Push Method, Device, Equipment and Computer Storage Medium

Abstract

The present application discloses a push method, device, equipment and computer storage medium. In the method, first, according to a first preset rule, a target activity policy for the corresponding user is determined from multiple activity policies, so as to screen out the target activity policy that the user is most interested in in the scenario of multiple marketing activity policies. Then, according to a second preset rule, a target object that the user is interested in and associated with the target activity policy is determined, and business information is generated based on the target object and pushed to the user. In this way, after determining the target activity policy that the user is most interested in from multiple marketing activity policy scenarios, the merchant or commodity object that the user is interested in under the target activity policy can be further determined. Through the screening in the above two stages, the object that the user is interested in is obtained, and the screening accuracy is relatively high. Pushing the business information corresponding to the screened target object to the user is beneficial to improving the attractiveness of the pushed information to the user, and thus improving the success rate of pushing in the multiple marketing activity scenarios.

Description

Technical Field

[0001] This application belongs to the technical field of e-commerce, and particularly relates to a push method, device, equipment and computer storage medium. Background Art

[0002] A marketing activity refers to a marketing method in which a business party promotes product sales or retains users by intervening in social activities or integrating effective resources to plan large-scale activities. Usually, in related technologies, most can recommend merchants to users based on a single marketing activity scenario. For example, recommend merchants to users through the business rules of a single marketing activity, or recommend products to users based on data statistics of user purchase data items.

[0003] However, in practical applications, since there are many business parties, there are often multiple marketing activities running in parallel. The above-mentioned push methods for single marketing activities in related technologies cannot make full use of the resource value of multiple marketing activities, nor can they recommend the most interesting activities or merchants to users in the scenario of multiple marketing activities running in parallel, resulting in low accuracy of recommended content. Summary of the Invention

[0004] The embodiments of this application provide a push method, device, equipment and computer storage medium, which can improve the accuracy of recommended content for users.

[0005] In a first aspect, the embodiments of this application provide a push method, and the method includes:

[0006] Determine a target activity policy corresponding to the user from multiple activity policies through a first preset rule;

[0007] Determine a target object associated with the target activity policy through a second preset rule, where the target object is an object of interest to the user;

[0008] Generate business information according to the target object and the target activity policy;

[0009] Push the business information to the user.

[0010] In some embodiments, determining a target activity policy corresponding to the user from multiple activity policies through a first preset rule includes:

[0011] Obtain the first historical transaction data of the user in multiple activity policies;

[0012] Obtain the historical behavior characteristic data of the user;

[0013] According to the first preset rule, perform probability calculation based on the historical behavior characteristic data and the first historical transaction data to obtain the transaction probability data of the user corresponding to each activity policy;

[0014] Determine the target activity strategy that the user is interested in according to the transaction probability data.

[0015] In some embodiments, the first preset rule includes a sorting rule.

[0016] Determine the target activity strategy corresponding to the user from multiple activity strategies through the first preset rule, including:

[0017] When the first historical transaction data of the user among multiple activity strategies does not meet the preset conditions, sort the priorities of the multiple activity strategies according to the sorting rule;

[0018] Determine the activity strategy with the highest priority as the target activity strategy according to the sorting result.

[0019] In some embodiments, determine the target object associated with the target activity strategy through the second preset rule, including:

[0020] Obtain the second historical transaction data of the user corresponding to multiple objects, where the multiple objects are the objects associated with the target activity strategy;

[0021] According to the second preset rule, perform probability calculation based on the second historical transaction data to obtain the transaction probability data of the user corresponding to each object;

[0022] Determine the target object that the user is interested in according to the transaction probability data of the user corresponding to each object.

[0023] In some embodiments, the multiple objects include a first object and a second object, and the first object is an object that has a historical transaction relationship with the user;

[0024] Obtain the second historical transaction data of the user corresponding to multiple objects, including:

[0025] Perform similarity calculation based on the first object to obtain a second object similar to the first object;

[0026] Determine the transaction data between the user and the first object as the transaction data between the user and the second object;

[0027] Determine the transaction data between the user and the first object, and the transaction data between the user and the second object as the second historical transaction data.

[0028] In some embodiments, generate business information from the target object and the target activity strategy, including:

[0029] Obtain at least one resource data of the target object corresponding to the target activity strategy;

[0030] Determine the target resource data from the resource data through the preset business rule;

[0031] Generate service information based on the target resource data.

[0032] In a second aspect, an embodiment of the present application provides a pushing device, which includes:

[0033] A first determination module, configured to determine a target activity policy for the corresponding user from multiple activity policies through a first preset rule;

[0034] A second determination module, configured to determine a target object associated with the target activity policy through a second preset rule, where the target object is an object of interest to the user;

[0035] A generation module, configured to generate service information according to the target object and the target activity policy;

[0036] A pushing module, configured to push the service information to the user.

[0037] In some embodiments, the first determination module includes:

[0038] A first acquisition sub-module, configured to acquire first historical transaction data of the user in multiple activity policies;

[0039] A second acquisition sub-module, configured to acquire historical behavior characteristic data of the user;

[0040] A first calculation sub-module, configured to perform probability calculation according to the historical behavior characteristic data and the first historical transaction data according to the first preset rule to obtain transaction probability data of the user corresponding to each activity policy;

[0041] A first determination sub-module, configured to determine a target activity policy of interest to the user according to the transaction probability data.

[0042] In some embodiments, the second determination module includes:

[0043] A second determination sub-module, configured to acquire second historical transaction data of the user corresponding to multiple objects, where the multiple objects are objects associated with the target activity policy;

[0044] A second calculation sub-module, configured to perform probability calculation according to the second historical transaction data according to the second preset rule to obtain transaction probability data of the user corresponding to each object;

[0045] A third determination sub-module, configured to determine a target object of interest to the user according to the transaction probability data of the user corresponding to each object.

[0046] In a third aspect, an embodiment of the present application provides a computer device, which includes:

[0047] A processor and a memory storing computer program instructions;

[0048] When the processor executes computer program instructions, the push method as described in the first aspect is implemented.

[0049] In a fourth aspect, an embodiment of the present application provides a computer storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the push method as described in the first aspect is implemented.

[0050] In a fifth aspect, an embodiment of the present application provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device is caused to execute the push method as described in the first aspect.

[0051] The push method, device, equipment and computer storage medium according to the embodiments of the present application can first determine the target activity policy for the corresponding user from multiple activity policies through a first preset rule, and can screen out the target activity policy that the user is most interested in in the scenario of multiple marketing activity policies. Then, through a second preset rule, determine the target object that the user is interested in associated with the target activity policy, and generate business information based on the target object and the target activity policy and push it to the user. In this way, after determining the target activity policy that the user is most interested in from multiple marketing activity policy scenarios, the merchant or commodity object that the user is interested in under the target activity policy can be further determined. Through the screening of the above two stages, the object that the user is interested in is obtained, and the screening accuracy is relatively high. Pushing the business information corresponding to the screened target object to the user is beneficial to improving the attractiveness of the pushed information to the user, and thus improving the success rate of pushing in multiple marketing activity scenarios. Description of the Drawings

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required to be used in the embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0053] Figure 1 It is a schematic flowchart of the push method provided by an embodiment of the present application;

[0054] Figure 2 It is a schematic flowchart of the push method in a specific embodiment of the present application;

[0055] Figure 3 It is a schematic structural diagram of the push device provided by another embodiment of the present application;

[0056] Figure 4 It is a schematic structural diagram of the computer equipment provided by yet another embodiment of the present application. Detailed Embodiments

[0057] The features and exemplary embodiments of various aspects of the present application will be described in detail below. To make the objectives, technical solutions, and advantages of the present application clearer and more understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application and not to limit the present application. For those skilled in the art, the present application can be implemented without some of these specific details. The following description of the embodiments is only intended to provide a better understanding of the present application by showing examples of the present application.

[0058] It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover a non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the said element.

[0059] In the related art, most are solutions for recommending merchants to users in a single marketing activity scenario. One such solution is a recommendation solution based on business rules, which is implemented through label mapping relationships. In this solution, first, a first-level label mapping relationship between merchants and products is constructed, and then a second-level mapping relationship between merchant labels and population labels is constructed. Through these two levels of mapping relationships, the recommendation relationship between users and merchants is determined based on the products that users are interested in. This recommendation relationship is limited by the manual setting of label relevance. Not only does it require manual maintenance of label relevance, with relatively high manual maintenance costs, but the accuracy is also relatively low.

[0060] Another solution is a recommendation solution based on data statistical analysis. In this solution, it is necessary to, based on the historical purchase data of users, through statistical analysis methods, screen out the products with relatively high purchase frequencies by setting a threshold, and determine the recommendation relationship based on the screened products. This solution can only target users with relatively strong purchasing power and relies on the consumption data of these users. It cannot cover products that users have never purchased, with low data coverage, resulting in a narrow range of applicable users.

[0061] Moreover, both of the above two solutions only target a single marketing activity scenario, ignoring the scenario where multiple marketing activities are carried out in parallel, and cannot make full use of marketing resources to provide highly accurate recommendation results to users.

[0062] To solve the problems of the prior art, embodiments of the present application provide a push method, device, equipment, and computer storage medium. First, the push method provided by the embodiments of the present application will be introduced below.

[0063] Figure 1 The flowchart of the push method provided by an embodiment of the present application is shown. As Figure 1 shown, the method includes steps S101 to S104:

[0064] S101. Determine the target activity policy for the corresponding user from multiple activity policies through a first preset rule;

[0065] S102. Determine the target object associated with the target activity policy through a second preset rule, where the target object is the object of interest to the user;

[0066] S103. Generate service information according to the target object and the target activity policy;

[0067] S104. Push the service information to the user

[0068] According to the embodiments of the present application, first, the target activity policy for the corresponding user can be determined from multiple activity policies through a first preset rule, and the target activity policy that the user is most interested in can be screened out in the scenario of multiple marketing activity policies. Then, through a second preset rule, the target object of interest to the user associated with the target activity policy is determined, and service information is generated according to the target object and the target activity policy and pushed to the user. In this way, after determining the target activity policy that the user is most interested in from multiple marketing activity policy scenarios, the merchant or commodity object of interest to the user under the target activity policy can be further determined. Through the screening in the above two stages, the object of interest to the user is obtained, and the screening accuracy is relatively high. Pushing the service information corresponding to the screened target object to the user is beneficial to improving the attractiveness of the pushed information to the user, and thus improving the success rate of pushing in multiple marketing activity scenarios.

[0069] Exemplarily, the activity policy can be a marketing activity policy. Each marketing activity policy can be associated with multiple merchants or multiple commodities, and each merchant can also be associated with multiple commodities or multiple activity policies, and each commodity can also be associated with multiple merchants or multiple activity policies. For example, a certain online shopping platform has released three marketing activity policies A, B, and C during the same period, among which 300 merchants have participated in marketing activity policy A, 600 merchants have participated in marketing activity policy B, and 800 merchants have participated in marketing activity policy C. Then, marketing activity policy A establishes an association relationship with the 300 merchants, marketing activity policy B establishes an association relationship with the 600 merchants, and marketing activity policy C establishes an association relationship with the 800 merchants.

[0070] In the embodiments of the present application, when a business party releases multiple marketing activity strategies in the same period, in order to improve the user's participation in the activity strategies and avoid excessive interference of the business information of multiple activity strategies on the user, it is necessary to predict as accurately as possible the activity strategy that the user is most likely to be interested in. To this end, in some embodiments, by training the user's transaction data and behavioral characteristic data, the target activity strategy that the user is interested in is predicted. Specifically, step S101 determines the target activity strategy corresponding to the user from multiple activity strategies through a first preset rule, which may include steps S1011 to S1014:

[0071] S1011. Obtain the first historical transaction data of the user in multiple activity strategies.

[0072] In some specific examples, the first historical transaction data of the user in the activity strategy may include the historical transaction quantity. In some other examples, the first historical transaction data may also include data such as the transaction time, transaction object, and transaction frequency. In this embodiment, the first historical transaction data can be used to reflect the degree of interest of the user in the activity strategy.

[0073] Among them, the historical transaction quantity is the number of transaction records that the user has completed under each activity strategy during the validity period of the activity strategy. For example, during the validity period of activity strategy A, the user completed 3 transactions under activity strategy A, then the first historical transaction data of the user in activity strategy A may include the quantity, object, and transaction time of these 3 transactions, etc.

[0074] The transaction object may include merchants or goods.

[0075] The transaction frequency is the frequency of multiple transactions occurring within a period of time.

[0076] S1012. Obtain the historical behavioral characteristic data of the user.

[0077] In this embodiment, the historical behavioral characteristic data of the user may include the user's basic attributes, click behaviors on activity strategies, merchants or goods, and characteristics of transaction behaviors, etc.

[0078] Exemplarily, the user's basic attributes may include the user's gender, age, region (such as the region where the user account logs in to the platform), etc.

[0079] The click behavior may be the click and view behavior of the user on activity strategies, merchants or goods based on the pages published on the platform.

[0080] The trading behavior can be the behavior of a user completing a payment transaction for a corresponding merchant or product. In some specific examples, the trading behavior may also include the trading selection behavior for the corresponding merchant or product, such as the behavior of adding a product to the shopping cart but not making a payment, or the behavior of not making a transaction after collecting / following a merchant. Or the trading behavior may also include the trading cancellation behavior for the merchant or product, that is, the behavior of canceling the payment after placing an order.

[0081] In this embodiment, the historical behavior characteristic data can be used to reflect the trading preferences of the user.

[0082] S1013. According to the first preset rule, perform probability calculation based on the historical behavior characteristic data and the first historical trading data to obtain the trading probability data of the user corresponding to each activity strategy.

[0083] In this embodiment, the first preset rule may include calculating the trading probability data of the user under each activity strategy according to the historical behavior characteristic data and the first historical trading data.

[0084] In this embodiment, when performing probability calculation, it can be implemented through a preset calculation model. Among them, the calculation model can be a model with preset training rules. For example, the logistic regression algorithm can be used. The historical behavior characteristic data of the user is used as the input characteristic data, that is, the independent variable, and the first historical trading data of the user under each activity strategy is used as the dependent variable. The historical behavior characteristic data and the first historical trading data are input into the calculation model, and based on the logistic regression algorithm, the trading probability of the user under each activity strategy can be quickly calculated. In this example, the above trading probability data can be trading probability values.

[0085] Among them, for multiple activity strategies parallel in the same period, the first historical trading data of the user under each activity strategy can be collected at the moment when these activity strategies are released. For example, within one day after the release of activity strategy A and activity strategy B, the first historical trading data of the user is collected.

[0086] The historical behavior characteristic data can be collected and stored in the corresponding server in advance so that it can be directly called, thereby improving the calculation efficiency in the scenario of massive data processing.

[0087] In some specific examples, the above calculation model can be executed once at regular intervals (such as every day) according to the preset time interval, so as to update the trading probability data of the user for each activity strategy during the validity period of the activity strategy as time progresses and the first historical trading data accumulates, so as to be able to screen out the target activity strategies that the user is interested in according to the actual needs of the user.

[0088] S1014. Determine the target activity strategies that the user is interested in according to the trading probability data.

[0089] In this embodiment, after obtaining the transaction probability data of the user under each activity strategy through step S1013, these transaction probability data are sorted according to the magnitude of the values of the transaction probability data. The activity strategy corresponding to the maximum probability value in the transaction probability data is screened out and determined as the target activity strategy that the user is most interested in.

[0090] It can be understood that there can be one target activity strategy. In some specific examples, there can also be multiple target activity strategies, and this embodiment does not make a unique limitation.

[0091] In the embodiment of the present application, through training and calculation based on the user's first historical transaction data and historical behavior characteristic data, the target activity strategy that the user is most interested in and most matches the user is screened out from multiple activity strategies for the user. Furthermore, based on this target activity strategy, merchants or commodity objects that the user is interested in can be further screened for the user, improving the accuracy when recommending business information related to the object for the user, thereby facilitating improving the attractiveness of the business information to the user, attracting the user to successfully participate in the corresponding marketing activity for transactions, and then improving the execution of the marketing activity strategy, so that the marketing resources can be fully utilized.

[0092] In some embodiments, since in the case of cold start of the activity strategy (i.e., there is no first historical transaction data of the user for the time being), there is insufficient data support, and the target activity strategy that the user is interested in cannot be accurately predicted based on the user's first historical transaction data and user behavior characteristics. Therefore, in this embodiment, in step 101, it may specifically further include steps S1015 to S1016:

[0093] S1015. When the first historical transaction data of the user under multiple activity strategies does not meet the preset conditions, according to the sorting rule, sort the priorities of the multiple activity strategies;

[0094] S1016. According to the sorting result, determine the activity strategy with the highest priority as the target activity strategy.

[0095] In this embodiment, the first preset rule may further include a preset sorting rule. In the cold start stage of multiple activity strategies, the user does not generate sufficient transaction data (i.e., does not meet the preset conditions) under each activity strategy. Therefore, the transaction probability data of the user cannot be accurately calculated through the calculation model. Instead, the priorities between multiple activity strategies can be defined through the preset sorting rule. In some specific examples, the transaction data generated by the user within a time span of more than one day after the activity strategy is announced can be considered to have met the preset conditions. In other examples, it can also be determined whether the preset conditions are met according to the data volume of the first historical transaction data.

[0096] Exemplarily, the preset sorting rule can be an expert rule. In the initial stage of releasing multiple activity strategies, based on the expert rule, the priority levels between the activity strategies can be defined. The sorting order of such priority levels can be used to determine the target activity strategy that the user is interested in. For example, for activity strategy A and activity strategy B released simultaneously, in the expert rule set based on expert experience, it is defined that the priority of activity strategy A is higher than that of activity strategy B. Then, in the sorting result, activity strategy A takes precedence over activity strategy B, and activity strategy A can be directly determined as the target activity strategy.

[0097] In the embodiment of the present application, in the cold start stage of the marketing activity strategy, an expert rule suitable for the general public users can be formulated according to expert experience, so that the determined target activity strategy can be universal, improving the coverage of users, and can also screen out the most popular marketing activity strategies for users, maximizing the attraction of the activity strategy to users in the initial stage of the announcement of the activity strategy.

[0098] In the embodiment of the present application, when in the scenario where multiple activity strategies are parallel, after the target activity strategy that the user is interested in is located, the merchant or commodity object that the user is interested in under the target activity strategy can also be screened out for the user through step S102 to achieve the purpose of accurate push. Specifically, in some specific embodiments, step 102 determines the target object associated with the target activity strategy through a second preset rule, which may include S1021 to S1023:

[0099] S1021. Obtain the second historical transaction data of the user corresponding to multiple objects, where the multiple objects are the objects associated with the target activity strategy;

[0100] S1022. According to the second preset rule, perform probability calculation based on the second historical transaction data to obtain the transaction probability data of the user corresponding to each object;

[0101] S1023. Determine the target object that the user is interested in according to the transaction probability data of the user corresponding to each object.

[0102] The target activity strategy located for the user can be associated with multiple objects, and the object can be a merchant or a commodity. In this embodiment, there is a fixed association relationship between the target activity strategy and the associated object, and this association relationship can be stored in the server of the corresponding platform that releases the activity strategy.

[0103] In step S1021, when the corresponding target activity strategy is located for the user, a corresponding mapping relationship is established between the user and the target activity strategy. Based on this mapping relationship, the transaction data (i.e., the second historical transaction data) that occurs between the user and all the objects associated with the corresponding target activity strategy can be queried.

[0104] Exemplarily, the second historical transaction data may include the number of transactions completed between the user and a single merchant, or may include the number of transactions in which the user purchases a single type of commodity.

[0105] In some specific examples, the second historical transaction data may further include data such as the transaction frequency corresponding to the user and the object.

[0106] In this embodiment, based on the second historical transaction data between the user and the above object, through step S1022, probability calculation may be performed on the second historical transaction data according to the second preset rule to obtain the transaction probability data corresponding to the user for each object, such as the transaction probability data for the user and each merchant, or the transaction probability data for the user to purchase various types of commodities.

[0107] After obtaining the transaction probability data corresponding to the user for each object, in step S1023, sorting may be performed according to the value size of the transaction probability data, and the objects with a higher value of the transaction probability data and a higher sorting position may be selected as the target objects of interest to the user.

[0108] It can be understood that the target object may be one or more. In order to enhance the attractiveness of the object associated with the specific marketing activity strategy to the user, in this example, the top ten objects in the sorting may be used as the target objects for the user to select for consumption transactions.

[0109] In the embodiment of the present application, probability calculation is performed based on the second historical transaction data between the user and the object associated with the corresponding target activity strategy, which can more accurately calculate the target objects of interest to the user, improve the attractiveness of the object associated with the target activity strategy to the user, thereby promoting the user to generate consumption transactions for the target object according to their own needs, and enhancing the user conversion rate under the target activity strategy.

[0110] In the embodiment of the present application, since the user's consumption behavior is relatively scattered, it may lead to the problem of sparsity of the target objects determined based on the user transaction data. For example, the user's consumption transactions are concentrated in one merchant or a small number of merchants. In this case, since the number of objects corresponding to the user's transactions is small, the generalization ability of the target object screening scheme is weak. Therefore, in this embodiment, the problem of sparsity of the obtained target objects may also be solved through the relevance of similar objects. Specifically, in this embodiment, in step S1021. obtaining the second historical transaction data corresponding to the user for multiple objects, the multiple objects may include a first object and a second object, and the first object is an object having a historical transaction relationship with the user, such as Figure 2 As shown, step S1021 may specifically include:

[0111] S211. Calculate the similarity according to the first object to obtain a second object similar to the first object;

[0112] S212. Determine the transaction data between the user and the first object as the transaction data between the user and the second object;

[0113] S213. Determine the transaction data between the user and the first object and the transaction data between the user and the second object as the second historical transaction data.

[0114] In this embodiment, the first object may be a merchant having a historical transaction relationship with the user. In other examples of pushing commodity information, the first object may also be a commodity having a historical transaction relationship with the user.

[0115] In the embodiment of the present application, the relevance between objects corresponding to the same Merchant Category Code (MCC) can be calculated in advance through step S211. For example, the relevance between multiple merchants under the same MCC category. Therefore, in this embodiment, the first object and the second object may belong to the same MCC category.

[0116] Exemplarily, in step S211, the relevance between the first object and the second object can be calculated through an item-based collaborative filtering algorithm (ItemCF). For example, if a target activity policy is associated with multiple merchant objects, and the user has transactions with a part of these objects (i.e., the first object), but the number of these objects is small, then the second object similar to the first object can be calculated through the ItemCF method. In this way, the transaction relevance between the user and the first object is approximately equal to the transaction relevance between the user and the second object. Therefore, after obtaining the second object, through step S212, the transaction data between the user and the first object can be determined as the transaction data between the user and the second object, and through step S213, the transaction data between the user and the first object and the transaction data between the user and the second object can be determined together as the second historical transaction data, realizing the effective filling of the transaction data between the user and the merchant object and solving the problem of the sparsity of the transaction merchant objects associated with the user.

[0117] In some specific examples, after obtaining rich enough second historical transaction data, when performing step S1022 to calculate probabilities according to the second historical transaction data according to the second preset rule to obtain the transaction probability data of the user corresponding to each object, the second preset rule may include Alternating Least Square (ALS). When calculating probabilities in step S1022, the ALS algorithm can be used to construct two implicit matrices based on the second historical transaction data. These two implicit matrices are respectively a matrix about the user and a matrix about the merchant. By performing a product operation on these two implicit matrices, the transaction probability data between the user and the merchant object can be obtained.

[0118] It should be understood that the ALS algorithm is a mature technology in the art, and the process of constructing two implicit matrices based on the ALS algorithm will not be elaborated here.

[0119] According to the embodiments of the present application, in the process of determining the target objects of interest to users based on the transaction data with merchant objects, through the calculation of the similarity correlation between merchant objects, the problem of sparse transaction data of the objects associated with the target marketing strategy for users can be solved, which is conducive to expanding the quantity or dimension of the target objects of interest to the matched users, meeting the transaction needs of users, and thus promoting the transaction volume.

[0120] In some other specific examples, if there is insufficient transaction data between the user and the first object during the cold start phase of the activity strategy, multiple target objects can be determined through expert rules. For example, the top ten merchants liked by the general public users under the current target activity strategy can be selected according to expert experience.

[0121] In some embodiments, after positioning the target activity strategy of interest to the user and the objects of interest to the user from multiple activity strategies, business information about the target activity strategy and the target objects can be generated through step S103. In some specific examples, the business information may include user identification (Identity Document, ID), target activity strategy information, and target object information. For example, the business information can be "User X, the XX merchant you are interested in is having an activity of reducing 30 yuan when the consumption reaches 300 yuan. Hurry up and participate" and other content.

[0122] Exemplarily, the activity strategy can be applied to multiple consumption scenarios such as purchase, recharge, and refueling. In specific consumption scenarios, each activity strategy may have resource allocation forms such as actively claiming coupons and passively sending coupons. For example, in the mode of passively sending coupons, users may passively participate in multiple marketing activities but do not understand the activity strategies of each marketing activity. To avoid disturbing users multiple times, this embodiment can select the activity strategy that the user is most interested in from numerous marketing activities for reach reminder under the limited number of business information reminders.

[0123] Specifically, in this embodiment, step S103 for generating business information according to the target objects and the target activity strategy may include steps S1031 to S1033:

[0124] S1031. Obtain at least one resource data of the target object corresponding to the target activity strategy;

[0125] S1032. Determine the target resource data from the resource data through a preset business rule;

[0126] S1033. Generate business information according to the target resource data.

[0127] In this embodiment, the resource data can be in the form of coupons, tickets, points, etc., and this embodiment does not make a unique limitation.

[0128] The business rule can be a rule for determining the target resource data according to the validity period or data value of the resource data. The business rule can be used to determine the push priority of the resource data or to deduplicate the resource data, etc.

[0129] For example, when the user actively or passively receives multiple coupons corresponding to the target object under the target activity policy, the business rule can be used to deduplicate and prioritize the multiple coupons. For example, by sorting, the coupons that are about to expire can be screened out, or the coupons with greater discount strength can be screened out as the target resource data to generate business information and push it to the user. For example, according to the target resource data, the business information obtained is "Your (200 yuan off for refueling 200 yuan) coupon is about to expire! Use the X QuickPass program at merchants such as D and E!"

[0130] According to the embodiments of the present application, the resource data can be screened through the business rule, which helps to improve the verification volume of ticket resources under the marketing activity strategy and promote the improvement of the user's consumption transaction volume. After actual experimental tests, compared with the information push based on a single expert rule, the business information push based on the above business rule in this embodiment can increase the total verification volume of ticket resources in multiple marketing activity scenarios by 81.67%.

[0131] Moreover, the business information pushed in the embodiments of the present application is more attractive to users and helps to increase the number of participating users in the marketing activity. After actual experimental tests, compared with the information push based on a single expert rule, the business information push based on the above business rule in this embodiment can increase the number of users who receive the information and participate in the specified marketing activity by 75.93%.

[0132] At the same time, since the business information pushed in the embodiments of the present application is more in line with the content that users are interested in, it helps to increase the number of merchant transaction volumes in the marketing activity. After actual experimental tests, compared with the information push based on a single expert rule, the business information push based on the above business rule in this embodiment can increase the number of merchant transaction volumes corresponding to the marketing activity by 11%.

[0133] For the push method provided by the embodiments of the present application, the execution subject can be a push device. In the embodiments of the present application, taking the push device executing the push method as an example, the push device provided by the embodiments of the present application is described.

[0134] Figure 3 The structural schematic diagram of the push device provided by the embodiments of the present application is shown. As Figure 3 shown, the device includes:

[0135] The first determination module 301 is configured to determine the target activity policy for the corresponding user from multiple activity policies according to a first preset rule;

[0136] The second determination module 302 is configured to determine the target object associated with the target activity policy according to a second preset rule, where the target object is the object of interest of the user;

[0137] The generation module 303 is configured to generate service information according to the target object and the target activity policy;

[0138] The push module 304 is configured to push the service information to the user.

[0139] In the embodiments of the present application, the target activity policy for the corresponding user can be first determined from multiple activity policies according to the first preset rule, and the target activity policy that the user is most interested in can be screened out in the scenario of multiple marketing activity policies. Then, according to the second preset rule, the target object of interest of the user associated with the target activity policy is determined, and service information is generated according to the target object and the target activity policy and pushed to the user. In this way, after determining the target activity policy that the user is most interested in from multiple marketing activity policy scenarios, the merchant or commodity object of interest of the user under the target activity policy can be further determined. Through the above two-stage screening, the object of interest of the user is obtained, and the screening accuracy is relatively high. Pushing the service information corresponding to the screened target object to the user is beneficial to improving the attractiveness of the pushed information to the user, thereby improving the success rate of pushing in multiple marketing activity scenarios.

[0140] Exemplarily, the activity policy can be a marketing activity policy. Each marketing activity policy can be associated with multiple merchants or multiple commodities, and each merchant can also be associated with multiple commodities or multiple activity policies, and each commodity can also be associated with multiple merchants or multiple activity policies.

[0141] In the embodiments of the present application, when the business party publishes multiple marketing activity policies in the same period, in order to improve the user's participation in the activity policy and at the same time avoid too much interference from the service information of multiple activity policies to the user, it is necessary to predict the activity policy that the user is most likely to be interested in as much as possible. For this purpose, in some embodiments, the target activity policy that the user is interested in is predicted by training the user's transaction data and behavior characteristic data. Specifically, the first determination module 101 may include:

[0142] The first acquisition sub-module is configured to acquire the first historical transaction data of the user in the multiple activity policies;

[0143] The second acquisition sub-module is configured to acquire the historical behavior characteristic data of the user;

[0144] The first calculation sub-module is used to calculate probabilities according to the first preset rule based on historical behavior characteristic data and first historical transaction data, so as to obtain transaction probability data of the user corresponding to each activity strategy.

[0145] The first determination sub-module is used to determine the target activity strategy that the user is interested in according to the transaction probability data.

[0146] In some specific examples, the first historical transaction data of the user in the activity strategy may include the historical transaction quantity. In some other examples, the first historical transaction data may further include data such as transaction time, transaction object, transaction frequency, etc. In this embodiment, the first historical transaction data can be used to reflect the degree of interest of the user in the activity strategy.

[0147] Among them, the historical transaction quantity is the number of transaction records that the user has completed under each activity strategy during the validity period of the activity strategy.

[0148] The transaction object may include merchants or commodities.

[0149] The transaction frequency is the frequency of multiple transactions occurring within a period of time.

[0150] In this embodiment, the historical behavior characteristic data of the user may include the user's basic attributes, click behaviors on activity strategies, merchants or commodities, and characteristics of transaction behaviors, etc.

[0151] Exemplarily, the user's basic attributes may include the user's gender, age, region (such as the region where the user account logs in to the platform), etc.

[0152] The click behavior may be the click and view behavior of the user on the activity strategy, merchant or commodity based on the page published by the platform.

[0153] The transaction behavior may be the behavior of the user completing the payment transaction for the corresponding merchant or commodity. In some specific examples, the transaction behavior may also include the transaction selection behavior for the corresponding merchant or commodity, such as the behavior of adding a commodity to the shopping cart but not making a payment, or the behavior of collecting / following a merchant but not making a transaction. Or the transaction behavior may also include the transaction cancellation behavior for the merchant or commodity, that is, the behavior of canceling the payment after placing an order.

[0154] In this embodiment, the historical behavior characteristic data can be used to reflect the transaction preferences of the user.

[0155] In this embodiment, the first preset rule may include calculating the transaction probability data of the user under each activity strategy according to the historical behavior characteristic data and the first historical transaction data.

[0156] In this embodiment, when calculating the probability, it can be achieved through a preset calculation model. Among them, the calculation model can be a model with preset training rules. For example, the logistic regression algorithm can be adopted. The historical behavior feature data of the user is used as the input feature data, that is, the independent variable, and the first historical transaction data of the user under each activity strategy is used as the dependent variable. The historical behavior feature data and the first historical transaction data are input into the calculation model, and based on the logistic regression algorithm, the transaction probability of the user under each activity strategy can be quickly calculated. In this example, the above transaction probability data can be a transaction probability value.

[0157] Among them, for multiple parallel activity strategies in the same period, the first historical transaction data of the user under each activity strategy can be collected at the moment when these activity strategies are released.

[0158] The historical behavior feature data can be collected and stored in the corresponding server in advance so that it can be directly called, thereby improving the calculation efficiency in the scenario of processing massive data.

[0159] In some specific examples, the above calculation model can perform calculations regularly (such as every day) at a preset time interval, so as to update the transaction probability data of the user for each activity strategy within the validity period of the activity strategy as time progresses and the first historical transaction data accumulates, so as to be able to screen out the target activity strategies that the user is interested in according to the actual needs of the user.

[0160] In this embodiment, after obtaining the transaction probability data of the user under each activity strategy, these transaction probability data are sorted according to the value size order of the transaction probability data. The activity strategy corresponding to the maximum probability value in the transaction probability data is selected and determined as the target activity strategy that the user is most interested in.

[0161] It can be understood that the target activity strategy can be one. In some specific examples, the target activity strategy can also be multiple, and this embodiment does not make a unique limitation.

[0162] In the embodiment of the present application, through the training calculation based on the first historical transaction data and historical behavior feature data of the user, the target activity strategy that the user is most interested in and most matches the user is screened out from multiple activity strategies for the user. Furthermore, based on this target activity strategy, merchants or commodity objects that the user is interested in can be further screened for the user, improving the accuracy when recommending object-related business information to the user, thereby facilitating improving the attractiveness of business information to the user, attracting the user to successfully participate in the corresponding marketing activities for transactions, and then improving the execution power of the marketing activity strategy, so that the marketing resources can be fully utilized.

[0163] In some embodiments, in the case of cold start of the active policy (i.e., there is no first historical transaction data of the user), due to insufficient data support, the target active policy that the user is interested in cannot be accurately predicted based on the user's first historical transaction data and user behavior characteristics. Therefore, in this embodiment, the first determination module 301 may further include:

[0164] A sorting sub-module, configured to, when the first historical transaction data of the user in multiple active policies does not meet the preset conditions, sort the priorities of the multiple active policies according to the sorting rules;

[0165] A policy determination sub-module, configured to determine the active policy with the highest priority as the target active policy according to the sorting result.

[0166] In this embodiment, the first preset rule may further include a preset sorting rule. In the cold start stage of multiple active policies, the user does not generate sufficient transaction data under each active policy (i.e., does not meet the preset conditions). Therefore, the transaction probability data of the user cannot be accurately calculated through a calculation model. Instead, the priorities between multiple active policies can be defined through the preset sorting rules. In some specific examples, the transaction data generated by the user within a time span of more than one day after the active policy is announced can be considered to meet the preset conditions. In other examples, it can also be determined whether the preset conditions are met according to the data volume of the first historical transaction data.

[0167] Exemplarily, the preset sorting rule can be an expert rule. In the initial stage when multiple active policies are released, the priority levels between the active policies can be defined based on the expert rule. In this way, the sorting order of the priority levels can determine the active policy with the highest priority as the target active policy that the user is interested in.

[0168] In the embodiments of the present application, in the cold start stage of the marketing activity policy, an expert rule suitable for the general public can be formulated according to expert experience, so that the determined target active policy can be universal, improving the coverage of users, and can also screen out the marketing activity policies that are most popular among the public for users, maximizing the attraction of the activity policy to users in the initial stage of the activity policy announcement.

[0169] In the embodiments of the present application, when the target active policy that the user is interested in is located in the scenario where multiple active policies are parallel, the second determination module 302 can further screen out the merchants or commodity objects that the user is interested in under the target active policy for the user to achieve the purpose of accurate push. Specifically, in some specific embodiments, the second determination module 302 may include:

[0170] A second determination sub-module, configured to obtain the second historical transaction data of the user corresponding to multiple objects, where the multiple objects are the objects associated with the target active policy;

[0171] A second calculation sub-module, configured to perform probability calculation according to the second historical transaction data according to a second preset rule, so as to obtain transaction probability data of the user corresponding to each object;

[0172] A third determination sub-module, configured to determine a target object of interest to the user according to the transaction probability data of the user corresponding to each object.

[0173] The target activity strategy located for the user can be associated with multiple objects, and the object can be a merchant or a commodity. In this embodiment, there is a fixed association relationship between the target activity strategy and the associated object, and this association relationship can be stored in the server of the corresponding platform that publishes the activity strategy.

[0174] After the corresponding target activity strategy is located for the user, a corresponding mapping relationship is established between the user and the target activity strategy. Based on this mapping relationship, the transaction data (i.e., the second historical transaction data) that occurs between the user and all the objects associated with the corresponding target activity strategy can be queried.

[0175] Exemplarily, the second historical transaction data may include the number of transactions completed between the user and a single merchant, or may include the number of transactions in which the user purchases a single type of commodity.

[0176] In some specific examples, the second historical transaction data may further include data such as the transaction frequency between the user and the object.

[0177] In this embodiment, based on the second historical transaction data between the user and the above objects, the second calculation sub-module can perform probability calculation on the second historical transaction data according to the second preset rule to obtain transaction probability data of the user corresponding to each object.

[0178] After obtaining the transaction probability data of the user corresponding to each of the objects, through the third determination sub-module, the objects can be sorted according to the value of the transaction probability data, and the objects with a higher value of the transaction probability data and a higher ranking position can be selected as the target objects of interest to the user.

[0179] It can be understood that the target object can be one or more. In order to enhance the attraction of the objects associated with the specific marketing activity strategy to the user, in this example, the top ten objects in the ranking can be used as the target objects for the user to select for consumption transactions.

[0180] In the embodiment of the present application, by performing probability calculation based on the second historical transaction data between the user and the objects associated with the corresponding target activity strategy, the target objects of interest to the user can be calculated more accurately, the attraction of the objects associated with the target activity strategy to the user can be improved, so as to promote the user to generate consumption transactions for the target objects according to their own needs, and the user conversion rate under the target activity strategy can be increased.

[0181] In the embodiment of the present application, since the consumption behaviors of users are relatively scattered, it may lead to the problem of sparsity of target objects determined based on user transaction data. For example, the consumption transactions of users are concentrated in one merchant or a small number of merchants. In this case, since the number of objects corresponding to the user's transactions is small, the generalization ability of the target object screening scheme is weak. Therefore, in this embodiment, the problem of sparsity of the obtained target objects can also be solved through the relevance of similar objects. Specifically, in this embodiment, when the second determination sub-module obtains the second historical transaction data of a user corresponding to multiple objects, the multiple objects may include a first object and a second object, and the first object is an object having a historical transaction relationship with the user. Then, the second determination sub-module may specifically include:

[0182] A calculation unit, configured to calculate a similarity according to the first object to obtain a second object similar to the first object;

[0183] A first determination unit, configured to determine the transaction data between the user and the first object as the transaction data between the user and the second object;

[0184] A second determination unit, configured to determine the transaction data between the user and the first object, and the transaction data between the user and the second object as the second historical transaction data.

[0185] In this embodiment, the first object may be a merchant having a historical transaction relationship with the user. In other examples of pushing commodity information, the first object may also be a commodity having a historical transaction relationship with the user.

[0186] In the embodiment of the present application, the calculation unit can calculate in advance the relevance between objects corresponding to the same Merchant Category Code (MCC). For example, the relevance between multiple merchants under the same MCC category. Therefore, in this embodiment, the first object and the second object may belong to the same MCC category.

[0187] Exemplarily, the computing unit can calculate the relevance between the first object and the second object through the item collaboration filtering algorithm (ItemCF). For example, if a target activity policy is associated with multiple merchant objects, and a user is associated with a part of these objects (i.e., the first objects), but the number of these objects is small, then the second objects similar to the first objects can be calculated through ItemCF. In this way, the transaction relevance between the user and the first objects is approximately equal to the transaction relevance between the user and the second objects. Therefore, after obtaining the second objects, the first determination unit can determine the transaction data between the user and the first objects as the transaction data between the user and the second objects, and the second determination unit can determine the transaction data between the user and the first objects and the transaction data between the user and the second objects together as the second historical transaction data, so as to effectively fill the transaction data between the user and the merchant objects and solve the problem of sparsity of the transaction merchant objects associated with the user.

[0188] In some specific examples, after obtaining sufficiently rich second historical transaction data, when the first determination unit calculates the transaction probability data of the user corresponding to each object according to the second preset rule based on the second historical transaction data, the second preset rule may include the Alternating Least Square (ALS). When the first determination unit performs probability calculation, it can use the ALS algorithm to construct two implicit matrices according to the second historical transaction data. These two implicit matrices are respectively the matrix about the user and the matrix about the merchant. By performing a product operation on these two implicit matrices, the transaction probability data between the user and the merchant objects can be obtained.

[0189] It should be understood that the ALS algorithm is a mature technology in this field, and the process of constructing two implicit matrices based on the ALS algorithm will not be elaborated here.

[0190] According to the embodiments of the present application, in the process of determining the target objects of interest to the user based on the transaction data with the merchant objects, by calculating the similarity relevance between the merchant objects, the problem of sparse transaction data of the objects associated with the user and the target marketing strategy can be solved, which is beneficial to expanding the quantity or dimension of the target objects of interest to the matching users, meeting the transaction needs of the users, and thus promoting the transaction volume.

[0191] In some other specific examples, if in the cold start stage of the activity policy, the transaction data between the user and the first objects is insufficient, then multiple target objects can be determined through expert rules. For example, the top ten merchants liked by the general public users under the current target activity policy are selected according to expert experience.

[0192] In some embodiments, after locating the target activity policy of interest for the user and the object of interest to the user from multiple active policies, the generation module 303 can generate business information about the target activity policy and the target object, and push it to the user's terminal through the push module 304. In some specific examples, the business information may include user identity (Identity Document, ID), target activity policy information, and target object information.

[0193] Exemplarily, the activity policy can be applied to multiple consumption scenarios such as purchasing, recharging, and refueling. In specific consumption scenarios, each activity policy may have resource allocation forms such as actively claiming coupons and passively sending coupons. To avoid disturbing the user multiple times, this embodiment can select the activity policy that the user is most interested in from numerous marketing activities for reach and reminder under a limited number of business information reminders. Specifically, in this embodiment, the generation module 303 may include:

[0194] A third acquisition sub-module, configured to acquire at least one resource data of the target object corresponding to the target activity policy;

[0195] A fourth determination sub-module, configured to determine target resource data from the resource data through a preset business rule;

[0196] An information generation sub-module, configured to generate business information according to the target resource data.

[0197] In this embodiment, the resource data may be in the form of coupons, tickets, points, etc., and this embodiment does not make a unique limitation.

[0198] The business rule may be a rule for determining target resource data according to the validity period or data value of the resource data. The business rule can be used to determine the push priority of the resource data or to deduplicate the resource data, etc.

[0199] According to the embodiments of the present application, the resource data can be screened through business rules, which helps to improve the verification volume of ticket resources under the marketing activity policy and promote the increase of the user's consumption transaction volume. After actual experimental tests, compared with the information push based on a single expert rule, the business information push based on the above business rules in this embodiment can increase the total verification volume of ticket resources in multiple marketing activity scenarios by 81.67%.

[0200] Moreover, the business information pushed in the embodiments of the present application is more attractive to users, which helps to increase the number of participating users in the marketing activity. After actual experimental tests, compared with the information push based on a single expert rule, the business information push based on the above business rules in this embodiment can increase the number of users who receive the information and participate in the specified marketing activity by 75.93%.

[0201] Meanwhile, since the service information pushed in the embodiments of this application better conforms to the content that users are interested in, it helps to increase the number of merchant transactions in marketing activities. After actual experimental tests, compared with the information push based on a single expert rule, the business information push based on the above business rules in this embodiment can increase the number of merchant transactions corresponding to the marketing activity by 11%.

[0202] It should be noted that all relevant contents of each step involved in the above method embodiments can be cited in the function descriptions of the corresponding functional modules and can achieve their corresponding technical effects. For the sake of concise description, they will not be elaborated here.

[0203] Figure 4 The figure shows a schematic hardware structure diagram of a computer device provided by an embodiment of this application.

[0204] The computer device may include a processor 401 and a memory 302 storing computer program instructions.

[0205] Specifically, the above-mentioned processor 401 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0206] The memory 402 may include a mass storage for data or instructions. By way of example and not limitation, the memory 402 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. In a suitable case, the memory 402 may include a removable or non-removable (or fixed) medium. In a suitable case, the memory 402 may be internal or external to the integrated gateway disaster recovery device. In a specific embodiment, the memory 402 is a non-volatile solid state memory.

[0207] The memory may include a read only memory (ROM), a random access memory (RAM), a magnetic disk storage media device, an optical storage media device, a flash memory device, an electrical, optical, or other physical / tangible memory storage device. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described in reference to the method according to one aspect of this application.

[0208] The processor 401 realizes any one of the push methods in the above embodiments by reading and executing the computer program instructions stored in the memory 402.

[0209] In one example, the computer device may further include a communication interface 403 and a bus 410. Among them, as Figure 4 shown, the processor 401, the memory 402, and the communication interface 403 are connected through the bus 410 to complete communication with each other.

[0210] The communication interface 403 is mainly used to realize the communication between each module, device, unit, and / or device in the embodiments of the present application.

[0211] The bus 410 includes hardware, software, or both, and couples the components of the computer device to each other. By way of example and not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses or a combination of two or more of these. In a suitable case, the bus 410 may include one or more buses. Although the embodiments of the present application describe and illustrate specific buses, the present application contemplates any suitable bus or interconnect.

[0212] In addition, in combination with the push method in the above embodiments, the embodiments of the present application can be implemented by providing a computer storage medium. Computer program instructions are stored on the computer storage medium; when the computer program instructions are executed by a processor, any one of the push methods in the above embodiments is realized.

[0213] Moreover, in combination with the push method in the above embodiments, the embodiments of the present application can provide a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the push method as described in the above embodiments.

[0214] It should be clear that the present application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, the detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions after understanding the spirit of the present application, or change the order between steps.

[0215] The functional modules shown in the above-described structural block diagrams can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a functional card, and so on. When implemented in software, the elements of the present application are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium or transmitted via a data signal carried in a carrier wave over a transmission medium or a communication link. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical discs, hard disks, fiber optic media, radio frequency (RF) links, and so on. The code segment can be downloaded via a computer network such as the Internet, an intranet, and so on.

[0216] It should also be noted that the exemplary embodiments mentioned in the present application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above steps, that is, the steps can be executed in the order mentioned in the embodiments, or different from the order in the embodiments, or several steps can be executed simultaneously.

[0217] Aspects of the present application have been described above with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present application. It should be understood that each block in the flowcharts and / or block diagrams, and the combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the functions / actions specified in one or more blocks of the flowcharts and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It can also be understood that each block in the block diagrams and / or flowcharts, and the combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by dedicated hardware performing the specified functions or actions, or by a combination of dedicated hardware and computer instructions.

[0218] As described above, this is only the specific implementation manner of the present application. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein. It should be understood that the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present application.

Claims

1. A push method, characterized in that, the method includes: When the business party releases multiple activity policies in the same period, determine the target activity policy that the user is interested in from the multiple activity policies through a first preset rule, and the multiple activity policies correspond to multiple consumption scenarios; each of the activity policies is associated with multiple objects, each object is associated with multiple of the activity policies, and the objects associated with the activity policy are the objects that participated in the activity policy; Determine the target objects associated with the target activity policy through a second preset rule, and the target objects are the objects that the user is interested in; Generate business information according to the target objects and the target activity policy; Push the business information to the user; The generating business information according to the target objects and the target activity policy includes: Obtain at least one resource data of the target objects corresponding to the target activity policy; Determine the target resource data from the resource data through a preset business rule; Generate the business information according to the target resource data.

2. The method according to claim 1, characterized in that, The determining the target activity policy that the user is interested in from the multiple activity policies through the first preset rule includes: Obtain the first historical transaction data of the user in the multiple activity policies; Obtain the historical behavior characteristic data of the user; According to the first preset rule, perform probability calculation according to the historical behavior characteristic data and the first historical transaction data to obtain the transaction probability data of the user corresponding to each of the activity policies; Determine the target activity policy that the user is interested in according to the transaction probability data.

3. The method according to claim 1, characterized in that, The first preset rule includes a sorting rule, The determining the target activity policy that the user is interested in from the multiple activity policies through the first preset rule includes: When the first historical transaction data of the user in the multiple activity policies does not meet the preset conditions, sort the priorities of the multiple activity policies according to the sorting rule; According to the sorting result, determine the activity policy with the highest priority as the target activity policy.

4. The method according to claim 1, characterized in that, The determining the target objects associated with the target activity policy through the second preset rule includes: Obtain the second historical transaction data of the user corresponding to multiple objects, and the multiple objects are the objects associated with the target activity policy; According to the second preset rule, perform probability calculation according to the second historical transaction data to obtain the transaction probability data of the user corresponding to each of the objects; Determine the target objects that the user is interested in according to the transaction probability data of the user corresponding to each of the objects.

5. The method according to claim 4, characterized in that, The multiple objects include a first object and a second object, and the first object is an object that has a historical transaction relationship with the user; The obtaining the second historical transaction data of the user corresponding to multiple objects includes: Perform similarity calculation based on the first object to obtain the second object similar to the first object; Determine the transaction data between the user and the first object as the transaction data between the user and the second object; Determine the transaction data between the user and the first object and the transaction data between the user and the second object as the second historical transaction data.

6. A push device, characterized in that the device includes: A first determination module, configured to, when a service provider publishes multiple activity policies in the same period, determine a target activity policy that the user is interested in from the multiple activity policies through a first preset rule, where the multiple activity policies correspond to multiple consumption scenarios; each of the activity policies is associated with multiple objects, each of the objects is associated with multiple of the activity policies, and the object associated with the activity policy is the object that participated in the activity policy; A second determination module, configured to determine a target object associated with the target activity policy through a second preset rule, where the target object is an object that the user is interested in; A generation module, configured to generate service information according to the target object and the target activity policy; A push module, configured to push the service information to the user; The generation module includes: A third acquisition sub-module, configured to acquire at least one resource data corresponding to the target object for the target activity policy, where the resource data is data corresponding to a ticket resource; A fourth determination sub-module, configured to determine target resource data from the resource data through a preset service rule; An information generation sub-module, configured to generate the service information according to the target resource data.

7. The device according to claim 6, characterized in that the first determination module includes: A first acquisition sub-module, configured to acquire first historical transaction data of the user in the multiple activity policies; A second acquisition sub-module, configured to acquire historical behavior characteristic data of the user; A first calculation sub-module, configured to perform probability calculation according to the historical behavior characteristic data and the first historical transaction data according to the first preset rule to obtain transaction probability data of the user corresponding to each of the activity policies; A first determination sub-module, configured to determine a target activity policy that the user is interested in according to the transaction probability data.

8. The device according to claim 6, characterized in that the second determination module includes: A second determination sub-module, configured to acquire second historical transaction data of the user corresponding to multiple objects, where the multiple objects are objects associated with the target activity policy; A second calculation sub-module, configured to perform probability calculation according to the second historical transaction data according to the second preset rule to obtain transaction probability data of the user corresponding to each of the objects; A third determination sub-module, configured to determine a target object that the user is interested in according to the transaction probability data of the user corresponding to each of the objects.

9. A computer device, characterized in that the device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the push method described in any one of claims 1-5 is implemented.

10. A computer storage medium, characterized in that, computer program instructions are stored on the computer storage medium, and when the computer program instructions are executed by a processor, the push method described in any one of claims 1-5 is implemented.

11. A computer program product, characterized in that, when the instructions in the computer program product are executed by a processor of an electronic device, the electronic device is caused to execute the push method described in any one of claims 1-5.

Images