship, the diversion attribute information of the current user is inserted into the active diversion relationship to update the active diversion relationship.

2. The user-based marketing activity processing method according to claim 1, characterized in that: The multi-branch tree construction process includes: Obtaining each preset ratio and the corresponding priority level; wherein the sum of each preset ratio is 1; Sort by priority level from high to low to obtain the preset proportions after sorting; When the number of users meets the preset ratio of the first priority level, the users meeting the preset ratio of the first priority level are allocated to the group of the preset ratio of the first priority level, and the group corresponding to the preset ratio of the first priority level is closed; Opening a preset ratio of groups of the second priority level to facilitate the entry of the remaining users, until all users are allocated to all the sorted preset ratio groups; The node coding information is established by using the sorted cascade information corresponding to each preset ratio to construct the multi-branch tree.

3. The user-based marketing activity processing method according to claim 1, characterized in that: The multi-branch tree construction process includes: Acquire the user's attribute information; wherein the attribute information at least includes gender information, age information, channel information, province information, city information, occupation information and credit limit information; Cascading the attribute information to determine the attribute information corresponding to each cascade; Obtaining marketing means corresponding to the marketing activity; Establishing a first mapping relationship between the attribute information corresponding to each of the cascades and the marketing means; Taking the attribute information corresponding to each of the cascades as a parent node, and taking the sub-attribute information under the attribute information corresponding to each of the cascades as a child node; The parent node and the child node are identified by node coding information to establish the multi-branch tree.

4. The user-based marketing activity processing method according to claim 1, characterized in that: The multi-branch tree construction process includes: Get the various activity stages of marketing activities; Determine the corresponding marketing means according to each stage of the activity; Acquire the user's attribute information; wherein the attribute information at least includes gender information, age information, channel information, province information, city information, occupation information and credit limit information; Cascading the attribute information to determine the attribute information corresponding to each cascade; Establishing a first mapping relationship between the attribute information corresponding to each of the cascades and the marketing means; Taking the attribute information corresponding to each of the cascades as a parent node, and taking the sub-attribute information under the attribute information corresponding to each of the cascades as a child node; The parent node and the child node are identified by node coding information to establish the multi-branch tree.

5. The user-based marketing activity processing method according to any one of claims 1 to 4, characterized in that: Determining the diversion data corresponding to the current user according to the diversion attribute information of the current user and the activity diversion relationship includes: Searching in the activity diversion relationship according to the diversion attribute information of the current user to determine whether the current user exists; If so, the data corresponding to the current user in the activity diversion relationship is used as the diversion data corresponding to the current user; wherein the diversion data is the marketing activity in which the current user participates and the node coding information of the marketing activity corresponding to the multi-branch tree.

6. The user-based marketing activity processing method according to claim 5, characterized in that: Analyzing and processing the marketing activities of the target multi-branch tree corresponding to the diversion data of the current user to obtain the marketing activity participation result of the current user, including: In the case where there are multiple target multi-branch trees, checking the weight ratios corresponding to the target marketing activities to which the current user belongs in each target multi-branch tree; wherein the weight ratios are related to the node cascades where the corresponding target marketing activities are located; If there is a target marketing activity with a weight ratio less than the first preset ratio, the target marketing activity with a weight ratio less than the first preset ratio is ignored, and the target marketing activity with a weight ratio greater than or equal to the first preset ratio is retained; Determining the number of target marketing activities with a weight ratio greater than or equal to a first preset ratio; If the number of target marketing activities with a weight ratio greater than or equal to the first preset ratio is 1, analyzing and processing the target marketing activities with a weight ratio greater than or equal to the first preset ratio to determine the marketing activity participation results; If the number of target marketing activities with a weight ratio greater than or equal to the first preset ratio is not 1, then the target marketing activity with the largest weight ratio is selected from the target marketing activities with a weight ratio greater than or equal to the first preset ratio for analysis and processing to obtain the marketing activity participation results.

7. The user-based marketing activity processing method according to claim 5, characterized in that: Analyzing and processing the marketing activities of the target multi-branch tree corresponding to the diversion data of the current user to obtain the marketing activity participation result of the current user, including: When there are multiple target multitrees, obtaining activity targets of influencing activities of each target multitree; Pre-setting the influence factor of the current user participation of each target multi-branch tree according to the time sequence; The number of target users corresponding to the current user participating in the marketing activity is determined according to the activity goal and various influencing factors.

8. A user-based marketing activity processing device, characterized in that: include: An acquisition module is used to acquire the current user's diversion attribute information and the pre-built activity diversion relationship; wherein the activity diversion relationship is used to characterize the marketing activities corresponding to the multi-branch tree to which the user belongs and the multi-branch tree node coding information; A determination module, configured to determine the diversion data corresponding to the current user according to the diversion attribute information of the current user and the activity diversion relationship if the diversion attribute information of the current user exists in the activity diversion relationship, and to analyze and process the marketing activities of the target multi-branch tree corresponding to the diversion data of the current user to obtain the marketing activity participation result of the current user; The inserting module is used for inserting the diversion attribute information of the current user into the active diversion relationship according to the diversion attribute information of the current user if the diversion attribute information of the current user does not exist in the active diversion relationship, so as to update the active diversion relationship.

9. A user-based marketing activity processing device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the user-based marketing activity processing method as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the user-based marketing activity processing method according to any one of claims 1 to 7 are implemented.

Images