CN114285896A - Information pushing method, device, equipment, storage medium and program product - Google Patents
Information pushing method, device, equipment, storage medium and program product Download PDFInfo
- Publication number
- CN114285896A CN114285896A CN202111632951.7A CN202111632951A CN114285896A CN 114285896 A CN114285896 A CN 114285896A CN 202111632951 A CN202111632951 A CN 202111632951A CN 114285896 A CN114285896 A CN 114285896A
- Authority
- CN
- China
- Prior art keywords
- target user
- user
- determining
- type
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The embodiment of the application provides an information pushing method, an information pushing device, information pushing equipment, a storage medium and a program product, and relates to the technical field of recommendation systems. The information pushing method comprises the following steps: acquiring a user type of a target user; determining basic index data of the target user according to the user type of the target user and the use data of the target user in a preset application program; and determining the push content of the target user according to the basic index data of the target user, so that a push strategy for automatically determining the push content based on the application type and the use data in the application program is realized, the efficiency and the accuracy of making the push content are improved, and the experience of the user in using the application program is improved.
Description
Technical Field
The embodiment of the application relates to the technical field of recommendation systems, in particular to an information pushing method, an information pushing device, information pushing equipment, a storage medium and a program product.
Background
The business of the financial industry is expanded to the aspect of permeating the life of users from the online and offline channel limited by the bank, and is cooperated with the industries of medical treatment, business excess and the like, so that more convenient financial service is provided for the users, and the systematized financial ecology is formed step by step.
In a financial ecological scene, the number of users of a financial platform is large, and the user demands are different. Therefore, operators of the financial platform need to make different marketing strategies and push corresponding preferential activities or financial products in a short message pushing mode or an application program pushing mode.
Financial products or preferential activities are pushed in a manual mode, time consumption is long, and pushing efficiency is low.
Disclosure of Invention
The embodiment of the application provides an information pushing method, an information pushing device, information pushing equipment, a storage medium and a program product, realizes an automatic pushing method based on user types and index data, and improves the popularization efficiency of pushing financial products, preferential activities and the like.
In a first aspect, an embodiment of the present application provides an information pushing method, where the method includes:
acquiring a user type of a target user; determining basic index data of the target user according to the user type of the target user and the use data of the target user in a preset application program; and determining the push content of the target user according to the basic index data of the target user.
Optionally, the obtaining the user type of the target user includes:
acquiring behavior data of the target user; and determining the user type of the target user according to the behavior data of the target user.
Optionally, determining the user type of the target user according to the behavior data of the target user includes:
determining the customer life cycle of the target user according to the behavior data of the target user; determining the user type of the target user according to the customer life cycle of the target user; wherein the behavioral data comprises: the time of browsing the pushed content for the first time, the time of registering the preset application program, the time of signing a product for the first time, the time of signing a product for the last time, and the time of logging off the preset application program.
Optionally, determining the user type of the target user according to the customer life cycle of the target user includes:
acquiring the user assets of the target user recorded in a preset application program; and determining the user type of the target user according to the customer life cycle of the target user and the user assets of the target user.
Optionally, determining the basic index data of the target user according to the user type of the target user and the usage data of the target user in a preset application program, includes:
determining each index to be extracted of the target user according to the user type of the target user; and extracting each basic index data of the target user from the use data of the target user in the preset application program according to each index to be extracted of the target user.
Optionally, determining each index to be extracted of the target user according to the user type of the target user includes:
acquiring a pre-established index corresponding relation, wherein the index corresponding relation is used for representing indexes to be extracted corresponding to various user types; and determining each index to be extracted of the target user according to the user type of the target user and the index corresponding relation.
Optionally, the basic index data includes one or more of time for registering the preset application program, time for logging in the preset application program, a subscription record, a browsing record, time for logging out the preset application program, and the like, asset distribution, login times, subscription frequency, and push browsing frequency.
Optionally, the method further includes:
and establishing analysis models corresponding to various user types in advance.
Optionally, determining the push content of the target user according to the basic index data of the target user includes: and determining the push content of the target user according to the basic index data of the target user and the analysis model corresponding to the user type of the target user.
Optionally, the method further includes:
according to a set period, determining derivative indexes corresponding to various user types according to basic index data and promotion paths of various users; and aiming at each user type, generating an evaluation report of the analysis model corresponding to the user type according to the derivative indexes corresponding to the user type, so as to adjust the analysis model corresponding to the user type based on the evaluation report.
In a second aspect, an embodiment of the present application further provides an information pushing apparatus, where the apparatus includes:
the user type acquisition module is used for acquiring the user type of the target user; the index data determining module is used for determining basic index data of the target user according to the user type of the target user and the use data of the target user in a preset application program; and the push content determining module is used for determining the push content of the target user according to the basic index data of the target user.
Optionally, the user type obtaining module is specifically configured to:
acquiring behavior data of the target user; and determining the user type of the target user according to the behavior data of the target user.
Optionally, the user type obtaining module includes:
the period determining unit is used for determining the customer life cycle of the target user according to the behavior data of the target user; the user type determining unit is used for determining the user type of the target user according to the customer life cycle of the target user; wherein the behavioral data comprises: the time of browsing the pushed content for the first time, the time of registering the preset application program, the time of signing a product for the first time, the time of signing a product for the last time, and the time of logging off the preset application program.
Optionally, the user type determining unit is specifically configured to:
acquiring the user assets of the target user recorded in a preset application program; and determining the user type of the target user according to the customer life cycle of the target user and the user assets of the target user.
Optionally, the index data determining module includes:
the to-be-extracted item determining unit is used for determining each to-be-extracted index of the target user according to the user type of the target user; and the index data extraction unit is used for extracting each basic index data of the target user from the use data of the target user in the preset application program according to each index to be extracted of the target user.
Optionally, the to-be-extracted item determining unit is specifically configured to:
acquiring a pre-established index corresponding relation, wherein the index corresponding relation is used for representing indexes to be extracted corresponding to various user types; and determining each index to be extracted of the target user according to the user type of the target user and the index corresponding relation.
Optionally, the basic index data includes one or more of time for registering the preset application program, time for logging in the preset application program, a subscription record, a browsing record, time for logging out the preset application program, and the like, asset distribution, login times, subscription frequency, and push browsing frequency.
Optionally, the apparatus further comprises:
and the model establishing module is used for establishing analysis models corresponding to various user types in advance.
Optionally, the push content determining module is specifically configured to:
and determining the push content of the target user according to the basic index data of the target user and the analysis model corresponding to the user type of the target user.
Optionally, the apparatus further comprises:
the derivative index determining module is used for determining derivative indexes corresponding to various user types according to the set period and the basic index data and promotion paths of various users; and the model adjusting module is used for generating an evaluation report of the analysis model corresponding to the user type according to the derivative indexes corresponding to the user type aiming at each user type so as to adjust the analysis model corresponding to the user type based on the evaluation report.
In a third aspect, an embodiment of the present application further provides an information pushing apparatus, including a memory and at least one processor; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the information pushing method provided by any embodiment of the application.
In a fourth aspect, the present application further provides a computer-readable storage medium, where computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, the computer-executable instructions are used to implement the information pushing method provided in any embodiment of the present application.
In a fifth aspect, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the information push method as provided in any embodiment of the present application is implemented.
According to the information pushing method, the information pushing device, the information pushing equipment, the information storage medium and the program product, aiming at content pushing in a financial ecological scene, the basic index data of a user are automatically determined according to the type of the user and the use data of the user in a preset application program, and then matching of pushed contents is carried out based on the basic index data, so that automatic pushing of the pushed contents such as products and preferential activities is achieved, the content pushing efficiency is improved, the pushing accuracy is high, the experience of the user in using the preset application program is improved, and the user activity and the satisfaction are improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
Fig. 1 is an application scenario diagram of an information push method according to an embodiment of the present application;
fig. 2 is a flowchart of an information pushing method according to an embodiment of the present application;
fig. 3 is a flowchart of an information pushing method according to another embodiment of the present application;
fig. 4 is a flowchart of an information pushing method according to another embodiment of the present application;
fig. 5 is a schematic structural diagram of an information pushing apparatus according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of an information pushing apparatus according to an embodiment of the present application.
With the above figures, there are shown specific embodiments of the present application, which will be described in more detail below. These drawings and written description are not intended to limit the scope of the inventive concepts in any manner, but rather to illustrate the inventive concepts to those skilled in the art by reference to specific embodiments.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The following describes the technical solutions of the present application and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
The following explains an application scenario of the embodiment of the present application:
fig. 1 is an application scenario diagram of an information pushing method provided in an embodiment of the present application, as shown in fig. 1, in a financial ecological scenario, a financial platform is combined with various platforms, such as a business platform, a medical platform, a government platform, and the like in fig. 1, and features of a user are not only financial features, but also have more aspects.
In order to improve the user experience and the loyalty, the financial platform needs to push contents such as preferential activities and products to the user terminal irregularly or regularly, so as to improve the activity of the user. In the prior art, an operator often pushes activities or products for a user based on data of the user recorded in an application program, such as browsing records, purchasing records, and the like.
The manner in which the content is pushed is determined manually, which is inefficient. And because the user characteristics are various, operators often cannot comprehensively analyze all the characteristics of the users, so that the pushed content is often not matched with the user requirements, and the use experience of the users is influenced.
In order to improve the efficiency and accuracy of content push, an embodiment of the present application provides an information push method, and the main concept thereof is: basic index data used for determining the pushed content is determined according to the user type and the use data of the user in the application program, and then automatic formulation of the pushed content is achieved based on the basic index data, a self-adaptive content pushing strategy is achieved, and user experience is improved.
Fig. 2 is a flowchart of an information pushing method according to an embodiment of the present application. The information push method may be executed by an information push device, where the specific form of the information push device may be a computer, a server, or other terminal devices, and in some embodiments, the information push device may be connected to a server of each preset application program, as shown in fig. 2, where the information push method provided in this embodiment includes the following steps:
step S201, a user type of the target user is acquired.
The target user may be any user who registers or logs in the preset application program, or any user who browses the content of the preset application program.
In order to push different contents for different users differently, the user types need to be divided. The user type of the target user may be specifically determined according to one or more of a customer life cycle, a user asset, a user tag, etc. of the target user.
The customer life cycle is a parameter for describing a stage where a business relationship between a user and an enterprise is located, and may include an introduction period, a growth period, a maturity period, a dormancy period, and a loss period. The user assets are the assets of the target user on a preset application program or a financial platform. The user tag may be a user tag set for a user when the user portrait is drawn.
Optionally, the obtaining the user type of the target user includes:
acquiring behavior data of the target user; and determining the user type of the target user according to the behavior data of the target user.
The behavior data may be activity data of the target user on the financial platform and on each other platform associated with the financial platform, that is, on each preset application program, such as the target application program and each application program associated with the target application program, and may also include activity data on a webpage, an applet, and the like associated with the target application program, such as browsing records, purchase records, registration time, and the like. The target application may be an application of a banking or financial institution.
Specifically, the behavior data may include data generated by the target user when browsing push content corresponding to the bank or the financial institution, and may also include activity data of the target user in a preset application program and each application program associated with the preset application program.
For example, the default application may be an application of a bank or financial institution, and the other applications associated with the default application may be a social application, a short video application, a shopping application, a payment application, etc.
In some embodiments, the behavioral data includes: the time of browsing the pushed content for the first time, the time of registering the preset application program, the time of signing the product for the first time, the time of signing the product for the last time, the time of logging in the preset application program for the last time, and the time of logging out the preset application program. A record of each time the target user signs up for a product may also be included.
The pushed content browsed by the user can be content published on each preset application program and application programs, web pages, applets and the like associated with the preset application program.
Specifically, if the target user does not register the preset application program and the time for browsing the pushed content for the first time exists, determining that the user type of the target user is the first type, and if the target user registers the preset application program and the time length from the time of no signing any product or the time of signing the product for the first time to the current time is less than the first length, determining that the user type of the target user is the second type; if the time length of the time of the target user for signing the product for the first time and the current time is greater than the second length or the times of signing the product by the target user is greater than the preset times, determining that the user type of the target user is a third type; if the time length from the time of the last signed product of the target user to the current time is longer than the third length or the time length from the time of the last login of the target user to the current time of the preset application program to the target user is longer than the fourth length, determining that the user type of the target user is the fourth type; and if the time of the target user logging off the preset application program or the time of the target user logging in the preset application program for the last time and the time length of the current time are greater than the fifth length, determining that the user type of the target user is the fifth type. Wherein the second length is greater than the first length and the fifth length is greater than the fourth length.
In some embodiments, the behavior data may also include user assets, i.e., user assets that the target user has deposited in a pre-set application. Furthermore, on the basis of the classification, the first type to the fifth type can be further divided by combining user assets to obtain more user types.
Optionally, determining the user type of the target user according to the behavior data of the target user includes:
determining the customer life cycle of the target user according to the behavior data of the target user; and determining the user type of the target user according to the customer life cycle of the target user.
Specifically, if the target user does not register the preset application program and the time for browsing the pushed content for the first time exists, determining that the life cycle of the client of the target user is a lead-in period, and if the target user registers the preset application program and the time length from the time of no signing any product or the time of signing the product for the first time to the current time is less than a first length, determining that the life cycle of the client of the target user is a growth period; if the time length of the time of the target user for signing the product for the first time and the current time is greater than the second length or the times of signing the product by the target user is greater than the preset times, determining the life cycle of the target user as the mature period; if the time length from the time of the last signed product of the target user to the current time is longer than the third length or the time length from the time of the last login of the target user to the current time of the preset application program to the target user is longer than the fourth length, determining that the life cycle of the target user is a dormant period; and if the time of the target user logging off the preset application program or the time of the target user logging in the preset application program for the last time and the time of the current time are longer than the fifth length, determining that the life cycle of the target user is the loss period. Wherein the second length is greater than the first length and the fifth length is greater than the fourth length. Of course, other methods for dividing the life cycle of the client may be adopted, which is not limited in the present application.
Specifically, after obtaining the customer life cycle of the target user, the user type of the target user may be determined based on the user entry information, the user assets, and other information of the target user and the customer life cycle. The user basic information may include information of industry, age, gender, and the like in which the target user is engaged.
In the technical scheme of the application, the acquisition, storage, application and the like of the related user personal information, such as the user basic information, are all in accordance with the regulations of related laws and regulations, and do not violate the customs of the public order.
In some embodiments, the user may be subjected to type division of the first stage based on the life cycle of the client to obtain an introduction period type, a maturity period type, a dormancy period type, and a churn period type, and each of the four types, namely the maturity period type, the dormancy period type, and the churn period type, is further divided into 5 sub-types based on the user assets from low to high, respectively.
Step S202, determining basic index data of the target user according to the user type of the target user and the use data of the target user in a preset application program.
The usage data of the target user in the preset application program may include browsing records, product purchasing records, login records, and other data.
Specifically, after the user category of the target user is obtained, the basic index data that the target user needs to extract may be determined based on the corresponding relationship between the user category and the basic index data, and then the basic index data of the target user may be extracted based on the usage data of the target user in the preset application program.
Specifically, a unique user identification code may be set for each user, so as to obtain the usage data of the target user in the preset application program from the server based on the user identification code.
In some embodiments, the number of the preset applications may be multiple, and the information push device or the information push server may read, from the server of each preset application, the usage data of the target user in each preset application based on the user identifier of the target user, and further determine the basic index data of the target user based on the user type of the target user and the usage data of the target user in each preset application.
Optionally, the basic index data includes one or more of time for registering the preset application program, time for logging in the preset application program, a subscription record, a browsing record, time for logging out the preset application program, and the like, asset distribution, login times, subscription frequency, and push browsing frequency.
Specifically, different user types have different basic index data to be extracted.
In some embodiments, if the life cycle of the target user is an introduction period or the type of the target user is an introduction period type, the basic index data corresponding to the target user may include a browsing record and a source channel, where the source channel is used to describe a channel through which the user browses the push content, and may be a preset application program, an application program associated with the preset application program, an applet, a web page, and the like. If the life cycle of the target user is a growth period or the type of the target user is a growth period type, the basic index data corresponding to the target user can be a subscription record, a browsing record, asset distribution, login times, a subscription frequency and a push browsing frequency. If the life cycle of the target user is the maturity period or the type of the target user is the maturity period type, the basic index data corresponding to the target user can be the contract signing record, the browsing record, the asset distribution and the pushing browsing frequency. If the life cycle of the target user is a sleep period or the type of the target user is a sleep period type, the basic index data corresponding to the target user may include time for logging in a preset application, a subscription record, a browsing record and asset distribution. If the life cycle of the target user is the churn period or the type of the target user is the churn period type, the basic index data corresponding to the target user may include time for logging in a preset application program, a subscription record and a browsing record.
Specifically, basic index data to be extracted may be set in advance for each user type, and the number and content of the basic index data corresponding to different user types may be different.
Step S203, determining the push content of the target user according to the basic index data of the target user.
Specifically, after the basic index data of the target user is determined or extracted, the pushed content matched with the basic index data of the target user can be determined from the pushed content library according to a preset matching rule based on the basic index data of the target user. The push content library can store various financial products and preferential activities which need to be pushed.
Specifically, the basic index data of the user may be input into a pre-designed or built analysis model, and then the pushed content matched with the basic index data of the target user is determined from the pushed content library.
In some embodiments, the analytical model may be a Neural network model, such as a Self-Organizing feature mapping (SOFM) network model, a Convolutional Neural network model (CNN), and so on.
The information push method provided by the embodiment of the application aims at content push in a financial ecological scene, and achieves automatic determination of basic index data of a user according to the type of the user and the use data of the user in a preset application program, and then matching of pushed content is conducted based on the basic index data, so that automatic push of pushed content such as products and preferential activities is achieved, content push efficiency is improved, push accuracy is high, user experience of using the preset application program is improved, and user activity and satisfaction are improved.
Fig. 3 is a flowchart of an information pushing method according to another embodiment of the present application, where the information pushing method according to this embodiment is further detailed in step S201 to step S203 based on the embodiment shown in fig. 2, and as shown in fig. 3, the information pushing method according to this embodiment may include the following steps:
step S301, acquiring the behavior data of the target user.
Step S302, determining the customer life cycle of the target user according to the behavior data of the target user.
Step S303, acquiring the user assets of the target user recorded in the preset application program.
Step S304, determining the user type of the target user according to the customer life cycle of the target user and the user assets of the target user.
Specifically, the user type of the target user may be determined according to the range of the user assets of the target user and the customer life cycle of the target user.
Specifically, the user types may be divided into five first types, i.e., an introduction period, a growth period, an maturity period, a dormancy period, and a churn period, according to the customer life cycle of the user, and further, the user types of each user are divided into a plurality of second types, e.g., 3 types, 5 types, e.g., a low asset type, a medium asset type, and a high asset type, based on the user assets of the user from high to low. Combining the first type and the second type, the user type of each user can be obtained.
For example, if the first type of the target user is a growth-period type A2 and the second type is a higher-asset type B4, the target type of the target user may be an A2B4 type.
Step S305, determining each index to be extracted of the target user according to the user type of the target user.
Specifically, each index to be extracted, which needs to be extracted and corresponds to the type identification code, can be obtained according to the type identification code of the user type of the target user, so that each index to be extracted of the target user can be obtained. And the indexes to be extracted are different corresponding to different user types.
Optionally, determining each index to be extracted of the target user according to the user type of the target user includes:
acquiring a pre-established index corresponding relation, wherein the index corresponding relation is used for representing indexes to be extracted corresponding to various user types; and determining each index to be extracted of the target user according to the user type of the target user and the index corresponding relation.
Specifically, each index to be extracted corresponding to the user type may be searched from the index correspondence based on the user type of the target user, and the index to be extracted corresponding to the user type may be used as each index to be extracted of the target user.
Step S306, extracting, according to each index to be extracted of the target user, each basic index data of the target user from the usage data of the target user in the preset application program.
Specifically, after determining each index to be extracted of the target user, the server may send each index to be extracted to the server of the corresponding preset application program according to the preset application program corresponding to each index to be extracted, and then the server of the preset application program obtains the usage data of the preset application program of the target user stored on the server, and obtains the basic index data of the corresponding one or more indexes to be extracted, and sends the basic index data of the corresponding one or more indexes to be extracted to the message push device or the message push server.
In some embodiments, the server of each preset application may send the usage data of the preset application of the target user to the message pushing device or the message pushing server at regular time or at irregular time, so that the message pushing device or the message pushing server extracts, according to each index to be extracted of the target user, each basic index data of the target user from the usage data of the target user in each preset application.
Step S307, determining the push content of the target user according to each basic index data of the target user and the analysis model corresponding to the user type of the target user.
Specifically, the analysis models corresponding to various user types may be established in advance.
Specifically, for each user type, the pushed content of each sample user can be determined by an expert according to the basic index data of each sample user of the user type, the sample data consisting of the basic index data and the pushed content of each sample user is divided into a training set and a verification set according to a set proportion, such as 8:2, 9:1, 7:3 and the like, an analysis model of the user type is trained based on the training set, parameters of the analysis model are adjusted through back propagation, the trained analysis model is verified based on the verification set, the parameters of the analysis model are further adjusted based on the verification result until the analysis model reaches the training termination condition, and the trained analysis model is output for use and further reaches the analysis models corresponding to the user types.
Specifically, each piece of basic index data of the target user may be input into an analysis model corresponding to the user type of the target user, so that the push content corresponding to the target user is output through an output layer of the analysis model.
Specifically, based on the user type of the target user, an analysis model matched with the user type is determined, basic index data of the target user is input into the matched analysis model, so that a push tag of push content of the target user is obtained, and based on the push tag pushed in, the push content of the target user is determined from a push content library.
Furthermore, the push mode of the push content can be determined according to the life cycle of the client of the target user, wherein the push mode comprises a push mode through a preset application program, a push mode through a short message, a push mode through a telephone and the like.
In the embodiment, for content push in a financial ecological scene, user types are accurately divided based on two factors, namely user assets and user life cycles, and a set of basic index data required to be extracted is formulated for various user types so as to adapt to different requirements of users of different user types; and then, based on each basic index data of the target user and the user type corresponding analysis model of the target user, the push content of the target user is automatically determined, so that the automatic determination of the push content is realized, the determined push content better meets the user requirements, and the satisfaction degree and the viscosity of the user are improved.
Fig. 4 is a flowchart of an information pushing method according to another embodiment of the present application, where the information pushing method according to this embodiment is further detailed in step S203 on the basis of the embodiment shown in fig. 2, and a step of adjusting an analysis model based on a derivative index is added after step S203, as shown in fig. 4, the information pushing method according to this embodiment may include the following steps:
step S401, a user type of each target user is obtained.
Step S402, aiming at each target user, determining basic index data of the target user according to the user type of the target user and the use data of the target user in a preset application program.
Step S403, for each target user, determining push content of the target user according to the basic index data of the target user and the analysis model corresponding to the user type of the target user.
Step S404, according to a set period, determining derivative indexes corresponding to various user types according to the basic index data and promotion paths of various users.
The promotion path is used for describing the change situation of the customer life cycle of the user in each set period. The derived index is an index obtained on the basic index data and used for evaluating the pushing effect.
After determining the push content of each user for a period of time based on the analysis model corresponding to each user type, the push effect needs to be evaluated according to a set period, such as 7 days, 10 days, 15 days, or other time lengths. Specifically, the derived indexes corresponding to various user types may be calculated according to the recorded basic index data of each user in the current setting period and the promotion path of each user.
In some embodiments, a mulberry map corresponding to the current set period may be drawn and displayed according to the promotion path of each user within the current set period, so as to visually display the transition situation of each user.
In some embodiments, the derived metrics may include metrics such as user conversion rate, subscription conversion rate, user activity, user churn rate, and the like.
The user conversion rate is specific to the user in the introduction period and is used for describing the proportion of the user in the introduction period converted into the user in the growth period. The contract conversion rate is specific to the users in the growth period and the maturity period, and is used for describing the proportion of the number of the users in the growth period and the maturity period who contract the products corresponding to the push content to the number of the users reading the push content. The user activity can be determined according to indexes such as user login times, online time, push browsing frequency, signed product frequency and the like, and is used for describing the activity degree of the user using the preset application program in the current set period.
Step S405, aiming at each user type, generating an evaluation report of the analysis model corresponding to the user type according to the derivative index corresponding to the user type, so as to adjust the analysis model corresponding to the user type based on the evaluation report.
Specifically, after the derivative indexes corresponding to various user types are obtained, the pushing effect of the analysis model of the user type can be evaluated according to the value range of the derivative index corresponding to each user type, and an evaluation report is generated, so that an operator can know the pushing effect of the analysis model accurately.
Further, a pushing score of the analysis model of each user type may be calculated based on the derived index corresponding to the user type, and if the pushing score is lower than a preset score, such as 60, 55, 50, etc., a model adjustment report is generated to remind an operator to adjust parameters of the analysis model of the user type, or to perform training of the analysis model of the user type again, so as to improve accuracy of the analysis model, thereby improving service quality of a preset application program.
In the embodiment, for content push in a financial ecological scene, basic index data of a user is automatically determined according to the user type and use data of the user in a preset application program, and then push content of a target user of the user type is automatically determined based on the basic index data and an analysis model corresponding to the user type, so that automatic push of push content such as products and preferential activities is realized, and content push efficiency is improved; and calculating derived indexes of the analysis models of various user types according to a set period based on basic index data and promotion paths of users, and further evaluating and adjusting the analysis models based on the derived indexes to improve the pushing accuracy of the analysis models, so that contents which are more in line with the preference and the requirements of the users are pushed for the users, and the activity of the users is improved.
Fig. 5 is a schematic structural diagram of an information pushing apparatus according to an embodiment of the present application, and as shown in fig. 5, the information pushing apparatus according to the embodiment includes: a user type obtaining module 510, an index data determining module 520 and a push content determining module 530.
The user type obtaining module 510 is configured to obtain a user type of a target user; an index data determining module 520, configured to determine basic index data of the target user according to the user type of the target user and usage data of the target user in a preset application program; a push content determining module 530, configured to determine, according to the basic index data of the target user, the push content of the target user.
Optionally, the user type obtaining module 510 is specifically configured to:
acquiring behavior data of the target user; and determining the user type of the target user according to the behavior data of the target user.
Optionally, the user type obtaining module 510 includes:
the period determining unit is used for determining the customer life cycle of the target user according to the behavior data of the target user; the user type determining unit is used for determining the user type of the target user according to the customer life cycle of the target user; wherein the behavioral data comprises: the time of browsing the pushed content for the first time, the time of registering the preset application program, the time of signing a product for the first time, the time of signing a product for the last time, and the time of logging off the preset application program.
Optionally, the user type determining unit is specifically configured to:
acquiring the user assets of the target user recorded in a preset application program; and determining the user type of the target user according to the customer life cycle of the target user and the user assets of the target user.
Optionally, the index data determining module 520 includes:
the to-be-extracted item determining unit is used for determining each to-be-extracted index of the target user according to the user type of the target user; and the index data extraction unit is used for extracting each basic index data of the target user from the use data of the target user in the preset application program according to each index to be extracted of the target user.
Optionally, the to-be-extracted item determining unit is specifically configured to:
acquiring a pre-established index corresponding relation, wherein the index corresponding relation is used for representing indexes to be extracted corresponding to various user types; and determining each index to be extracted of the target user according to the user type of the target user and the index corresponding relation.
Optionally, the basic index data includes one or more of time for registering the preset application program, time for logging in the preset application program, a subscription record, a browsing record, time for logging out the preset application program, and the like, asset distribution, login times, subscription frequency, and push browsing frequency.
Optionally, the apparatus further comprises:
and the model establishing module is used for establishing analysis models corresponding to various user types in advance.
Optionally, the push content determining module 530 is specifically configured to:
and determining the push content of the target user according to the basic index data of the target user and the analysis model corresponding to the user type of the target user.
Optionally, the apparatus further comprises:
the derivative index determining module is used for determining derivative indexes corresponding to various user types according to the set period and the basic index data and promotion paths of various users; and the model adjusting module is used for generating an evaluation report of the analysis model corresponding to the user type according to the derivative indexes corresponding to the user type aiming at each user type so as to adjust the analysis model corresponding to the user type based on the evaluation report.
The information pushing device provided by the embodiment of the application can execute the information pushing method provided by any embodiment corresponding to fig. 2 to 4 of the application, and has the corresponding functional modules and beneficial effects of the execution method.
Fig. 6 is a schematic structural diagram of an information pushing apparatus according to an embodiment of the present application, and as shown in fig. 6, the information pushing apparatus includes: memory 610, processor 620, and computer programs.
The computer program is stored in the memory 610 and configured to be executed by the processor 620 to implement the information pushing method provided in any embodiment corresponding to fig. 2 to 4 of the present application. The transparent transmission device can be the main equipment or the auxiliary equipment.
Wherein the memory 610 and the processor 620 are connected by a bus 630.
The related description may be understood by referring to the related description and effect corresponding to the steps in fig. 2 to fig. 4, and redundant description is not repeated here.
An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the information pushing method provided in any embodiment corresponding to fig. 2 to 4 of the present application.
The computer readable storage medium may be, among others, ROM, Random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like.
An embodiment of the present application provides a computer program product, which includes a computer program, and the computer program is executed by a processor of an information pushing apparatus to control an information pushing device to implement the information pushing method provided in any embodiment corresponding to fig. 2 to 4 of the present application.
The processor may be an integrated circuit chip having signal processing capabilities. The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of modules is merely a division of logical functions, and an actual implementation may have another division, for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may be in an electrical, mechanical or other form.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (13)
1. An information pushing method, characterized in that the method comprises:
acquiring a user type of a target user;
determining basic index data of the target user according to the user type of the target user and the use data of the target user in a preset application program;
and determining the push content of the target user according to the basic index data of the target user.
2. The method of claim 1, wherein obtaining the user type of the target user comprises:
acquiring behavior data of the target user;
and determining the user type of the target user according to the behavior data of the target user.
3. The method of claim 2, wherein determining the user type of the target user based on the behavior data of the target user comprises:
determining the customer life cycle of the target user according to the behavior data of the target user;
determining the user type of the target user according to the customer life cycle of the target user;
wherein the behavioral data comprises: the time of browsing the pushed content for the first time, the time of registering the preset application program, the time of signing a product for the first time, the time of signing a product for the last time, and the time of logging off the preset application program.
4. The method of claim 3, wherein determining the user type of the target user based on the customer lifecycle of the target user comprises:
acquiring the user assets of the target user recorded in a preset application program;
and determining the user type of the target user according to the customer life cycle of the target user and the user assets of the target user.
5. The method of claim 1, wherein determining the base indicator data of the target user according to the user type of the target user and the usage data of the target user in a preset application program comprises:
determining each index to be extracted of the target user according to the user type of the target user;
and extracting each basic index data of the target user from the use data of the target user in the preset application program according to each index to be extracted of the target user.
6. The method according to claim 5, wherein determining each index to be extracted of the target user according to the user type of the target user comprises:
acquiring a pre-established index corresponding relation, wherein the index corresponding relation is used for representing indexes to be extracted corresponding to various user types;
and determining each index to be extracted of the target user according to the user type of the target user and the index corresponding relation.
7. The method of claim 1, wherein the base index data comprises one or more of time to register the preset application, time to log in the preset application, sign-up record, browsing record, time to log out the preset application, asset distribution, number of log-ins, sign-up frequency, and push browsing frequency.
8. The method according to any one of claims 1 to 7, wherein determining the push content of the target user according to the basic index data of the target user comprises:
and determining the push content of the target user according to the basic index data of the target user and the analysis model corresponding to the user type of the target user.
9. The method of claim 8, further comprising:
according to a set period, determining derivative indexes corresponding to various user types according to basic index data and promotion paths of various users;
and aiming at each user type, generating an evaluation report of the analysis model corresponding to the user type according to the derivative indexes corresponding to the user type, so as to adjust the analysis model corresponding to the user type based on the evaluation report.
10. An information pushing apparatus, characterized in that the apparatus comprises:
the user type acquisition module is used for acquiring the user type of the target user;
the index data determining module is used for determining basic index data of the target user according to the user type of the target user and the use data of the target user in a preset application program;
and the push content determining module is used for determining the push content of the target user according to the basic index data of the target user.
11. An information push apparatus characterized by comprising: a memory and at least one processor;
the memory stores computer-executable instructions;
the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the information pushing method of any one of claims 1-9.
12. A computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the information push method according to any one of claims 1 to 9 is implemented.
13. A computer program product comprising a computer program, characterized in that the computer program realizes the information pushing method according to any of claims 1-9 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111632951.7A CN114285896B (en) | 2021-12-28 | 2021-12-28 | Information pushing method, device, equipment, storage medium and program product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111632951.7A CN114285896B (en) | 2021-12-28 | 2021-12-28 | Information pushing method, device, equipment, storage medium and program product |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114285896A true CN114285896A (en) | 2022-04-05 |
| CN114285896B CN114285896B (en) | 2023-07-07 |
Family
ID=80877518
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111632951.7A Active CN114285896B (en) | 2021-12-28 | 2021-12-28 | Information pushing method, device, equipment, storage medium and program product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114285896B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115314845A (en) * | 2022-08-01 | 2022-11-08 | 青岛海尔施特劳斯水设备有限公司 | Message sending method, device, server and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170364933A1 (en) * | 2014-12-09 | 2017-12-21 | Beijing Didi Infinity Technology And Development Co., Ltd. | User maintenance system and method |
| US20200236184A1 (en) * | 2017-09-21 | 2020-07-23 | Zhangyue Technology Co., Ltd. | Method, electronic device and computer storage medium for pushing information |
| CN112148973A (en) * | 2020-09-04 | 2020-12-29 | 京东数字科技控股股份有限公司 | Data processing method and device for information push |
| CN113836426A (en) * | 2021-09-29 | 2021-12-24 | 上海淇玥信息技术有限公司 | Information pushing method and device and electronic equipment |
-
2021
- 2021-12-28 CN CN202111632951.7A patent/CN114285896B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170364933A1 (en) * | 2014-12-09 | 2017-12-21 | Beijing Didi Infinity Technology And Development Co., Ltd. | User maintenance system and method |
| US20200236184A1 (en) * | 2017-09-21 | 2020-07-23 | Zhangyue Technology Co., Ltd. | Method, electronic device and computer storage medium for pushing information |
| CN112148973A (en) * | 2020-09-04 | 2020-12-29 | 京东数字科技控股股份有限公司 | Data processing method and device for information push |
| CN113836426A (en) * | 2021-09-29 | 2021-12-24 | 上海淇玥信息技术有限公司 | Information pushing method and device and electronic equipment |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115314845A (en) * | 2022-08-01 | 2022-11-08 | 青岛海尔施特劳斯水设备有限公司 | Message sending method, device, server and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114285896B (en) | 2023-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107730389A (en) | Electronic installation, insurance products recommend method and computer-readable recording medium | |
| CN105023165A (en) | Method, device and system for controlling release tasks in social networking platform | |
| CN107808346B (en) | Evaluation method and evaluation device for potential target object | |
| CN104579909B (en) | Method and equipment for classifying user information and acquiring user grouping information | |
| CN111178983B (en) | User gender prediction method, device, equipment and storage medium | |
| US20200074509A1 (en) | Business data promotion method, device, terminal and computer-readable storage medium | |
| CN110798567A (en) | Short message classification display method and device, storage medium and electronic equipment | |
| CN107633257B (en) | Data quality evaluation method and device, computer readable storage medium and terminal | |
| JP2011227721A (en) | Interest extraction device, interest extraction method, and interest extraction program | |
| CN109711917A (en) | Information-pushing method and device | |
| CN111695938B (en) | Product pushing method and system | |
| CN111104590A (en) | Information recommendation method, device, medium and electronic equipment | |
| CN111311294A (en) | Data processing method, device, medium and electronic equipment | |
| CN113592535A (en) | Advertisement recommendation method and device, electronic equipment and storage medium | |
| CN111626767A (en) | Resource data distribution method, device and equipment | |
| CN104572775A (en) | Advertisement classification method, device and server | |
| CN114285896B (en) | Information pushing method, device, equipment, storage medium and program product | |
| CN108959289B (en) | Website category acquisition method and device | |
| CN112950359A (en) | User identification method and device | |
| CN112287208B (en) | User portrait generation method, device, electronic equipment and storage medium | |
| CN112330373A (en) | User behavior analysis method and device and computer readable storage medium | |
| CN112085332A (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN111858686A (en) | Data display method and device, terminal equipment and storage medium | |
| CN111340062A (en) | Mapping relation determining method and device | |
| CN111445284B (en) | Determination method and device of orientation label, computing equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |