CN111401969A - Method, device, server and storage medium for improving user retention rate - Google Patents
Method, device, server and storage medium for improving user retention rate Download PDFInfo
- Publication number
- CN111401969A CN111401969A CN202010256277.6A CN202010256277A CN111401969A CN 111401969 A CN111401969 A CN 111401969A CN 202010256277 A CN202010256277 A CN 202010256277A CN 111401969 A CN111401969 A CN 111401969A
- Authority
- CN
- China
- Prior art keywords
- user
- loss
- curve
- classification category
- historical
- 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
- 230000014759 maintenance of location Effects 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000000717 retained effect Effects 0.000 claims description 6
- 230000002354 daily effect Effects 0.000 description 10
- 230000005284 excitation Effects 0.000 description 9
- 230000006399 behavior Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 125000004122 cyclic group Chemical group 0.000 description 4
- 230000003203 everyday effect Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008450 motivation Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 206010048909 Boredom Diseases 0.000 description 1
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010411 cooking Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0224—Discounts or incentives, e.g. coupons or rebates based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0235—Discounts or incentives, e.g. coupons or rebates constrained by time limit or expiration date
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present disclosure relates to a method, an apparatus, a server, and a storage medium for improving a user retention rate. The method comprises the following steps: acquiring a user loss curve of a historical newly added user in a classification category to which a target user belongs, wherein the user loss curve reflects the loss condition of the historical newly added user in the classification category; determining a key time node of the historical newly-added user loss in the classification category according to the user loss curve; and exciting the target user based on the key time node to improve the retention probability of the target user. Because the target user has a high possibility of losing the key time node, the target user is accurately stimulated based on the key time node, so that the possibility of losing the target user can be reduced, and the retention rate of the target user is improved.
Description
Technical Field
The present disclosure relates to the field of data processing technologies, and in particular, to a method, an apparatus, a server, and a storage medium for improving a user retention rate.
Background
With the development of internet technology, more and more application software (APP) are emerging for users to use so as to meet the requirements of work, entertainment and the like. However, in practical applications, after a user uses a certain application software for a period of time, the application software may not be used due to lack of interest, and the like, thereby causing a phenomenon that a large amount of users are lost. It is therefore desirable to provide a method that can improve the user retention rate to address this problem.
Disclosure of Invention
The present disclosure provides a method, an apparatus, a server, and a storage medium for improving a user retention rate, which can reduce user loss of application software, thereby improving the user retention rate. The technical scheme of the disclosure is as follows:
according to a first aspect of embodiments of the present disclosure, there is provided a method for improving a user retention rate, including:
acquiring a user loss curve of a historical newly added user in a classification category to which a target user belongs, wherein the user loss curve reflects the loss condition of the historical newly added user in the classification category;
determining a key time node of the historical newly-added user loss in the classification category according to the user loss curve;
and exciting the target user based on the key time node to improve the retention probability of the target user.
According to a second aspect of embodiments of the present disclosure, there is provided an apparatus for improving user retention, comprising:
the user churn curve acquisition unit is configured to execute user churn curves of historical newly added users in a classification category to which a target user belongs, wherein the user churn curves reflect churn conditions of the historical newly added users in the classification category;
an excitation time point determining unit configured to determine a key time node of the historical new user churn in the classification category according to the user churn curve;
an incentive unit configured to perform an incentive for the target user based on the key time node to increase a probability of retention of the target user.
According to a third aspect of the embodiments of the present disclosure, there is provided a server, including:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the method for improving user retention provided by the embodiments of the present disclosure.
According to a fourth aspect of the embodiments of the present disclosure, there is provided a storage medium, wherein instructions of the storage medium, when executed by a processor of a server, enable the server to perform the method for improving user retention provided by the embodiments of the present disclosure.
According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product, which when run on a computer, causes the computer to execute the method for improving user retention provided by embodiments of the present disclosure.
The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:
by adopting the user excitation method provided by the embodiment of the disclosure, the user loss curve of the historical newly added user in the classification category to which the target user belongs is obtained, then the key time node of the historical newly added user loss in the classification category is determined according to the user loss curve, and then the target user is excited based on the key time node. Because the target user has a high possibility of losing the key time node, the target user is accurately stimulated based on the key time node, so that the possibility of losing the target user can be reduced, and the retention rate of the target user is improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.
Fig. 1 is an application scenario to which the technical solution in the embodiment of the present disclosure can be applied, and in the scenario, the application scenario may include a server and a terminal device.
Fig. 2 is a flowchart illustrating a method for improving user retention according to an exemplary embodiment.
FIG. 3 is a diagram illustrating a user churn curve according to an exemplary embodiment.
Fig. 4 is a schematic diagram illustrating a specific structure of an apparatus for improving a user retention rate according to an exemplary embodiment.
Fig. 5 is a schematic diagram illustrating a specific structure of a server according to an exemplary embodiment.
Detailed Description
In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein.
As mentioned above, after a user uses a certain application software for a period of time, the application software may not be used due to lack of interest, and the like, thereby causing a phenomenon that a large amount of users are lost. For the provider of the application software, in order to reduce the user loss, it is usually necessary to incentivize the user, thereby increasing the user's retention rate. In the related art, users are often prompted to check-in daily in a gift, point method, thereby increasing their retention rate. However, in this way, since gifts, points, and the like need to be issued after the user signs in every day, on one hand, the cost is high, and on the other hand, after the user signs in for a plurality of consecutive days, emotions such as boredom may occur, resulting in poor effects.
The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
Fig. 1 shows an application scenario to which the technical solution in the embodiment of the present disclosure can be applied, and in the scenario, the application scenario may include a server 10 and a terminal device 20.
The server 10 may be an application server or a web server. The application server can be, for example, a background server of application software such as video application software, live broadcast application software, instant messaging application software or news information application software; the website server may be, for example, a background server for each news website.
The terminal device 20 may be a terminal or a mobile terminal such as a mobile phone, a computer or a tablet computer, and the terminal device 20 may have application software corresponding to the server 10 installed therein, or may access corresponding web application software through a browser in the terminal device 20.
Taking video application software as an example, the terminal device 20 is installed with the video application software at this time, and the server 10 is a background server of the video application software. The user may use the video application installed on the terminal device 20 for entertainment, learning, etc., but after a period of use, it may for some reason be no longer used. To this end, the provider of the video application needs to incentivize the user through the server 10.
Of course, the method provided by the embodiment of the present disclosure is not limited to be used in the application scenario shown in fig. 1, and may also be used in other possible application scenarios, and the embodiment of the present disclosure is not limited to this. The functions that can be implemented by each device in the application scenario shown in fig. 1 will be described in the following method embodiments, and will not be described in detail herein.
Referring to fig. 2, a specific flowchart of a method that can be used for improving the user retention rate according to an embodiment of the present disclosure is shown, which includes the following steps.
Step S31: and acquiring a user loss curve of the historical newly added user in the classification category to which the target user belongs.
The target user can be a user who needs to be stimulated according to actual conditions so as to improve the retention rate. For example, newly added users in a certain classification category in the near future (for example, in the last week, in the last 10 days, in the last 30 days, etc.) may be used as the target users, or when the activity of users in a certain classification category is low, all users in the classification category may be used as the target users, or some users may be randomly selected from all users in the application software as the target users.
Generally, in order to provide differentiated services for different users, the users need to be classified according to their identity information, behavior information, and the like, so as to assign the different users to corresponding classification categories, wherein the identity information may include the age, sex, region (province, city, and the like) of the users, the behavior information may include articles frequently visited by the users, videos watched by the users, and the like, and the classification categories of the users may include military affairs, cooking skill, games, and the like. For example, a 23 year old male user in Beijing may be classified into game category categories because they often view game-like videos and articles.
Due to statistical analysis of data, it is found that one or more "key time nodes" are usually present in a user loss behavior of newly added users in different classification categories, and among the "key time nodes", the newly added users are seriously lost, that is, for a certain newly added user, the loss probability is high, and the "key time nodes" corresponding to different classification categories may not be the same. Based on the characteristic, the user loss curves of the historical new users corresponding to different classification categories can be generated according to the loss data or the retention data of the historical new users in the different classification categories, so that the key time nodes in the corresponding classification categories are predicted according to the user loss curves, and the users are stimulated at the key time nodes, so that the effect of accurate stimulation is achieved, and the retention rate of the new users is improved. The user loss curve of the historical newly added user in a certain classification category can generally reflect the loss condition of the historical newly added user in the classification category, for example, the ordinate of the user loss curve is the number of the historical newly added user, and the abscissa of the user loss curve is the number of days after the account of the historical newly added user is registered or the number of days after the user first accesses the application software.
In addition, whether the user is a history newly added user can be determined according to the account registration time point of the user or the time point of first accessing the application software. For example, if the current time is 2019, 10, 01 and the account of a certain user is registered as 2019, 09, 04, the user is a new user in 2019, 09, 04 and is a history new user relative to the current time.
The specific way of determining the user churn curve of the classification category to which the target user belongs may be to obtain the user churn curve generated in advance from a database, in which the user churn curves of the corresponding historical newly added users may be generated in advance for each classification category, and the user churn curves are stored in the database, and when necessary, the classification category to which the target user belongs is determined first, and then the corresponding user churn curve is obtained from the database according to the classification category. This approach is generally time consuming as the generation and acquisition of the user churn curve is separated, the user churn curve is generated in advance and acquired from the database when needed. Another specific way to determine the user churn curve of the classification category to which the target user belongs may be to generate the user churn curve immediately when needed.
The user loss curve of the newly added historical user can be generated in advance or generated immediately by the following method:
the first method is as follows: and counting the loss data or the retained data of the historical newly added users in a certain classification category within a preset time period, so as to draw a corresponding user loss curve.
The preset time period may be 1 week, 10 days, 30 days, 50 days, 1 year, etc. Therefore, the loss data or the retention data of the history new user in the preset time period may be the loss data or the retention data of the history new user in the preset time period after the account registration time point or the time point of accessing the application software for the first time. For example, historical new users in the category of the game category are counted for data loss or data retention within 30 days after the account registration time point.
The second method comprises the following steps: randomly selecting a plurality of history new users from the history new users of the classification category, and then drawing a user loss curve according to the loss data or the retained data of each randomly selected history new user in a preset time period.
Compared with the first mode, in the second mode, part of the newly added historical users need to be randomly selected from the newly added historical users of the classification category, so that the user loss curve of the classification category is drawn by taking the newly added historical users of the part as statistical samples. When the number of historical new users in the classification category is large (for example, greater than 100 ten thousand or other numbers), in order to reduce the data statistics, a user churn curve can be drawn in this way. Conversely, when the number of the historical newly added users in the classification category is small, the user churn curve can be drawn by adopting the first mode.
In addition, since there may be differences between new users at different time points, for example, there may be differences between an early user and a new user registered recently as the version of the application software is updated. Therefore, in order to reduce the influence caused by such difference, at least one day may be randomly selected from each of the last M months, and a plurality of history new users may be selected from the history new users of the category on each randomly selected day, where M is specifically an integer greater than 1, and for example, M may be 12, 10, or another value.
For example, a day may be randomly selected from each of the last 12 months, and a plurality of history new users may be selected from the history new users of the category on each randomly selected day. Generally, if the number of new users of the category on a certain randomly selected day is greater than a certain number (for example, 10 ten thousand, 20 ten thousand or other values), some users may be randomly selected from the new users as statistical samples; if the number of the new users of the classification category on a certain randomly selected day is less than or equal to a certain number, the new users can be directly used as statistical samples.
After a plurality of history new users are selected from the history new users of each day randomly selected by the classification category, corresponding numbers can be distributed to the selected history new users. Generally for statistical purposes, the number may contain a user identification, such as an account name, and a time point of account registration (or a time point of first access to application software) of a historically added user. For example, if the user identifier of a certain history new user is 10000, and the account registration time point is 2019, 08 and 23, the number of the history new user may be 10000-20190823; for the history new users registered in 03 of 09 months 03 in 2019 and having the user identification of 20000, the number of the history new users may be 20000-plus 20190903.
After the selected history new users are assigned with corresponding numbers, the loss conditions of the history new users in a preset time period (such as one week, 10 days, 30 days and the like) can be tracked through the numbers, and loss data or remaining data of the history new users in the preset time period is obtained, so that a corresponding user loss curve is drawn.
Fig. 3 shows an example of a user churn curve in practical applications. In this example, the preset time period is 30 days, the ordinate is the number of remaining users that have been added to the history every day, and the abscissa is the day. And the retention quantity of the history newly added users on the first day is the retention quantity of the selected history newly added users. The remaining number of the newly added historical users on the next day is calculated as follows: for example, for a history newly added user with codes of 10000-; for the history newly added user coded with 20000-plus 20190903, judging whether the history newly added user accesses the application software behavior in 20190904 days, if so, adding 1 to the retention number of the history newly added user in the next day, and if not, adding 0 to the retention number of the history newly added user in the next day; similarly, the same method is adopted for other history new users, so that the remaining number of the history new users in the next day is finally counted.
The remaining number of the newly added historical users on the third day to the remaining number of the newly added historical users on the 30 th day can be counted in the same way.
Therefore, after counting the remaining number of the historical newly added users from the first day to the 30 th day, the data can be used for drawing a corresponding user churn curve.
Step S32: and determining a key time node of the historical newly-added user loss in the classification category according to the user loss curve.
Due to the user churn curve of the historical newly added users in a certain classification category, the churn condition of the historical newly added users in the classification category can be reflected. Therefore, the daily-to-annular ratio loss rate of the historical newly-added users in the corresponding classification categories in a second preset time period can be calculated according to the user loss curve, wherein the second preset time period can be one week, 10 days, 30 days and the like; the daily cycle specific loss rate on day N can be calculated by the following formula:
the daily ring ratio loss rate on the nth day (the number of retained days on the nth day-the number of retained days on (N-1)) day/the number of retained days on (N-1), where N is a positive integer greater than 1. And the daily ring ratio slip rate on the appointed first day is 0.
Therefore, the daily and ring ratio loss rate in the second preset time period can be calculated through the method, and then the key time node of the historical newly-increased user loss in the classification category is determined according to the size of each daily and ring ratio loss rate, so that the key time node is used for user excitation. One way is that, in each day-to-ring ratio loss rate, time points corresponding to each day-to-ring ratio loss rate greater than a preset threshold may be determined as excitation time points, for example, the day-to-ring ratio loss rates of days 15 and 21 are greater than the preset threshold, and days 15 and 21 may be determined as key time nodes; in another mode, the day-to-ring ratio loss rates may be sorted according to size, and then a time point corresponding to the largest day-to-ring ratio loss rate is selected to be determined as a key time node, or time points corresponding to a plurality of (e.g., 3) largest day-to-ring ratio loss rates are selected to be determined as key time nodes, for example, the 15 th day may be determined as a key time node when the day-to-ring ratio loss rate of the 15 th day is the largest day-to-ring ratio loss rate.
Step S33: and exciting the target user based on the key time node so as to improve the retention probability of the target user.
For the target user, an account registration time point or a time point of first accessing the application software of the target user may be obtained, and when the account registration time point or the time point of first accessing the application software is reached, the target user is a new user, so that the target user is stimulated by combining the determined key time node.
For example, the key time node is 15 days, and the account registration time point of the target user is 2019, 11, and 2 days, the target user is most likely to lose in 2019, 11, and 16 days (i.e., the first day starting at 2019, 11, and 2 days, and the next 15 days), so that the target user can be motivated in 2019, 11, and 16 days, for example, gifts, points, and the like are issued to the user in 2019, 11, and 16 days, and the gifts, points, and the like are collected by the user in 2019, 11, and 16 days, so that the target user is prompted to continue to use the application software, and the loss of the target user on the key time node is prevented.
By adopting the user excitation method provided by the embodiment of the disclosure, the user loss curve of the historical newly added user in the classification category to which the target user belongs is obtained, then the key time node of the historical newly added user loss in the classification category is determined according to the user loss curve, and then the target user is excited based on the key time node. Because the target user has a high possibility of losing the key time node, the target user is accurately stimulated based on the key time node, so that the possibility of losing the target user can be reduced, and the retention rate of the target user is improved.
In addition, by the method, on one hand, because the user loss curve of the historical newly-added user corresponds to the classification category to which the target user belongs, different key time nodes can be determined for users of different classification categories, so that excitation is performed according to the different key time nodes, and the characteristics of the users of different classification categories are better met; on the other hand, when the excitation is carried out according to the determined key time node, compared with a method of issuing gifts and points after signing in every day, the cost can be reduced, and accurate excitation can be carried out at a key time point with high possibility of user loss, so that the effect is improved.
It should be noted that, in practical applications, application software is usually updated continuously, and behavior habits of newly added users and early users may be greatly different. Therefore, the user loss curve of the historically added user of the classification category to which the target user belongs, determined by the method, cannot accurately reflect the user loss condition of the recently added user. In order to further adjust the method, thereby further improving the incentive effect and the retention rate of the target user, the method may further comprise: and determining a new user loss curve of the classification category to which the target user belongs in a latest preset time period, wherein the new user loss curve reflects the loss condition of the new user in the latest preset time period, and the preset time period can be 7 days, 10 days, 30 days and the like.
For example, a classification category to which the target user belongs, a newly added user loss curve in the last 30 days, or a newly added user loss curve in the last 30 days may be obtained in real time. For the obtaining or drawing manner of the new user churn curve within 30 days, reference may be made to step S31, which is not described in detail here.
In addition, as to the step S32, the key time node of the historical new user churn in the classification category is determined according to the user churn curve, which may be specifically determined according to the user churn curve of the historical new user determined in the step S31 and the new user churn curve in the latest preset time period.
When determining the key time node according to the user loss curve of the newly added user in the history and the newly added user loss curve in the latest preset time period, the newly added user loss curve in the latest preset time period (referred to as a first curve) may be compared with the user loss curve of the newly added user in the history (referred to as a second curve), if the deviation of the first curve relative to the second curve is small, for example, the second curve is taken as a reference, and the fluctuation range of the first curve relative to the second curve is smaller than a second preset threshold, it is indicated that the difference in behavior habits of the newly added user is not large compared with the early user, and at this time, the key time node may be determined directly by using the second curve.
On the contrary, if the deviation of the first curve relative to the second curve is large, for example, the fluctuation range of the first curve relative to the second curve is larger than the second preset threshold based on the second curve, which indicates that the difference in behavior habits of the newly added user is larger than that of the earlier user, the first curve and the second curve need to be combined to determine the key time node. For example, the key time node to be selected may be determined according to the first curve, and the key time node to be selected may also be determined according to the second curve, and then the union of the two may be used as the finally determined key time node; or determining a key time node to be selected according to the second curve, and then carrying out certain adjustment on the key time node to be selected by combining the variation trend of the first curve; or, the daily and cyclic ratio loss rate may be calculated according to the first curve, and the daily and cyclic ratio loss rate may be calculated according to the second curve, so that the largest one or more daily and cyclic ratio loss rates are selected from the daily and cyclic ratio loss rates, and the key time node is determined according to the corresponding time point.
Based on the same inventive concept as the user motivation method provided by the embodiment of the present disclosure, the present disclosure also provides an apparatus for improving user retention rate, as shown in fig. 4, which is a block diagram of the apparatus according to an exemplary embodiment. Referring to fig. 4, the apparatus 40 includes: a user churn curve acquisition unit 401, a key time node determination unit 402, and an excitation unit 403, where:
a user churn curve obtaining unit 401 configured to perform obtaining a user churn curve of a historical newly added user in a classification category to which a target user belongs, where the user churn curve reflects churn conditions of the historical newly added user in the classification category;
a key time node determining unit 402 configured to determine a key time node of a history of new user churn in the classification category according to the user churn curve;
an incentive unit 403 configured to perform an incentive for the target user based on the key time node to increase a probability of retention of the target user.
Since the apparatus 40 employs the same inventive concept as the user motivation method provided by the disclosed embodiment, the problems in the prior art can also be solved. In addition, for the apparatus 40, if there is an unclear point, the corresponding contents in the method embodiment may be referred to, and are not described herein again.
In addition, the embodiment of the disclosure can also provide a server. Fig. 5 is a block diagram illustrating a server 50 according to an example embodiment. The server 50 comprises a processor 501 and a memory 502 for storing instructions executable by the processor 501. Wherein the processor 501 is configured to execute the instructions to implement the method for improving the user retention provided by the embodiments of the present disclosure.
In practice, the server 50 may also include a network interface 503, an I/O controller 504, a mass storage device 505, and a bus 506 for connecting them.
In an exemplary embodiment, the present disclosure also provides a storage medium comprising instructions, such as the memory 502 comprising instructions, executable by the processor 501 of the server 50 to perform the above-described method. The storage medium may be a non-transitory computer readable storage medium, which may be, for example, a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
The disclosed embodiments may also provide a computer program product which, when run on a computer, causes the computer to perform the method for improving user retention provided by the disclosed embodiments.
The computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, e.g., from one website site, computer, server, or data center, over a wired (e.g., coaxial cable, fiber optic, digital subscriber line (DS L)) or wireless (e.g., infrared, wireless, microwave, etc.) medium to be stored by a computer or a data center integrated server, data center, etc. the computer-readable storage medium may be any available medium that can be stored by a computer or a data storage device that includes one or more available media such as a magnetic medium, (e.g., a floppy Disk, a magnetic tape, an optical medium (e.g., a Solid State medium), a DVD, or a Solid State medium (SSD)).
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure 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 present disclosure is limited only by the appended claims.
Claims (10)
1. A method for increasing a user retention rate, comprising:
acquiring a user loss curve of a historical newly added user in a classification category to which a target user belongs, wherein the user loss curve reflects the loss condition of the historical newly added user in the classification category;
determining a key time node of the historical newly-added user loss in the classification category according to the user loss curve;
and exciting the target user based on the key time node to improve the retention probability of the target user.
2. The method according to claim 1, wherein obtaining a user churn curve for a historically added user in a category to which the target user belongs specifically comprises:
randomly selecting a plurality of history new users from the history new users of the classification category;
and drawing the user loss curve according to the randomly selected loss data or the retained data of each history newly added user in a preset time period.
3. The method of claim 2, wherein randomly selecting a plurality of history new users from the history new users of the classification category comprises:
and respectively randomly selecting at least one day from each month of the latest M months, and selecting a plurality of history new users from the randomly selected history new users of each day of the classification category, wherein M is an integer more than 1.
4. The method according to claim 1, wherein obtaining a user churn curve for a historically added user in a category to which the target user belongs specifically comprises: and acquiring a user loss curve of the historical added user in the classification category to which the target user belongs from the user loss curves of the historical added users respectively corresponding to the plurality of classification categories generated in advance.
5. The method of claim 1, further comprising: determining a new user loss curve of the classification category to which the target user belongs in a latest preset time period, wherein the new user loss curve reflects the loss condition of the new user in the latest preset time period; then the process of the first step is carried out,
determining a key time node of the historical newly-added user loss in the classification category according to the user loss curve, specifically comprising:
and determining the key time node of the historical newly added user loss in the classification category according to the user loss curve of the historical newly added user and the newly added user loss curve in the latest preset time period.
6. The method according to claim 1, wherein determining a key time node of a historical new user churn in the classification category according to the user churn curve specifically comprises:
calculating the daily-to-annular ratio loss rate of the historical newly-added users in the classification category in a second preset time period according to the user loss curve;
and determining the key time node according to the daily-to-annular ratio loss rate in the second preset time period.
7. The method according to claim 6, wherein determining the key time node according to the magnitude of the daily-to-ring ratio churn rate in the second preset time period specifically includes:
determining, as the key time node, a time point corresponding to each daily-to-cyclic ratio loss rate greater than a preset threshold value among the daily-to-cyclic ratio loss rates in the second preset time period; or the like, or, alternatively,
and determining the time points corresponding to the maximum one or more daily-to-annular ratio loss rates in the second preset time period as the key time nodes.
8. An apparatus for improving user retention, comprising:
the user churn curve acquisition unit is configured to execute user churn curves of historical newly added users in a classification category to which a target user belongs, wherein the user churn curves reflect churn conditions of the historical newly added users in the classification category;
a key time node determining unit configured to determine a key time node of a history of new user churn in the classification category according to the user churn curve;
an incentive unit configured to perform an incentive for the target user based on the key time node to increase a probability of retention of the target user.
9. A server, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the method for improving user retention according to any one of claims 1 to 7.
10. A storage medium having instructions that, when executed by a processor of a server, enable the server to perform a method for improving user retention according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010256277.6A CN111401969B (en) | 2020-04-02 | 2020-04-02 | Method, device, server and storage medium for improving user retention |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010256277.6A CN111401969B (en) | 2020-04-02 | 2020-04-02 | Method, device, server and storage medium for improving user retention |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111401969A true CN111401969A (en) | 2020-07-10 |
| CN111401969B CN111401969B (en) | 2024-02-20 |
Family
ID=71413697
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010256277.6A Active CN111401969B (en) | 2020-04-02 | 2020-04-02 | Method, device, server and storage medium for improving user retention |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111401969B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112465568A (en) * | 2020-12-15 | 2021-03-09 | 掌阅科技股份有限公司 | Promotion activity generation method, computing device and computer storage medium |
| CN113457166A (en) * | 2021-07-20 | 2021-10-01 | 网易（杭州）网络有限公司 | Game player churn information processing method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170169458A1 (en) * | 2015-12-11 | 2017-06-15 | T-Mobile U.S.A., Inc. | Determining awards for mobile device users based on renewal events |
| CN108364195A (en) * | 2018-02-09 | 2018-08-03 | 腾讯科技（深圳）有限公司 | User retains probability forecasting method, device, predictive server and storage medium |
| CN109461023A (en) * | 2018-10-12 | 2019-03-12 | 中国平安人寿保险股份有限公司 | It is lost user and retrieves method and device, electronic equipment, storage medium |
| CN110222975A (en) * | 2019-05-31 | 2019-09-10 | 北京奇艺世纪科技有限公司 | A kind of loss customer analysis method, apparatus, electronic equipment and storage medium |
| CN110264262A (en) * | 2019-06-18 | 2019-09-20 | 北京字节跳动网络技术有限公司 | Data processing method, device and electronic equipment based on user behavior |
-
2020
- 2020-04-02 CN CN202010256277.6A patent/CN111401969B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170169458A1 (en) * | 2015-12-11 | 2017-06-15 | T-Mobile U.S.A., Inc. | Determining awards for mobile device users based on renewal events |
| CN108364195A (en) * | 2018-02-09 | 2018-08-03 | 腾讯科技（深圳）有限公司 | User retains probability forecasting method, device, predictive server and storage medium |
| CN109461023A (en) * | 2018-10-12 | 2019-03-12 | 中国平安人寿保险股份有限公司 | It is lost user and retrieves method and device, electronic equipment, storage medium |
| CN110222975A (en) * | 2019-05-31 | 2019-09-10 | 北京奇艺世纪科技有限公司 | A kind of loss customer analysis method, apparatus, electronic equipment and storage medium |
| CN110264262A (en) * | 2019-06-18 | 2019-09-20 | 北京字节跳动网络技术有限公司 | Data processing method, device and electronic equipment based on user behavior |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112465568A (en) * | 2020-12-15 | 2021-03-09 | 掌阅科技股份有限公司 | Promotion activity generation method, computing device and computer storage medium |
| CN113457166A (en) * | 2021-07-20 | 2021-10-01 | 网易（杭州）网络有限公司 | Game player churn information processing method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111401969B (en) | 2024-02-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108763502B (en) | Information recommendation method and system | |
| US20190012683A1 (en) | Method for predicting purchase probability based on behavior sequence of user and apparatus for the same | |
| US8732015B1 (en) | Social media pricing engine | |
| CN110148012B (en) | User motivation method, device, computer equipment and storage medium | |
| US20140025620A1 (en) | Inferring user mood based on user and group characteristic data | |
| EP2698967A1 (en) | Social network data mining method for terminal user, and relevant method, device and system | |
| US9342842B2 (en) | Context-switching taxonomy for mobile advertisement | |
| US20130311283A1 (en) | Data mining method for social network of terminal user and related methods, apparatuses and systems | |
| CN107330718B (en) | Media anti-cheating method and device, storage medium and terminal | |
| WO2016181580A1 (en) | Information processing device, information processing method, and information processing program | |
| CN107835132B (en) | Method and device for tracking flow source | |
| CN113127723B (en) | User portrait processing method, device, server and storage medium | |
| CN114938458B (en) | Object information display method and device, electronic equipment and storage medium | |
| US20150245110A1 (en) | Management of invitational content during broadcasting of media streams | |
| CN107977678A (en) | Method and apparatus for output information | |
| CN111401969A (en) | Method, device, server and storage medium for improving user retention rate | |
| CN112883275B (en) | Live broadcast room recommendation method, device, server and medium | |
| CN113850416A (en) | Advertisement promotion cooperation object determining method and device | |
| CN115375339A (en) | Multimedia information recommendation method, device and equipment and computer storage medium | |
| US10607254B1 (en) | Attribution modeling using withheld or near impressions | |
| CN110557351B (en) | Method and apparatus for generating information | |
| CN110210884B (en) | Method, device, computer equipment and storage medium for determining user characteristic data | |
| KR20130091391A (en) | Server and method for recommending contents, and recording medium storing program for executing method of the same in computer | |
| CN110751526A (en) | Advertisement pushing method and device, computer equipment and storage medium | |
| CN101677274A (en) | Website operation management method and device |
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 |