CN113626705B - User retention analysis method, device, electronic equipment and storage medium - Google Patents
User retention analysis method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113626705B CN113626705B CN202110915583.0A CN202110915583A CN113626705B CN 113626705 B CN113626705 B CN 113626705B CN 202110915583 A CN202110915583 A CN 202110915583A CN 113626705 B CN113626705 B CN 113626705B
- Authority
- CN
- China
- Prior art keywords
- user
- user group
- retention rate
- predicted value
- users
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of data analysis, and provides a user retention analysis method, a device, electronic equipment and a storage medium. Obtaining a first predicted value set of the first user group with specific behavior characteristics according to the behavior characteristic set of the first user group; then, based on the first predicted value set, a second user group is obtained, and the second predicted value set of the second user group with specific behavior characteristics is different from the first predicted value set by a preset range; and finally, obtaining the relation between the specific behavior characteristic and the retention rate according to the first retention rate of the first user group and the second retention rate of the second user group. Therefore, the first user group and the second user have an association relationship by setting conditions of the first predicted value set and the second predicted value set. The analysis of the retention rate of the user is realized, and the influence of the selective deviation is avoided, so that an accurate result is obtained, and the analysis of key influence factors is facilitated.
Description
Technical Field
The present invention relates to the field of data analysis technologies, and in particular, to a method and apparatus for user retention analysis, an electronic device, and a storage medium.
Background
With the development of technology, the big data processing analysis can be applied to social service, game service, live broadcast service and other service scenes.
In these business scenarios, it is necessary to analyze the retention of the user. In the related art, due to the fact that the service scene is updated or the selected test user has deviation, prediction is inaccurate or low in accuracy.
Disclosure of Invention
In view of the above, the present invention aims to provide a user retention analysis method, a device, an electronic apparatus and a storage medium.
In order to achieve the above object, the technical scheme adopted by the embodiment of the invention is as follows:
in a first aspect, the present invention provides a method for user retention analysis, the method comprising:
obtaining a first predicted value set of the first user group with specific behavior characteristics according to the behavior characteristic set of the first user group;
acquiring a second user group according to the first predicted value set; a second predicted value set of the second user group with the specific behavior characteristics is different from the first predicted value set by a preset range;
and obtaining the relation between the specific behavior characteristic and the retention rate according to the first retention rate of the first user group and the second retention rate of the second user group.
In an alternative embodiment, the first user group includes a plurality of first users, and the behavior feature set of the first user group includes a behavior feature of each of the first users;
the step of obtaining a first predicted value set of the first user group with specific behavior characteristics according to the behavior characteristic set of the first user group comprises the following steps:
obtaining a first estimated value of each first user with the specific behavior characteristics according to the behavior characteristics and the prediction model of each first user;
and obtaining the first predicted value set according to all the first estimated values.
In an alternative embodiment, the first set of predictors includes a plurality of first predictors;
the step of obtaining the second user group according to the first predicted value set includes:
acquiring behavior characteristics of a plurality of undetermined users;
obtaining a second estimated value of each undetermined user with the specific behavior characteristics according to the behavior characteristics of each undetermined user and the prediction model;
determining a plurality of target users from the plurality of pending users; the second estimated value of each target user is different from one of the first predicted values by a preset range; the second group of users includes all target users.
In an alternative embodiment, the step of obtaining the relationship between the specific behavior feature and the retention rate according to the first retention rate of the first user group and the second retention rate of the second user group includes:
obtaining a retention rate difference value according to the first retention rate of the first user group and the second retention rate of the second user group;
and obtaining the relation between the specific behavior characteristic and the retention rate according to the preset range and the retention rate difference value.
In a second aspect, the present invention provides a user retention analysis device, the device comprising:
the system comprises an acquisition module, a prediction module and a prediction module, wherein the acquisition module is used for acquiring a first predicted value set of a first user group with specific behavior characteristics according to the behavior characteristic set of the first user group;
the determining module is used for acquiring a second user group according to the first predicted value set; the first predicted value set and a second predicted value set of the second user group with the specific behavior characteristics are different by a preset range;
and the analysis module is used for obtaining the relation between the specific behavior characteristic and the retention rate according to the first retention rate of the first user group and the second retention rate of the second user group.
In an alternative embodiment, the first user group includes a plurality of first users, and the behavior feature set of the first user group includes a behavior feature of each of the first users; the acquisition module has a function for:
obtaining a first estimated value of each first user with the specific behavior characteristics according to the behavior characteristics and the prediction model of each first user;
and obtaining the first predicted value set according to all the first estimated values.
In an alternative embodiment, the first set of predictors includes a plurality of first predictors; the determining module is specifically configured to:
acquiring behavior characteristics of a plurality of undetermined users;
obtaining a second estimated value of each undetermined user with the specific behavior characteristics according to the behavior characteristics of each undetermined user and the prediction model;
determining a plurality of target users from the plurality of pending users; the second estimated value of each target user is different from one of the first predicted values by a preset range; the second group of users includes all target users.
In an alternative embodiment, the analysis module is specifically configured to:
obtaining a retention rate difference value according to the first retention rate of the first user group and the second retention rate of the second user group;
and obtaining the relation between the specific behavior characteristic and the retention rate according to the preset range and the retention rate difference value.
In a third aspect, the invention provides an electronic device comprising a processor and a memory, the memory storing a computer program, the processor implementing the method of any of the preceding embodiments when executing the computer program.
In a fourth aspect, the present invention provides a storage medium having stored thereon a computer program which, when executed by a processor, implements a method according to any of the preceding embodiments.
The embodiment of the invention provides a user retention analysis method, a device, electronic equipment and a storage medium. Obtaining a first predicted value set of the first user group with specific behavior characteristics according to the behavior characteristic set of the first user group; then, based on the first predicted value set, a second user group is obtained, and the second predicted value set of the second user group with specific behavior characteristics is different from the first predicted value set by a preset range; and finally, obtaining the relation between the specific behavior characteristic and the retention rate according to the first retention rate of the first user group and the second retention rate of the second user group. Therefore, the first user group and the second user have an association relationship by setting conditions of the first predicted value set and the second predicted value set. Compared with the prior art, the method can avoid selective deviation in the process of selecting and testing the user, realize analysis of the retention rate of the user, obtain accurate results and is beneficial to analyzing key influencing factors.
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
Fig. 1 shows a schematic view of a scenario provided by an embodiment of the present invention;
fig. 2 is a schematic block diagram of an electronic device according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of a user retention analysis method according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart of a user retention analysis method according to an embodiment of the present invention;
FIG. 5 is a schematic flow chart of a user retention analysis method according to an embodiment of the present invention;
FIG. 6 is a schematic flow chart of a user retention analysis method according to an embodiment of the present invention;
fig. 7 is a functional block diagram of a user retention analysis device according to an embodiment of the present invention.
Icon: 100-server; 102-terminal equipment; a 120-processor; 130-memory; 170-a communication interface; 300-user retention analysis means; 310-an acquisition module; 330-a determination module; 350-analysis module.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present invention.
It is noted that relational terms such as "first" and "second", and the like, are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the prior art, for the retention analysis of the user, an AB test mode can be adopted to implement a strategy on an experimental group so as to be compared with a control group, but the feasibility and the accuracy of the mode have great difficulty. Or adopting a mode of selecting two test user groups, and analyzing key factors influencing the retention rate based on the retention rates of the two test user groups. However, in this way, the selection of the test user population is strict, which may cause inaccurate analysis results due to a selection bias (selection bias) of the test user population. The embodiment of the invention further provides a user retention analysis method to solve the technical problems of the related technology, and the user retention analysis method provided by the embodiment of the invention is described below.
Fig. 1 is a schematic view of a scenario provided in an embodiment of the present invention. The system comprises a server 100 and a plurality of terminal devices 102, wherein the server 100 is in communication connection with the plurality of terminal devices 102 to realize data interaction.
The server 100 may be a stand-alone server or a server cluster composed of a plurality of servers.
The terminal device 102 may be a smart phone, personal computer, tablet, wearable device, notebook, ultra-mobile personal computer (UMPC), netbook, personal digital assistant (Personal Digital Assistant, PDA), or the like. The embodiment of the present invention is not limited in any way.
Optionally, the scene graph may be used to provide a variety of possible services including, but not limited to: multimedia streaming services, cloud gaming, distributed storage, etc. Taking live video as an example, the server 100 may be a server providing live video streaming, and the terminal device 102 may install live video related Application (APP).
The server 100 may collect and analyze data related to the live video application in the terminal device 102 for different analysis purposes. The terminal device 102 may obtain relevant data of the user when using the live video application, and report the relevant data to the server 100.
Fig. 2 is a block diagram of an electronic device according to an embodiment of the invention. The electronic device includes a processor 120, a memory 130, and a communication interface 170.
The processor 120, the memory 130, and the communication interface 170 are electrically connected directly or indirectly to each other to realize data transmission or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The user retention analysis device 300 includes at least one software functional module that may be stored in the memory 130 in the form of software or firmware (firmware) or cured in an Operating System (OS) of the server 100. The processor 120 is configured to execute executable modules stored in the memory 130, such as software functional modules or computer programs included in the user retention analysis device 300.
The processor 120 may be an integrated circuit chip with signal processing capability. The processor 120 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; but may also be a Digital Signal Processor (DSP), application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The Memory 130 may be, but is not limited to, a random access Memory 130 (Random Access Memory, RAM), a Read Only Memory 130 (ROM), a programmable Read Only Memory 130 (Programmable Read-Only Memory, PROM), an erasable Read Only Memory 130 (Erasable Programmable Read-Only Memory, EPROM), an electrically erasable Read Only Memory 130 (Electric Erasable Programmable Read-Only Memory, EEPROM), etc. The memory 130 is configured to store a program, and the processor 120 executes the program after receiving an execution instruction, and the method executed by the server 100 according to the process definition disclosed in any embodiment of the present invention may be applied to the processor 120 or implemented by the processor 120.
The communication interface 170 may be used for communication of signaling or data with other node devices.
It should be noted that the structure shown in fig. 2 is only a schematic structural diagram of the electronic device, and the electronic device may further include more or fewer components than those shown in fig. 2, or have a different configuration from that shown in fig. 2. The components shown in fig. 2 may be implemented in hardware, software, or a combination thereof.
It will be appreciated that the electronic device shown in fig. 2 may be configured to implement the server 100 or the terminal device 102 in fig. 1 described above; the electronic device may further comprise other modules for realizing the respective functions of the terminal device, such as: radio frequency circuitry, I/O interfaces, batteries, touch screens, microphones/speakers, etc. And are not limited herein.
The steps in the methods provided in the embodiments of the present invention are executed with the server 100 as an execution body, and corresponding technical effects are achieved.
Referring to fig. 3, fig. 3 is a flowchart illustrating a user retention analysis method according to an embodiment of the invention.
Step S202, obtaining a first predicted value set of the first user group with specific behavior characteristics according to the behavior characteristic set of the first user group;
it can be understood that, in the process of using the application program, the terminal device can obtain the use condition of the user, namely, the behavior feature.
The specific behavior feature refers to a preset behavior feature for analyzing the influence of the specific behavior feature on the retention rate of the user. For example, a subscription behavior is a particular behavior feature when analyzing the impact of this behavior feature on user retention.
Alternatively, a plurality of users may be preset as the first user group, for example, in a live broadcast service scenario, in a process of using a live video application program, a terminal device of the user may collect behavior features of the user, such as a viewing duration, a viewing day, a viewing number of times, a barrage, a registration duration, an active day, a viewing anchor number, a level, and the like, and then send the behavior features to the server.
After receiving the behavior characteristics of each user, the server can obtain a behavior characteristic set of the first user group, and according to the behavior characteristic set, a first predicted value set of the first user group with specific behavior characteristics can be obtained. This first set of predictors may be understood as being a scoring value representing the propensity of the first group of users to produce the particular behavioral characteristic.
Step S204, obtaining a second user group according to the first predicted value set;
optionally, after the server obtains the first set of predicted values of the first user group, the server may obtain the second user group according to the first set of predicted values.
Optionally, the second set of predicted values and the first set of predicted values of the second user group with specific behavior characteristics meet a preset condition, where the preset condition may be that the second set of predicted values and the first set of predicted values differ by a preset range, e.g., a difference between the second set of predicted values and the first set of predicted values may be a preset multiple of the first set of predicted values. The second set of predictors may be understood as being a predisposition score for representing that the second group of users has a specific behavioral characteristic.
It can be understood that, if the first predicted value set of the first user group and the second predicted value set of the second user group meet the preset condition, a certain association relationship exists between the first user group and the second user group.
Step S206, obtaining the relation between the specific behavior characteristics and the retention rate according to the first retention rate of the first user group and the second retention rate of the second user group;
optionally, after the first user group and the second user group are obtained, the retention rates of the two users, that is, the first retention rate of the first user group and the second retention rate of the second user group, may be calculated respectively, and based on the retention rates of the two user groups, the relationship between the specific behavior feature and the retention rate, that is, the influence of the specific behavior feature on the user retention rate may be obtained.
For ease of understanding, the above steps will be described below with respect to subscription behavior as a specific behavior feature, by way of example with reference to the schematic diagram of the scenario shown in fig. 1.
As shown in fig. 1, the number of the first user groups may be preset, and the behavior feature sets of the first user groups may be acquired through the plurality of terminal devices 102, where the behavior feature sets include behavior features such as a viewing duration, a viewing day, a viewing frequency, a barrage, a registration duration, an active day, a viewing anchor number, a level, and the like; each terminal device 102 then reports the collected behavioral characteristics to the server 100.
After the server 100 obtains the behavior feature set of the first user group, according to the behavior feature set of the first user group, a first predicted value set of the first user group with specific behavior features is obtained, and then a tendency score of the first user group with subscription behaviors is obtained.
And then, according to the first predicted value set, acquiring a second user group, wherein the second predicted value set of the second user group with the specific behavior characteristic is different from the first predicted value set by a preset range. Optionally, the average value of the first set of predicted values is a first average value, and the average value of the second set of predicted values is a second average value. The second set of predicted values differs from the first set of predicted values by a predetermined range, and the difference between the first average value and the second average value may be a predetermined multiple, such as 0.05 times, of the first average value.
After the server 100 obtains the second user group, a first retention rate of the first user group and a second retention rate of the second user group are obtained, and based on the retention rates of the two user groups, a relationship between a specific behavior feature and the retention rate, that is, an influence of subscription behavior and the user retention rate is obtained.
Based on the steps, a first predicted value set of the first user group with specific behavior characteristics is obtained according to the behavior characteristic set of the first user group; then, based on the first predicted value set, a second user group is obtained, and the second predicted value set of the second user group with specific behavior characteristics is different from the first predicted value set by a preset range; and finally, obtaining the relation between the specific behavior characteristic and the retention rate according to the first retention rate of the first user group and the second retention rate of the second user group. Therefore, the first user group and the second user have an association relationship by setting conditions of the first predicted value set and the second predicted value set. Compared with the prior art, the method can avoid selective deviation in the process of selecting and testing the user, realize analysis of the retention rate of the user, obtain accurate results and is beneficial to analyzing key influencing factors.
Optionally, as known from the above steps, the first predicted value set of the first user may affect the result analysis, so in order to improve accuracy, the embodiment of the present invention provides a possible implementation manner, please refer to fig. 4, wherein step S202 may further include the following steps:
step S202-1, obtaining a first estimated value of each first user with specific behavior characteristics according to the behavior characteristics and the prediction model of each first user;
wherein the first user group comprises a plurality of first users, and the behavior feature set of the first user group comprises the behavior feature of each first user;
the predictive model is a model previously built from a large number of test data that predicts the user's predisposition scores for producing a particular positioning feature based on the user's behavioral characteristics. If the predictive model is a logistic regression model: g (z) =1/(1+e-z), z representing behavioral characteristics, g (z) representing a predicted predisposition score for the user to develop a particular behavioral characteristic, which predisposition score may also be represented by s.
Alternatively, the behavior characteristics of each first user may be used as an input of a prediction model, and the output of the prediction model is the first estimated value of each first user with a specific behavior characteristic. The first estimate may be understood as a score representing the propensity of the first user to produce the particular behavioral characteristic.
Step S202-3, obtaining a first predicted value set according to all the first estimated values;
it will be appreciated that there may be outliers in all of the first estimates obtained, and that screening of all of the first estimates is required in order to avoid that these outliers affect the accuracy of the analysis results.
Alternatively, the mean and standard deviation may be calculated based on all the first estimated values, the mean may be represented by u, and the standard deviation may be represented by sigma, and then a set of first estimated values within a preset interval, such as a [ u-3 sigma, u+3 sigma ] interval, may be used as the first set of predicted values. It should be noted that, the preset interval may be designed according to actual requirements, and the embodiment of the present invention is not limited.
Through the steps, according to the behavior characteristics and the prediction model of each first user in the first user group, a first estimated value of each first user with specific behavior characteristics can be obtained, and then all the first estimated values are screened to obtain a first predicted value set. By screening out the abnormal values, the inaccuracy of analysis caused by the abnormal values is avoided, and the accuracy is improved.
Optionally, in the step, it is mentioned that the second user may be acquired based on the first set of predicted values, so that the first user group and the second user group have a certain association relationship. Further, the embodiment of the present invention provides a possible implementation manner, please refer to fig. 5, wherein step S204 may further include the following steps:
step S204-1, obtaining behavior characteristics of a plurality of undetermined users;
optionally, the behavior features of the plurality of pending users may be collected by the terminal device, and the behavior features of each pending user may be sent to the server, so that the server obtains the behavior features of the plurality of pending users.
Step S204-3, obtaining a second estimated value of each pending user with specific behavior characteristics according to the behavior characteristics and the prediction model of each pending user;
alternatively, the behavior characteristics of each pending user may be used as an input of a prediction model, and the output of the prediction model is the second estimated value of each pending user having a specific behavior characteristic. The second estimate may be understood as a score representing the propensity of the pending user to generate the particular behavioral characteristic.
Step S204-5, determining a plurality of target users from a plurality of undetermined users;
it is understood that the first predicted value set includes a plurality of first predicted values, and the first predicted value may be understood as a first estimated value in the above-mentioned preset interval.
Alternatively, a plurality of target users meeting a preset criterion may be determined from a plurality of undetermined users according to all the second estimated values, where the preset criterion is that the second estimated value of the target user differs from a first estimated value by a preset range, for example, a difference between the second estimated value of the target user and the first estimated value is a preset multiple of the first estimated value and the first estimated value is greater than the second estimated value.
Optionally, all target users meeting the preset standard in the plurality of undetermined users are used as the second user group.
For a better understanding of the present invention, the above steps will be further illustrated with respect to subscription behavior as a specific behavior feature.
For example, when analyzing the influence of subscription behaviors on user retention analysis, the user retention analysis method provided by the embodiment of the invention can enable the acquired two user groups to have relatively close tendencies in subscription behaviors such as subscription times, and meanwhile, certain differences exist in the subscription behaviors, so that the selective deviation brought by selecting users can be eliminated, and the influence of the subscription behaviors on the user retention can be accurately analyzed.
Assuming that whether the user is subject to policy intervention has an association with subscription behavior, a binary intervention T can be used to indicate whether the user is subject to policy intervention, i.e. T i =0 means that the user is not being intervened, T i =1 indicates that the user is being tampered with.
For each user i, it produces two results, Y, based on whether it is subject to policy intervention i0 And Y i1 . Wherein Y is i0 Indicating that the user is not exposed toDuring intervention, the retention probability of the intervention product is increased; y is Y i1 Indicating that the user has been tampered with, the probability of retention increases. The user-generated result may be represented by Y, e.g., T when the user is not being tampered with i When=0, y=y i0 。
To avoid selective bias, a user may be simulated as compared to the user itself, and then formulated: att=e [ Y i1 -Y i0 |T＝1]T=1 denotes the user who is being intervened, ATT denotes the average impact that the policy has on the user who is being intervened.
However, for a user, it is neither possible nor possible to intervene, i.e. Y in the above formula i1 -Y i0 And cannot be calculated. Furthermore, the target user which is relatively close to the user in subscription behavior can be obtained through the user retention analysis method provided by the embodiment of the invention, so that the two user groups, namely the first user group and the second user group, have homogeneity. The user' S subscription behavior tendency score S can be expressed as: s=pr [ t= 1|X =x]X represents the behavior characteristics of the user, and t=1 represents the user who is being intervened.
Furthermore, based on the behavior characteristics and the prediction model of each first user in the first user group, a first estimated value, which is a tendency score of subscription behavior of each first user, can be obtained, and after all the first estimated values are filtered, a plurality of first predicted values, namely a first predicted value set, are obtained.
According to the first predicted value, a target user corresponding to the first predicted value is obtained, wherein the tendency score of the subscription behavior of the target user, namely the second estimated value, is different from the first predicted value by a preset range, for example, the difference between the second estimated value and the first predicted value is 0.05 times of the first predicted value, and the first predicted value is larger than the second estimated value.
It can be seen that, based on each first predicted value in the first predicted value set, target users meeting preset criteria are obtained, and all target users are used as the second user group. The method can avoid the selective difference between the first user group and the second user group, further eliminate the influence caused by the selective difference and improve the analysis accuracy.
For the step S206, a possible implementation manner is provided in the embodiment of the present invention. Referring to fig. 6, step S206 may further include the following steps:
step S206-1, obtaining a retention rate difference value according to the first retention rate of the first user group and the second retention rate of the second user group;
optionally, after the first user group and the second user group are acquired, a retention rate average of the first user group, that is, a first retention rate, and a retention rate average of the second user group, that is, a second retention rate, may be calculated. The first retention may be denoted by u1 and the second retention by u2, the retention difference u3=u1-u 2.
Step S206-3, obtaining the relation between the specific behavior characteristics and the retention rate according to the preset range and the retention rate difference;
optionally, after the retention rate difference is obtained, a relationship between the specific behavior feature and the retention rate may be obtained according to the preset range and the retention rate difference.
For example, taking the subscription behavior as a specific behavior feature example, when the preset range is 5%, that is, when the difference between the first predicted value of the first user and the second estimated value of the corresponding target user is 0.05 times of the first predicted value. It will be appreciated that when the behavioral tendentiousness score of a user varies by 5%, the retention of that user varies by u3. The influence of the subscription behavior on the retention of the user, i.e. the relation of the specific behavior characteristics and the retention, can be obtained.
In order to perform the respective steps of the above embodiments and of the various possible ways, an implementation of a user retention analysis device is presented below. Referring to fig. 7, fig. 7 is a functional block diagram of a user retention analysis device 300 according to an embodiment of the invention. It should be noted that, the basic principle and the technical effects of the user retention analysis device 300 provided in this embodiment are the same as those of the above embodiment, and for brevity, reference should be made to the corresponding contents of the above embodiment. The user retention analysis device 300 includes:
an obtaining module 310, configured to obtain a first predicted value set of the first user group with a specific behavior feature according to the behavior feature set of the first user group;
a determining module 330, configured to obtain a second user group according to the first predicted value set; the first predicted value set is different from a second predicted value set of the second user group with specific behavior characteristics by a preset range;
and the analysis module 350 is configured to obtain a relationship between the specific behavior feature and the retention rate according to the first retention rate of the first user group and the second retention rate of the second user group.
Optionally, the first user group includes a plurality of first users, and the behavior feature set of the first user group includes a behavior feature of each first user; the acquisition module 310 has a function for: obtaining a first estimated value of each first user with specific behavior characteristics according to the behavior characteristics and the prediction model of each first user; and obtaining a first predicted value set according to all the first estimated values.
Optionally, the first set of predictors includes a plurality of first predictors; the determining module 330 is specifically configured to: acquiring behavior characteristics of a plurality of undetermined users; obtaining a second estimated value of each pending user with specific behavior characteristics according to the behavior characteristics and the prediction model of each pending user; determining a plurality of target users from a plurality of pending users; the second estimated value of each target user is different from a first predicted value by a preset range; the second user group includes all target users.
Optionally, the analysis module 350 is specifically configured to: obtaining a retention rate difference value according to the first retention rate of the first user group and the second retention rate of the second user group; and obtaining the relation between the specific behavior characteristic and the retention rate according to the preset range and the retention rate difference value.
The embodiment of the invention also provides an electronic device, which comprises a processor 120 and a memory 130, wherein the memory 130 stores a computer program, and when the processor executes the computer program, the user retention analysis method disclosed in the above embodiment is realized.
The embodiment of the present invention also provides a storage medium having a computer program stored thereon, which when executed by the processor 120 implements the user retention analysis method disclosed in the embodiment of the present invention.
In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. The apparatus embodiments described above are merely illustrative, for example, of the flowcharts and block diagrams in the figures that illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present invention may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method of user retention analysis, the method comprising:
obtaining a first predicted value set of the first user group with specific behavior characteristics according to the behavior characteristic set of the first user group;
acquiring a second user group according to the first predicted value set; a second predicted value set of the second user group with the specific behavior characteristics is different from the first predicted value set by a preset range, and the second predicted value set is close to the first predicted value set and has a difference;
and obtaining the relation between the specific behavior characteristic and the retention rate according to the first retention rate of the first user group and the second retention rate of the second user group.
2. The method of claim 1, wherein the first group of users comprises a plurality of first users, and wherein the set of behavioral characteristics of the first group of users comprises behavioral characteristics of each of the first users;
the step of obtaining a first predicted value set of the first user group with specific behavior characteristics according to the behavior characteristic set of the first user group comprises the following steps:
obtaining a first estimated value of each first user with the specific behavior characteristics according to the behavior characteristics and the prediction model of each first user;
and obtaining the first predicted value set according to all the first estimated values.
3. The method of claim 2, wherein the first set of predictors comprises a plurality of first predictors;
the step of obtaining the second user group according to the first predicted value set includes:
acquiring behavior characteristics of a plurality of undetermined users;
obtaining a second estimated value of each undetermined user with the specific behavior characteristics according to the behavior characteristics of each undetermined user and the prediction model;
determining a plurality of target users from the plurality of pending users; the second estimated value of each target user is different from one of the first predicted values by a preset range; the second group of users includes all target users.
4. The method of claim 1, wherein the step of deriving the relationship of the specific behavioral characteristic to retention based on the first retention of the first group of users and the second retention of the second group of users comprises:
obtaining a retention rate difference value according to the first retention rate of the first user group and the second retention rate of the second user group;
and obtaining the relation between the specific behavior characteristic and the retention rate according to the preset range and the retention rate difference value.
5. A user retention analysis device, the device comprising:
the system comprises an acquisition module, a prediction module and a prediction module, wherein the acquisition module is used for acquiring a first predicted value set of a first user group with specific behavior characteristics according to the behavior characteristic set of the first user group;
the determining module is used for acquiring a second user group according to the first predicted value set; the first predicted value set is different from a second predicted value set of the second user group with the specific behavior characteristic by a preset range, and the second predicted value set is close to the first predicted value set and has a difference;
and the analysis module is used for obtaining the relation between the specific behavior characteristic and the retention rate according to the first retention rate of the first user group and the second retention rate of the second user group.
6. The apparatus of claim 5, wherein the first group of users comprises a plurality of first users, and wherein the set of behavioral characteristics of the first group of users comprises behavioral characteristics of each of the first users; the acquisition module has a function for:
obtaining a first estimated value of each first user with the specific behavior characteristics according to the behavior characteristics and the prediction model of each first user;
and obtaining the first predicted value set according to all the first estimated values.
7. The apparatus of claim 6, wherein the first set of predictors comprises a plurality of first predictors; the determining module is specifically configured to:
acquiring behavior characteristics of a plurality of undetermined users;
obtaining a second estimated value of each undetermined user with the specific behavior characteristics according to the behavior characteristics of each undetermined user and the prediction model;
determining a plurality of target users from the plurality of pending users; the second estimated value of each target user is different from one of the first predicted values by a preset range; the second group of users includes all target users.
8. The apparatus of claim 5, wherein the analysis module is specifically configured to:
obtaining a retention rate difference value according to the first retention rate of the first user group and the second retention rate of the second user group;
and obtaining the relation between the specific behavior characteristic and the retention rate according to the preset range and the retention rate difference value.
9. An electronic device comprising a processor and a memory, the memory storing a computer program, the processor implementing the method of any one of claims 1 to 4 when executing the computer program.
10. A storage medium having stored thereon a computer program which, when executed by a processor, implements the method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110915583.0A CN113626705B (en) | 2021-08-10 | 2021-08-10 | User retention analysis method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110915583.0A CN113626705B (en) | 2021-08-10 | 2021-08-10 | User retention analysis method, device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113626705A CN113626705A (en) | 2021-11-09 |
| CN113626705B true CN113626705B (en) | 2023-10-20 |
Family
ID=78384133
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110915583.0A Active CN113626705B (en) | 2021-08-10 | 2021-08-10 | User retention analysis method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113626705B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114742569A (en) * | 2021-01-08 | 2022-07-12 | 广州视源电子科技股份有限公司 | User life stage prediction method and device, computer equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180053095A1 (en) * | 2016-08-19 | 2018-02-22 | International Business Machines Corporation | Iterative and Targeted Feature Selection |
| CN108648000A (en) * | 2018-04-24 | 2018-10-12 | 腾讯科技（深圳）有限公司 | Method and device, the electronic equipment that life cycle is assessed are retained to user |
| CN111459783A (en) * | 2020-04-03 | 2020-07-28 | 北京字节跳动网络技术有限公司 | Application program optimization method and device, electronic equipment and storage medium |
| CN113132762A (en) * | 2021-04-16 | 2021-07-16 | 广州虎牙科技有限公司 | Retention behavior factor analysis method and device, electronic equipment and readable storage medium |
-
2021
- 2021-08-10 CN CN202110915583.0A patent/CN113626705B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180053095A1 (en) * | 2016-08-19 | 2018-02-22 | International Business Machines Corporation | Iterative and Targeted Feature Selection |
| CN108648000A (en) * | 2018-04-24 | 2018-10-12 | 腾讯科技（深圳）有限公司 | Method and device, the electronic equipment that life cycle is assessed are retained to user |
| CN111459783A (en) * | 2020-04-03 | 2020-07-28 | 北京字节跳动网络技术有限公司 | Application program optimization method and device, electronic equipment and storage medium |
| CN113132762A (en) * | 2021-04-16 | 2021-07-16 | 广州虎牙科技有限公司 | Retention behavior factor analysis method and device, electronic equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113626705A (en) | 2021-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107733968B (en) | Application information pushing method and device, computer equipment and storage medium | |
| US11188785B2 (en) | Optimization of network data analysis device | |
| CN111478963B (en) | Message pushing method and device, electronic equipment and computer readable storage medium | |
| US20200257749A1 (en) | Method and a device for friend recommendation | |
| CN111459783B (en) | Application program optimization method and device, electronic equipment and storage medium | |
| US20140269339A1 (en) | System for analysing network traffic and a method thereof | |
| CN108243032B (en) | Method, device and equipment for acquiring service level information | |
| CN105471935B (en) | Information prompting method and device | |
| CN108322350B (en) | Service monitoring method and device and electronic equipment | |
| CN113626705B (en) | User retention analysis method, device, electronic equipment and storage medium | |
| CN115328974B (en) | Data real-time detection method, device, equipment and readable storage medium | |
| CN113485931A (en) | Test method, test device, electronic equipment and computer readable storage medium | |
| CN113194306B (en) | Frame rate fluctuation evaluation method and device, mobile terminal, system and storage medium | |
| CN115729783A (en) | Fault risk monitoring method, apparatus, storage medium and program product | |
| CN108595685B (en) | Data processing method and device | |
| CN110602207A (en) | Method, device, server and storage medium for predicting push information based on off-network | |
| EP2917882A1 (en) | Heuristics to quantify data quality | |
| CN113590017B (en) | Method, electronic device and computer program product for processing data | |
| CN116756522A (en) | Probability forecasting method and device, storage medium and electronic equipment | |
| CN114064445A (en) | Test method, device, equipment and computer readable storage medium | |
| CN110780820A (en) | Method and device for determining continuous storage space, electronic equipment and storage medium | |
| CN110781743A (en) | Crowd gathering event processing method and device and electronic equipment | |
| US10943175B2 (en) | Methods, systems and apparatus to improve multi-demographic modeling efficiency | |
| CN114143571B (en) | User processing method, device, equipment and storage medium | |
| CN114239510A (en) | Service information processing method and device, storage medium and electronic equipment |
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 |