CN108596652A - Active users prediction technique and device - Google Patents
Active users prediction technique and device Download PDFInfo
- Publication number
- CN108596652A CN108596652A CN201810267284.9A CN201810267284A CN108596652A CN 108596652 A CN108596652 A CN 108596652A CN 201810267284 A CN201810267284 A CN 201810267284A CN 108596652 A CN108596652 A CN 108596652A
- Authority
- CN
- China
- Prior art keywords
- retention ratio
- days
- day
- target product
- online
- 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.)
- Pending
Links
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
- 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
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A kind of active users prediction technique of the embodiment of the present application offer and device, this method include：Determine prediction online the N days day active users of target product；Obtain the target product number that Adds User daily in online 1st day to the N days；And according to preset at least two retention ratio anticipation functions, determine online 1st day of target product to newly-increased retention ratio daily in N 1 day；According to daily number and the 1st day of Adding User in the 1st day to the N days online the N days day active users of target product are determined to newly-increased retention ratio daily in N 1 day.The embodiment of the present application is in view of over time, in the different time sections of product life cycle, the dough softening of practical retention ratio is not unalterable in each period, therefore different retention ratio anticipation functions is generated for the different time sections of product life cycle, accurately statistic algorithm is provided for prediction active users, so as to day active users that calculate to a nicety out.
Description
Technical field
This application involves field of computer technology more particularly to active users prediction technique and devices.
Background technology
As reflection website, the important indicator of the traffic-operating period of the Internet, applications or online game, day active users
(Daily Active User, DAU) can provide some data for channel promotion, Cost evaluating and support and help.The prior art
In, it is the prediction that the empirical value based on user carries out active users, but the error rate of its prediction result is higher, leads to deficiency
To support Promotion Strategy to adjust and cost budgeting.
Invention content
The purpose of the embodiment of the present application is to provide a kind of active users prediction technique and device, to solve in the prior art
The existing empirical value based on user carries out active users prediction, and the caused higher technology of prediction result error rate is asked
Topic.
In order to solve the above technical problems, what the embodiment of the present application was realized in：
According to the embodiment of the present application in a first aspect, provide a kind of active users prediction technique, the method includes：
Determine prediction online the N days day active users of target product, N >=1；
Obtain the target product number that Adds User daily in online 1st day to the N days；And
According to preset at least two retention ratio anticipation functions, in determining the target product online 1st day to the N-1 days
Daily newly-increased retention ratio, wherein the retention ratio anticipation function is used to establish the online number of days of the target product and increases newly
Mapping relations between retention ratio；
In counting according to daily Adding User in described 1st day to the N days and is 1st day to the N-1 days described daily
Newly-increased retention ratio, determines online the N days day active users of the target product.
Optionally, as one embodiment, described according at least one of preset retention ratio anticipation function, determine described in
Before the step of target product newly-increased retention ratio daily in online 1st day to the N-1 days, further include：
Obtain the life cycle of the target product and multinomial retention index；
The life cycle of the target product was divided at least two periods；
It for each period, is carried out curve fitting using different retention indexs, obtains at least two period
Corresponding retention ratio anticipation function a, wherein period corresponds to a retention ratio anticipation function.
Optionally, as one embodiment, the life cycle by the target product was divided at least two times
Section, including：
The life cycle of the target product is divided into four periods；
Wherein, first time period is the target product online 1st day to the M1 days, and second time period is produced for the target
Online the M1+1 days to the M2 days of product, third period are the target product online the M2+1 days to the M3 days, the 4th time
Section is online the M3+1 days of the target product to life cycle last day.
Optionally, as one embodiment, the retention index includes：Retention ratio on the 1st, is retained retention ratio on the 7th on the 30th
Rate, retention ratio on the 60th, retention ratios on the 120th and retention ratio on the 240th；
It is described to be directed to each period, it is carried out curve fitting using different retention indexs, when obtaining described at least two
Between the corresponding retention ratio anticipation function of section, including：
For the first time period, according to retention ratio on the 1 of the target product, retention ratio on the 7th, retention ratios on the 30th and
Retention ratio carried out curve fitting on 60th, obtained the corresponding retention ratio anticipation function of the first time period；
For the second time period, according to retention ratio on the 1 of the target product, retention ratio on the 7th, retention ratio on the 30th,
Retention ratios on the 60th and retention ratio on the 120th carry out curve fitting, and obtain the corresponding retention ratio anticipation function of the second time period；
For the third period, according to retention ratio on the 1 of the target product, retention ratio on the 7th, retention ratio on the 30th,
60 increase day by day retention ratio, retention ratios on the 120th and retention ratios on the 240th carry out curve fitting, and obtain the third period and corresponding stay
Deposit rate anticipation function；
For the 4th period, according to retention ratios on the 240 of the target product and life cycle last day
Retention ratio carries out curve fitting, and obtains the 4th period corresponding retention ratio anticipation function.
Optionally, as one embodiment, it is described according in described 1st day to the N days it is daily Add User number and
Daily newly-increased retention ratio, determines online the N days day active users of the target product in described 1st day to the N-1 days,
Including：
According to preset active users calculation formula, it is 1st day to the N days described in it is daily Add User number and
Daily newly-increased retention ratio, calculates online the N days day active users of the target product in described 1st day to the N-1 days；
Wherein, the calculation formula isDAU(n)To apply online n-th
It day active users, DNU(i)For the online i-th day number that Adds User of application, R(n-i)For the n-th-i days newly-increased retention ratio, 1
≤i≤n。
Optionally, as one embodiment, the method further includes：
It active users and is actively used existing practical day using the day estimated by the retention ratio anticipation function
Amount carries out the adjustment of retention ratio anticipation function.
Optionally, described actively to be used day using what is estimated by the retention ratio anticipation function as one embodiment
Amount and existing practical day active users carry out the optimization of retention ratio anticipation function, including：
Obtain the online the practical active users daily in T1 days to the T2 days of the target product；
According to the retention ratio anticipation function, determines that the target product online the is daily in T1 days to the T2 days and estimate
Active users；
By practical active users daily in online the T1 days to the T2 days of the target product and estimate any active ues
Number is compared, and obtains comparison result；
When determining that the prediction accuracy of the retention ratio anticipation function is less than predetermined threshold value according to the comparison result, root
It is marked off according to the life cycle of the comparison result, the life cycle and/or the target product that adjust the target product
Period；
It is marked off according to the life cycle of the life cycle of the target product after adjustment and/or the target product
Period, generate new retention ratio anticipation function.
According to the second aspect of the embodiment of the present application, a kind of active users prediction meanss are provided, described device includes：
First determining module, for determining prediction online the N days day active users of target product, N >=1；
First acquisition module, for the number that Adds User daily in obtaining the target product online 1st day to the N days；
Second determining module, for according to preset at least two retention ratio anticipation functions, determining that the target product exists
Line newly-increased retention ratio daily in the 1st day to the N-1 days, wherein the retention ratio anticipation function is for establishing the target production
Mapping relations between the online number of days and newly-increased retention ratio of product；
Prediction module, for according to daily number and described 1st day of Adding User in described 1st day to the N days to the
Daily newly-increased retention ratio, determines online the N days day active users of the target product in N-1 days.
Optionally, as one embodiment, described device further includes：
Second acquisition module, the life cycle for obtaining the target product and multinomial retention index；
Division module, for the life cycle of the target product to be divided at least two periods；
Fitting module is carried out curve fitting using different retention indexs for being directed to each period, obtain it is described extremely
Corresponding retention ratio anticipation function of few two periods a, wherein period corresponds to a retention ratio anticipation function.
Optionally, as one embodiment, the division module, including：
Period division unit, for the life cycle of the target product to be divided into four periods；
Wherein, first time period is the target product online 1st day to the M1 days, and second time period is produced for the target
Online the M1+1 days to the M2 days of product, third period are the target product online the M2+1 days to the M3 days, the 4th time
Section is online the M3+1 days of the target product to life cycle last day.
Optionally, as one embodiment, the retention index includes：Retention ratio on the 1st, is retained retention ratio on the 7th on the 30th
Rate, retention ratio on the 60th, retention ratios on the 120th and retention ratio on the 240th；
The fitting module, including：
First curve matching unit, for being directed to the first time period, according to retention ratio, 7 on the 1 of the target product
Day retention ratio, retention ratios on the 30th and retention ratio on the 60th carry out curve fitting, and it is pre- to obtain the corresponding retention ratio of the first time period
Survey function；
Second curve matching unit, for being directed to the second time period, according to retention ratio, 7 on the 1 of the target product
Day retention ratio, retention ratio on the 30th, retention ratios on the 60th and retention ratio on the 120th carry out curve fitting, and obtain the second time period pair
The retention ratio anticipation function answered；
Third curve matching unit, for being directed to the third period, according to retention ratio, 7 on the 1 of the target product
Day retention ratio, retention ratio on the 30th, 60 increase day by day retention ratio, retention ratios on the 120th and retention ratios on the 240th carry out curve fitting, and obtain institute
State third period corresponding retention ratio anticipation function；
4th curve matching unit, for being directed to the 4th period, according to retention ratio on the 240 of the target product
It carries out curve fitting with the retention ratio of life cycle last day, obtains the 4th period corresponding retention ratio prediction letter
Number.
Optionally, as one embodiment, the prediction module, including：
Day active users predicting unit, for according to preset active users calculation formula, described 1st day to N
Daily Adding User newly-increased retention ratio daily in counting and being 1st day to the N-1 days described in it calculates the target production
Online the N days day active users of product；
Wherein, the calculation formula isDAU(n)To apply online n-th
It day active users, DNU(i)For the online i-th day number that Adds User of application, R(n-i)For the n-th-i days newly-increased retention ratio, 1
≤i≤n。
Optionally, as one embodiment, described device further includes：
Function adjusts module, for using estimated by the retention ratio anticipation function day active users and
Existing practical day active users carry out the adjustment of retention ratio anticipation function.
Optionally, as one embodiment, the function adjusts module, including：
Practical active users acquiring unit, it is daily in online the T1 days to the T2 days of the target product for obtaining
Practical active users；
Active users acquiring unit is estimated, for according to the retention ratio anticipation function, determining that the target product exists
Line the is daily in T1 days to the T2 days to estimate active users；
Comparing unit, for by online the T1 days to the T2 days of the target product daily practical active users and
It estimates active users to be compared, obtains comparison result；
Parameter adjustment unit, in the prediction accuracy for determining the retention ratio anticipation function according to the comparison result
In the case of less than predetermined threshold value, according to the comparison result, the life cycle of the target product and/or the target are adjusted
The period that the life cycle of product is marked off；
Function generation unit is used for the life cycle according to the target product after adjustment and/or the target product
Period for being marked off of life cycle, generate new retention ratio anticipation function.
According to the third aspect of the embodiment of the present application, a kind of electronic equipment is provided, including：
Processor；And
It is arranged to the memory of storage computer executable instructions, the executable instruction makes the place when executed
Manage the step of device executes aforementioned any active users prediction technique.
According to the fourth aspect of the embodiment of the present application, a kind of computer storage media is provided, which is characterized in that the calculating
The one or more programs of machine readable storage medium storing program for executing storage, one or more of programs are when the electronics for being included multiple application programs
When equipment executes so that the electronic equipment executes the step of aforementioned any active users prediction technique.
In view of over time, in the different time sections of product life cycle, actually being stayed in each period
The dough softening for depositing rate is not unalterable, in the embodiment of the present application, can be directed to different time sections, generates different be used in advance
The retention ratio anticipation function of the newly-increased retention ratio in corresponding day is surveyed, as predicts that any active ues provide accurately statistic algorithm.When need
When predicting the N days day active users of On-line Product, using above-mentioned at least two retention ratio anticipation functions, it is active to carry out day
The prediction of number of users, compared with prior art, the embodiment of the present application can more calculate to a nicety out a day active users, to
Positive directive function is played to channel promotion, Cost evaluating and promotion products perfection.
Description of the drawings
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments described in specification, for those of ordinary skill in the art, before not making the creative labor property
It puts, other drawings may also be obtained based on these drawings.
Fig. 1 is the flow chart of the active users prediction technique of one embodiment of the application；
Fig. 2 is the flow chart of the generation method of the retention ratio anticipation function of one embodiment of the application；
Fig. 3 is the curve graph of the retention ratio anticipation function of one embodiment of the application；
Fig. 4 is the comparison for estimating any active ues number curve and practical any active ues number curve of one embodiment of the application
Figure；
Fig. 5 is the structural schematic diagram of the active users prediction meanss of one embodiment of the application；
Fig. 6 is the structural schematic diagram of the electronic equipment of one embodiment of the application.
Specific implementation mode
In order to make those skilled in the art more fully understand the technical solution in this specification, below in conjunction with the application
Attached drawing in embodiment, technical solutions in the embodiments of the present application are clearly and completely described, it is clear that described reality
It is only this specification a part of the embodiment to apply example, instead of all the embodiments.The embodiment of base in this manual, ability
The every other embodiment that domain those of ordinary skill is obtained without making creative work, should all belong to this theory
The range of bright book protection.
The embodiment of the present application provides a kind of active users prediction technique and device.
A kind of active users prediction technique provided by the embodiments of the present application is introduced first below.
In order to make it easy to understand, to involved in the embodiment of the present application to some concepts explain.
Day active users (Daily Active User, DAU) are usually used in reflecting website, the Internet, applications or network trip
The traffic-operating period of play, DAU were usually counted within (statistics day) on the one, logged in or used number of users (the removal weight of some product
The user logged in again).
Add User day number (Daily New User, DNU), refers to the number of users of same day new registration and login.
User is retained, is referred in internet industry, user begins to use application within certain time, when by one section
Between after, continue to the user using the application.
Retention ratio refers to that retaining user accounts for the ratio to Add User at that time.Wherein, retention ratio on the 1st=(same day is newly-increased
In user, in the 2nd day number of users also logged in of registration)/increase total number of users newly within first day；Retention ratio on the 7th=(first day is newly-increased
User in, also had the number of users logged at the 7th day of registration)/increase total number of users newly within first day；Retention ratio=(first on the 30th
In its newly-increased user, also have the number of users logged within the 30th day in registration)/increase total number of users newly within first day；Retention ratio on the 60th
=(in first day newly-increased user, also having the number of users logged within the 60th day in registration)/increases total number of users newly in first day；120
Day retention ratio=(in first day newly-increased user, also having the number of users logged in the 120th day in registration)/first day newly-increased total use
Amount；Retention ratio on the 240th=(in first day newly-increased user, also having the number of users logged in the 240th day in registration)/first day
Increase total number of users newly.
The life cycle of product refers to the time span that On-line Product is 0 until user's retention ratio.
Fig. 1 is the flow chart of the active users prediction technique of one embodiment of the application, and this method is applied to electronics
Equipment, as shown in Figure 1, this method may comprise steps of：Step 101, step 102, step 103 and step 104, wherein
In a step 101, prediction online the N days day active users of target product, N >=1 are determined.
It, can be when receiving the active users predictions request of user's triggering in the embodiment of the present application, determination needs to predict
Online the N days day active users of target product.In practical applications, user can be in several ways (for example, voice side
Formula, text output click button), to trigger active users predictions request.
In the embodiment of the present application, target product may include：Network application or electronic product (such as mobile phone, tablet computer
Deng).
For ease of description, next technical scheme is introduced by taking network application as an example.
In one example, the on-line time of network application A is on January 1st, 2018, when user wishes to predict network application
Active users (i.e. network application A online 30th day active users) of the A on January 30th, 2018, the user can be
Corresponding active users predictions request is triggered on electronic equipment, when electronic equipment receives the active users predictions request
When, determine the prediction online 30th day day active users of network application A.
In a step 102, the target product number that Adds User daily in online 1st day to the N days is obtained.
In the embodiment of the present application, it can obtain that target product is daily in online 1st day to the N days actually to Add User
Number, can also obtain target product in online 1st day to the N days daily estimate the number that Adds User.
In one example, however, it is determined that the prediction online 30th day day active users of network application A then obtain network and answer
It is counted with online 1st day Add User of A, the online 2nd day number that Adds User of network application A ..., network application A the online 29th
It Add User number and the online 30th day number that Adds User of network application A.
In step 103, according to preset at least two retention ratio anticipation functions, target product is determined online 1st day extremely
The newly-increased retention ratio daily in N-1 days；Wherein, the retention ratio anticipation function be used to establish the online number of days of target product with it is new
Increase the mapping relations between retention ratio.
In the embodiment of the present application, retention ratio anticipation function can be interpreted as：One abscissa is the online day of target product
Number, ordinate are the curve of newly-increased retention ratio.
In one example, however, it is determined that the prediction online 30th day day active users of network application A, then by online number of days
1,2 ..., 28 and 29 are brought into respectively in retention ratio anticipation function, obtain the online 1st day newly-increased retention ratio of network application A, net
The online 2nd day newly-increased retention ratio of network application A ..., the online 28th day newly-increased retention ratio of network application A and network application A exist
The 29th day newly-increased retention ratio of line.
In view of over time, the dough softening of practical retention ratio in different time periods is not unalterable, is changed
Sentence is talked about, and APP user retains trend in the different dough softening significant differences for retaining day, in order to utmostly reduce each period
The error of retention ratio and actual value is estimated, that is, ensures that retention ratio anticipation function is more accurate, in the embodiment of the present application, is stayed in fitting
When depositing rate anticipation function, it is segmented to be fitted, i.e., uses different retention indexs in different time sections, be fitted in different time sections
Retention ratio anticipation function, finally obtain multinomial retention ratio anticipation function.
Specifically, as shown in Fig. 2, Fig. 2 is the generation method of the retention ratio anticipation function of one embodiment of the application
Flow chart, this method may comprise steps of：Step 201, step 202, step 203 and step 204, wherein
In step 201, the life cycle of target product and multinomial retention index are obtained.
In the embodiment of the present application, the life cycle of target product is usually discreet value, for example, the Life Cycle of tool-class application
Phase is 600 days, and the life cycle of video class application is 720 days, and cell phone apparatus itself can also have update situation, according to the study
As a result, the period of hand-off machine is 6 months 1 year per capita.The retention ratio of the life cycle last day of target product is 0.
In the embodiment of the present application, 6 retention indexs of target product can be obtained, retaining index for this 6 may include：1
Day retention ratio, retention ratio on the 7th, retention ratio on the 30th, retention ratio on the 60th, retention ratios on the 120th and retention ratio on the 240th.
It should be noted that for the product newly reached the standard grade soon, if without so much retention index, it can be according to similar production
Product, which are estimated, obtains corresponding retention index.
In step 202, the life cycle of target product was divided at least two periods.
Preferably, in the embodiment of the present application, the life cycle of target product can be divided into four periods, at this point,
Above-mentioned steps 202 can specifically include following steps：
The life cycle of target product is divided into four periods, wherein first time period is target product the online 1st
, to the M1 days, second time period is target product online the M1+1 days to the M2 days for it, and the third period is that target product is online
The M2+1 days to the M3 days, the 4th period was online the M3+1 days of target product to life cycle last day.
In one example, the life cycle of network application A is 720 days, and four periods were divided by 720 days, respectively
For：Network application A is 1st day to the 90th day online, network application A is 91st day to the 140th day online, network application A the online 141st
It was to the 240th day, online 240th day to the 720th day of network application A.
In step 203, it for each period, is carried out curve fitting using different retention indexs, obtains at least two
A period corresponding retention ratio anticipation function a, wherein period corresponds to a retention ratio anticipation function.
Preferably, when the life cycle of target product is divided into four periods, 4 retention ratio predictions can be obtained
Function, at this point, above-mentioned steps 203 can specifically include following steps：
For first time period, retained according to retention ratio on the 1 of target product, retention ratio on the 7th, retention ratios on the 30th and 60 days
Rate carries out curve fitting, and obtains the corresponding retention ratio anticipation function of first time period；
For second time period, retained according to retention ratio on the 1 of target product, retention ratio on the 7th, retention ratio on the 30th, 60 days
Rate and retention ratio on the 120th carry out curve fitting, and obtain the corresponding retention ratio anticipation function of second time period；
For the third period, increases day by day and stay according to retention ratio on the 1 of target product, retention ratio on the 7th, retention ratio, 60 on the 30th
It deposits rate, retention ratios on the 120th and retention ratio on the 240th to carry out curve fitting, obtains third period corresponding retention ratio anticipation function；
For the 4th period, according to retention ratios on the 240 of target product and the retention ratio of life cycle last day into
Row curve matching obtains the 4th period corresponding retention ratio anticipation function.
In one example, the life cycle of network application A is 720 days, the online preceding 90 days curve matchings of network application A
Function is obtained according to four retention ratio on the 1st, retention ratio on the 7th, retention ratio on the 30th, retention ratio on the 60th index fittings；Network application A
Online 91~140 days iunction for curve, according to retention ratio on the 1st, retention ratio on the 7th, retention ratio on the 30th, retention ratio, 120 on the 60th
Day five retention indexs fittings of retention ratio obtain；Online 141~240 days iunction for curve of network application A, were stayed according to 1 day
It deposits rate, retention ratio on the 7th, retention ratio on the 30th, retention ratio on the 60th, retention ratio on the 120th, retention ratio six on the 240th and retains index fitting
It obtains；Online 240~720 days iunction for curve of network application A, according to retention ratios on the 240th and 720 days retention ratios (value
It is obtained for 0) fitting.
In the embodiment of the present application, excel or other statistical tools may be used, carry out curve fitting, and then corresponded to
Retention ratio anticipation function.
In the embodiment of the present application, it is contemplated that if only with first four retain index (i.e. retention ratio on the 1st, retention ratio on the 7th, 30 days
Retention ratio, retention ratio on the 60th), due to the limitation of fitting function, later stage discreet value meeting fall slows down and actual value gap
It is increasing, then it can lead to the elongation for predicting active users with the time, active users and actual value deviation are also increasingly
Greatly.If with six retain indexs (i.e. retention ratio on the 1st, retention ratio on the 7th, retention ratio on the 30th, retention ratio on the 60th, retention ratio on the 120th,
Retention ratio on the 240th) it is only fitted a formula and predicts, by retention ratio on the 120th, retention ratio on the 240th was relatively low is influenced, and was fitted letter
Preceding 60 days retention ratios that number calculates can be more relatively low than actual value, also results in forecasting inaccuracy.Therefore, divide not in the embodiment of the present application
It is fitted with the period and retains curve, the retention ratio of estimating that can utmostly meet reduction each period obtains error with actual value.
In one example, the life cycle of network application A is 720 days, the online preceding 90 days curve matchings of network application A
Function is f (x), and x represents online number of days, 1≤x≤90；Online 91~140 days iunction for curve of network application A are g (x),
X represents online number of days, 91≤x≤140；Online 141~240 days iunction for curve of network application A are z (x), and x is represented
Line number of days, 141≤x≤240；Online 240~720 days iunction for curve of network application A are y (x), and x represents online number of days,
240≤x≤720.4 retention ratio anticipation functions are finally obtained, respectively：
In the embodiment of the present application, the curve graph of every retention ratio anticipation function can also be exported, show user, so as to
User intuitively perceives changing tendency of the retention ratio with application online number of days passage.For example, Fig. 3 shows that 4 retention ratios are pre-
Survey the curve graph of function, wherein abscissa x represents online number of days, and ordinate R (x) represents retention ratio.
At step 104, according to every in Add User number and the 1st day to the N-1 days daily in the 1st day to the N days
It newly-increased retention ratio determines online the N days day active users of target product.
In the embodiment of the present application, it is contemplated that the retention number on the day of same day active users=all history excited user number,
Therefore, if by theoretical formula it is found that known history activation number and the different retention ratios for retaining day, can calculate any active ues
Number；Wherein, theoretical formula is as follows：
DAU=old users flow back+Add User
DAU(n)=DNU(1)*R(n-1)+DNU(2)*R(n-2)+...+DNU(n-1)*R(1)+DNU(n), R(n-1)It is newly-increased for (n-1)th day
Retention ratio.
In these cases, above-mentioned steps 104 can specifically include following steps：
According to preset active users calculation formula, Add User number and the 1st day daily in the 1st day to the N days
To newly-increased retention ratio daily in the N-1 days, online the N days day active users of target product are calculated；
Wherein, preset active users calculation formula isDAU(n)
For online n-th day day active users of application, DNU(i)For the online i-th day number that Adds User of application, R(n-i)It is the n-th-i days
Newly-increased retention ratio, 1≤i≤n.
As seen from the above-described embodiment, it is contemplated that over time, in the different time sections of product life cycle, often
The dough softening of practical retention ratio is not unalterable in a period, in the embodiment, can be directed to different time sections, generate
The retention ratio anticipation function of the different newly-increased retention ratios for predicting corresponding day as predicts that any active ues offer is accurately united
Calculating method.When needing to predict the N days day active users of On-line Product, letter is predicted using above-mentioned at least two retention ratios
Number carries out the prediction of day active users, and compared with prior art, the embodiment of the present application, which can more calculate to a nicety out, lives day
Jump number of users, to play positive directive function to channel promotion, Cost evaluating and promotion products perfection.
In another embodiment provided by the present application, it is contemplated that prediction is a process for establishing model and verification hypothesis,
In order to enable final prediction result is more accurate, the practical day active users in a period of time, verification and tune can be used
Whole retention ratio anticipation function, at this point, active users prediction technique provided by the present application is further comprising the steps of：Step 105,
In,
In step 105, the day active users and existing reality estimated by retention ratio anticipation function are utilized
Day active users carry out the adjustment of retention ratio anticipation function.
Preferably, in the embodiment of the present application, can utilize estimated by retention ratio anticipation function day active users,
And existing practical day active users, the optimization of retention ratio anticipation function is carried out, to improve the essence of day active users
Really estimate.At this point, above-mentioned steps 105 can specifically include following steps：
Obtain practical active users of the target product online the in T1 days to the T2 days daily；
According to retention ratio anticipation function, determines that target product online the is daily in T1 days to the T2 days and estimate any active ues
Number；
By practical active users daily in online the T1 days to the T2 days of target product and estimate active users into
Row compares, and obtains comparison result；For example, Fig. 4 shows the comparison diagram of active users prediction curve and actual curve.
When determining that the prediction accuracy of retention ratio anticipation function is less than predetermined threshold value according to comparison result, tied according to comparing
Fruit, the period that the life cycle of the life cycle and/or target product that adjust target product is marked off；
In the embodiment of the present application, predetermined threshold value can be 3%, can also be set according to actual needs.
In the embodiment of the present application, if discreet value is less than actual value, extend the life cycle of target product；If discreet value is high
In actual value, then shorten the life cycle of target product.If discreet value less than/be higher than actual value, adjust different retention curves
Corresponding retention number of days segment.
The time marked off according to the life cycle of the life cycle of the target product after adjustment and/or target product
Section, generates new retention ratio anticipation function.
In the embodiment of the present application, when receiving the active users predictions request of user's triggering again, stayed using new
The rate anticipation function of depositing is predicted.
In another embodiment provided by the present application, removing can predict that following active users become by available data
, can also be by formulating reasonable desired value except gesture, counter Add User day number, the retention ratio for pushing away target and reaching needs, so as to for
Product programming, channel promotion, financial cost assessment provide conscientiously useful guidance.
Fig. 5 is the structural schematic diagram of the active users prediction meanss of one embodiment of the application, as shown in figure 5, living
Jump user forecast device 500, may include：First determining module 501, the first acquisition module 502, the second determining module 503
With prediction module 504, wherein
First determining module 501, for determining prediction online the N days day active users of target product, N >=1；
First acquisition module 502 Adds User for daily in obtaining the target product online 1st day to the N days
Number；
Second determining module 503, for according to preset at least two retention ratio anticipation functions, determining the target product
Daily newly-increased retention ratio in online 1st day to the N-1 days, wherein the retention ratio anticipation function is for establishing the target
Mapping relations between the online number of days and newly-increased retention ratio of product；
Prediction module 504, for according to the daily number and 1st day described of Adding User in described 1st day to the N days
To newly-increased retention ratio daily in the N-1 days, online the N days day active users of the target product are determined.
As seen from the above-described embodiment, it is contemplated that over time, in the different time sections of product life cycle, often
The dough softening of practical retention ratio is not unalterable in a period, in the embodiment, can be directed to different time sections, generate
The retention ratio anticipation function of the different newly-increased retention ratios for predicting corresponding day as predicts that any active ues offer is accurately united
Calculating method.When needing to predict the N days day active users of On-line Product, letter is predicted using above-mentioned at least two retention ratios
Number carries out the prediction of day active users, and compared with prior art, the embodiment of the present application, which can more calculate to a nicety out, lives day
Jump number of users, to play positive directive function to channel promotion, Cost evaluating and promotion products perfection.
In another embodiment provided by the present application, active users prediction meanss 500 can also include：
Second acquisition module, the life cycle for obtaining the target product and multinomial retention index；
Division module, for the life cycle of the target product to be divided at least two periods；
Fitting module is carried out curve fitting using different retention indexs for being directed to each period, obtain it is described extremely
Corresponding retention ratio anticipation function of few two periods a, wherein period corresponds to a retention ratio anticipation function.
In another embodiment provided by the present application, the division module may include：
Period division unit, for the life cycle of the target product to be divided into four periods；
Wherein, first time period is the target product online 1st day to the M1 days, and second time period is produced for the target
Online the M1+1 days to the M2 days of product, third period are the target product online the M2+1 days to the M3 days, the 4th time
Section is online the M3+1 days of the target product to life cycle last day.
In another embodiment provided by the present application, the retention index may include：Retention ratio on the 1st, retention ratio on the 7th,
Retention ratio on the 30th, retention ratio on the 60th, retention ratios on the 120th and retention ratio on the 240th；
The fitting module may include：
First curve matching unit, for being directed to the first time period, according to retention ratio, 7 on the 1 of the target product
Day retention ratio, retention ratios on the 30th and retention ratio on the 60th carry out curve fitting, and it is pre- to obtain the corresponding retention ratio of the first time period
Survey function；
Second curve matching unit, for being directed to the second time period, according to retention ratio, 7 on the 1 of the target product
Day retention ratio, retention ratio on the 30th, retention ratios on the 60th and retention ratio on the 120th carry out curve fitting, and obtain the second time period pair
The retention ratio anticipation function answered；
Third curve matching unit, for being directed to the third period, according to retention ratio, 7 on the 1 of the target product
Day retention ratio, retention ratio on the 30th, 60 increase day by day retention ratio, retention ratios on the 120th and retention ratios on the 240th carry out curve fitting, and obtain institute
State third period corresponding retention ratio anticipation function；
4th curve matching unit, for being directed to the 4th period, according to retention ratio on the 240 of the target product
It carries out curve fitting with the retention ratio of life cycle last day, obtains the 4th period corresponding retention ratio prediction letter
Number.
In another embodiment provided by the present application, the prediction module 504 may include：
Day active users predicting unit, for according to preset active users calculation formula, described 1st day to N
Daily Adding User newly-increased retention ratio daily in counting and being 1st day to the N-1 days described in it calculates the target production
Online the N days day active users of product；
Wherein, the calculation formula isDAU(n)To apply online n-th
It day active users, DNU(i)For the online i-th day number that Adds User of application, R(n-i)For the n-th-i days newly-increased retention ratio, 1
≤i≤n。
In another embodiment provided by the present application, active users prediction meanss 500 can also include：
Function adjusts module, for using estimated by the retention ratio anticipation function day active users and
Existing practical day active users carry out the adjustment of retention ratio anticipation function.
In another embodiment provided by the present application, the function adjusts module, may include：
Practical active users acquiring unit, it is daily in online the T1 days to the T2 days of the target product for obtaining
Practical active users；
Active users acquiring unit is estimated, for according to the retention ratio anticipation function, determining that the target product exists
Line the is daily in T1 days to the T2 days to estimate active users；
Comparing unit, for by online the T1 days to the T2 days of the target product daily practical active users and
It estimates active users to be compared, obtains comparison result；
Parameter adjustment unit, in the prediction accuracy for determining the retention ratio anticipation function according to the comparison result
In the case of less than predetermined threshold value, according to the comparison result, the life cycle of the target product and/or the target are adjusted
The period that the life cycle of product is marked off；
Function generation unit is used for the life cycle according to the target product after adjustment and/or the target product
Period for being marked off of life cycle, generate new retention ratio anticipation function.
The method that active users prediction meanss 500 can also carry out embodiment illustrated in fig. 1, and realize that active users are predicted
The function of device embodiment shown in Fig. 5, details are not described herein for the embodiment of the present application.
Fig. 6 is the structural schematic diagram of the electronic equipment of one embodiment of the application, as shown in fig. 6, in hardware view, it should
Electronic equipment includes processor, further includes optionally internal bus, network interface, memory.Wherein, memory may include interior
It deposits, such as high-speed random access memory (Random-Access Memory, RAM), it is also possible to further include non-volatile memories
Device (non-volatile memory), for example, at least 1 magnetic disk storage etc..Certainly, which is also possible that other
The required hardware of business.
Processor, network interface and memory can be connected with each other by internal bus, which can be ISA
(Industry Standard Architecture, industry standard architecture) bus, PCI (Peripheral
Component Interconnect, Peripheral Component Interconnect standard) bus or EISA (Extended Industry Standard
Architecture, expanding the industrial standard structure) bus etc..The bus can be divided into address bus, data/address bus, control always
Line etc..For ease of indicating, only indicated with a four-headed arrow in Fig. 6, it is not intended that an only bus or a type of
Bus.
Memory, for storing program.Specifically, program may include program code, and said program code includes calculating
Machine operational order.Memory may include memory and nonvolatile memory, and provide instruction and data to processor.
Processor is from then operation in corresponding computer program to memory is read in nonvolatile memory, in logical layer
Active users prediction meanss are formed on face.Processor executes the program that memory is stored, and specifically for executing following behaviour
Make：
Determine prediction online the N days day active users of target product, N >=1；
Obtain the target product number that Adds User daily in online 1st day to the N days；And
According to preset at least two retention ratio anticipation functions, in determining the target product online 1st day to the N-1 days
Daily newly-increased retention ratio, wherein the retention ratio anticipation function is used to establish the online number of days of the target product and increases newly
Mapping relations between retention ratio；
In counting according to daily Adding User in described 1st day to the N days and is 1st day to the N-1 days described daily
Newly-increased retention ratio, determines online the N days day active users of the target product.
The method that active users prediction meanss disclosed in the above-mentioned embodiment illustrated in fig. 6 such as the application execute can be applied to
In processor, or realized by processor.Processor may be a kind of IC chip, the processing capacity with signal.
During realization, each step of the above method can pass through the integrated logic circuit of the hardware in processor or software form
Instruction is completed.Above-mentioned processor can be general processor, including central processing unit (Central Processing Unit,
CPU), network processing unit (Network Processor, NP) etc.；It can also be digital signal processor (Digital Signal
Processor, DSP), it is application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), existing
Field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device are divided
Vertical door or transistor logic, discrete hardware components.It may be implemented or execute and is in the embodiment of the present application disclosed each
Method, step and logic diagram.General processor can be microprocessor or the processor can also be any conventional place
Manage device etc..The step of method in conjunction with disclosed in the embodiment of the present application, can be embodied directly in hardware decoding processor and execute
At, or in decoding processor hardware and software module combination execute completion.Software module can be located at random access memory,
This fields such as flash memory, read-only memory, programmable read only memory or electrically erasable programmable memory, register maturation
In storage medium.The storage medium is located at memory, and processor reads the information in memory, and above-mentioned side is completed in conjunction with its hardware
The step of method.
The method that the electronic equipment can also carry out Fig. 1, and realize active users prediction meanss embodiment shown in Fig. 1
Function, details are not described herein for the embodiment of the present application.
Certainly, other than software realization mode, other realization methods are not precluded in the electronic equipment of this specification, such as
The mode etc. of logical device or software and hardware combining, that is to say, that the executive agent of following process flow is not limited to each
Logic unit can also be hardware or logical device.
The embodiment of the present application also proposed a kind of computer readable storage medium, the computer-readable recording medium storage one
A or multiple programs, the one or more program include instruction, and the instruction is when the portable electronic for being included multiple application programs
When equipment executes, the method that the portable electronic device can be made to execute embodiment illustrated in fig. 1, and specifically for executing with lower section
Method：
Determine prediction online the N days day active users of target product, N >=1；
Obtain the target product number that Adds User daily in online 1st day to the N days；And
According to preset at least two retention ratio anticipation functions, in determining the target product online 1st day to the N-1 days
Daily newly-increased retention ratio, wherein the retention ratio anticipation function is used to establish the online number of days of the target product and increases newly
Mapping relations between retention ratio；
In counting according to daily Adding User in described 1st day to the N days and is 1st day to the N-1 days described daily
Newly-increased retention ratio, determines online the N days day active users of the target product.
In short, the foregoing is merely the preferred embodiment of this specification, it is not intended to limit the protection of this specification
Range.For all spirit in this specification within principle, any modification, equivalent replacement, improvement and so on should be included in this
Within the protection domain of specification.
System, device, module or the unit that above-described embodiment illustrates can specifically realize by computer chip or entity,
Or it is realized by the product with certain function.It is a kind of typically to realize that equipment is computer.Specifically, computer for example may be used
Think personal computer, laptop computer, cellular phone, camera phone, smart phone, personal digital assistant, media play
It is any in device, navigation equipment, electronic mail equipment, game console, tablet computer, wearable device or these equipment
The combination of equipment.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology realizes information storage.Information can be computer-readable instruction, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), fast flash memory bank or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storages, magnetic tape cassette, tape magnetic disk storage or other magnetic storage apparatus
Or any other non-transmission medium, it can be used for storage and can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
Including so that process, method, commodity or equipment including a series of elements include not only those elements, but also wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that wanted including described
There is also other identical elements in the process of element, method, commodity or equipment.
Each embodiment in this specification is described in a progressive manner, identical similar portion between each embodiment
Point just to refer each other, and each embodiment focuses on the differences from other embodiments.Especially for system reality
For applying example, since it is substantially similar to the method embodiment, so description is fairly simple, related place is referring to embodiment of the method
Part explanation.
Claims (13)
1. a kind of active users prediction technique, which is characterized in that the method includes：
Determine prediction online the N days day active users of target product, N >=1；
Obtain the target product number that Adds User daily in online 1st day to the N days；And
According to preset at least two retention ratio anticipation functions, determine the target product in online 1st day to the N-1 days daily
Newly-increased retention ratio, wherein the retention ratio anticipation function is used to establish the online number of days of the target product and is retained with newly-increased
Mapping relations between rate；
It is daily in counting according to daily Adding User in described 1st day to the N days and is 1st day to the N-1 days described to increase newly
Retention ratio determines online the N days day active users of the target product.
2. according to the method described in claim 1, it is characterized in that, predicting letter according at least one of preset retention ratio described
Number, determine the target product in online 1st day to the N-1 days daily newly-increased retention ratio the step of before, further include：
Obtain the life cycle of the target product and multinomial retention index；
The life cycle of the target product was divided at least two periods；
It for each period, is carried out curve fitting using different retention indexs, obtains at least two period respectively
Corresponding retention ratio anticipation function a, wherein period corresponds to a retention ratio anticipation function.
3. according to the method described in claim 2, it is characterized in that, the life cycle by the target product be divided into
Few two periods, including：
The life cycle of the target product is divided into four periods；
Wherein, first time period is the target product online 1st day to the M1 days, and second time period is that the target product exists
Line the M1+1 days to the M2 days, third period are online the M2+1 days to the M3 days of the target product, and the 4th period was
Online the M3+1 days of the target product is to life cycle last day.
4. according to the method described in claim 3, it is characterized in that, the retention index includes：Retention ratio on the 1st is retained on the 7th
Rate, retention ratio on the 30th, retention ratio on the 60th, retention ratios on the 120th and retention ratio on the 240th；
It is described to be directed to each period, it is carried out curve fitting using different retention indexs, obtains at least two period
Corresponding retention ratio anticipation function, including：
For the first time period, according to retention ratio on the 1 of the target product, retention ratio on the 7th, retention ratios on the 30th and 60 days
Retention ratio carries out curve fitting, and obtains the corresponding retention ratio anticipation function of the first time period；
For the second time period, according to retention ratio on the 1 of the target product, retention ratio on the 7th, retention ratio on the 30th, 60 days
Retention ratio and retention ratio on the 120th carry out curve fitting, and obtain the corresponding retention ratio anticipation function of the second time period；
For the third period, according to retention ratio on the 1 of the target product, retention ratio on the 7th, retention ratio on the 30th, 60 days
Increase retention ratio, retention ratios on the 120th and retention ratio on the 240th to carry out curve fitting, obtains the third period corresponding retention ratio
Anticipation function；
For the 4th period, according to the retention of retention ratio and life cycle last day on the 240 of the target product
Rate carries out curve fitting, and obtains the 4th period corresponding retention ratio anticipation function.
5. according to the method described in claim 1, it is characterized in that, described increase newly according to daily in described 1st day to the N days
Number of users and it is 1st day to the N-1 days described in daily newly-increased retention ratio, determine the target product online the N days days
Active users, including：
According to preset active users calculation formula, it is 1st day to the N days described in the daily number and described of Adding User
Daily newly-increased retention ratio, calculates online the N days day active users of the target product in 1st day to the N-1 days；
Wherein, the calculation formula isDAU(n)For using online n-th day
Day active users, DNU(i)For the online i-th day number that Adds User of application, R(n-i)For the n-th-i days newly-increased retention ratio, 1≤i
≤n。
6. according to the method described in claim 1, it is characterized in that, the method further includes：
Utilize the day active users and existing practical day any active ues estimated by the retention ratio anticipation function
Number carries out the adjustment of retention ratio anticipation function.
7. according to the method described in claim 6, it is characterized in that, described utilize is estimated to obtain by the retention ratio anticipation function
Day active users and existing practical day active users, carry out the optimization of retention ratio anticipation function, including：
Obtain the online the practical active users daily in T1 days to the T2 days of the target product；
According to the retention ratio anticipation function, determine the target product online the in T1 days to the T2 days it is daily estimate it is active
Number of users；
By practical active users daily in online the T1 days to the T2 days of the target product and estimate active users into
Row compares, and obtains comparison result；
When determining that the prediction accuracy of the retention ratio anticipation function is less than predetermined threshold value according to the comparison result, according to institute
State comparison result, the life cycle of the life cycle and/or the target product that adjust the target product marked off when
Between section；
According to the life cycle of the life cycle of the target product after adjustment and/or the target product marked off when
Between section, generate new retention ratio anticipation function.
8. a kind of active users prediction meanss, which is characterized in that described device includes：
First determining module, for determining prediction online the N days day active users of target product, N >=1；
First acquisition module, for the number that Adds User daily in obtaining the target product online 1st day to the N days；
Second determining module, for according to preset at least two retention ratio anticipation functions, determining the target product the online 1st
It is to daily newly-increased retention ratio in the N-1 days, wherein the retention ratio anticipation function be used to establish the target product
Mapping relations between line number of days and newly-increased retention ratio；
Prediction module, for according to daily number and described 1st day of Adding User in described 1st day to the N days to N-1
Daily newly-increased retention ratio, determines online the N days day active users of the target product in it.
9. device according to claim 8, which is characterized in that described device further includes：
Second acquisition module, the life cycle for obtaining the target product and multinomial retention index；
Division module, for the life cycle of the target product to be divided at least two periods；
Fitting module is carried out curve fitting using different retention indexs for being directed to each period, obtains described at least two
A period corresponding retention ratio anticipation function a, wherein period corresponds to a retention ratio anticipation function.
10. device according to claim 9, which is characterized in that the division module, including：
Period division unit, for the life cycle of the target product to be divided into four periods；
Wherein, first time period is the target product online 1st day to the M1 days, and second time period is that the target product exists
Line the M1+1 days to the M2 days, third period are online the M2+1 days to the M3 days of the target product, and the 4th period was
Online the M3+1 days of the target product is to life cycle last day.
11. device according to claim 10, which is characterized in that the retention index includes：Retention ratio on the 1st is retained on the 7th
Rate, retention ratio on the 30th, retention ratio on the 60th, retention ratios on the 120th and retention ratio on the 240th；
The fitting module, including：
First curve matching unit according to retention ratio on the 1 of the target product, is stayed on the 7th for being directed to the first time period
It deposits rate, retention ratios on the 30th and retention ratio on the 60th to carry out curve fitting, obtains the corresponding retention ratio prediction letter of the first time period
Number；
Second curve matching unit according to retention ratio on the 1 of the target product, is stayed on the 7th for being directed to the second time period
It deposits rate, retention ratio on the 30th, retention ratios on the 60th and retention ratio on the 120th to carry out curve fitting, it is corresponding to obtain the second time period
Retention ratio anticipation function；
Third curve matching unit according to retention ratio on the 1 of the target product, is stayed on the 7th for being directed to the third period
It deposits rate, retention ratio on the 30th, 60 increase day by day retention ratio, retention ratios on the 120th and retention ratios on the 240th to carry out curve fitting, obtains described
Three periods corresponding retention ratio anticipation function；
4th curve matching unit, for being directed to the 4th period, according to retention ratio and life on the 240 of the target product
The retention ratio of life last day in period carries out curve fitting, and obtains the 4th period corresponding retention ratio anticipation function.
12. device according to claim 8, which is characterized in that the prediction module, including：
Day active users predicting unit, for according to preset active users calculation formula, it is 1st day to the N days described in
It is daily Add User number and it is 1st day to the N-1 days described in daily newly-increased retention ratio, calculate the target product and exist
The N days day active users of line；
Wherein, the calculation formula isDAU(n)For using online n-th day
Day active users, DNU(i)For the online i-th day number that Adds User of application, R(n-i)For the n-th-i days newly-increased retention ratio, 1≤i
≤n。
13. device according to claim 8, which is characterized in that described device further includes：
Function adjusts module, for active users and having using the day estimated by the retention ratio anticipation function
Practical day active users, carry out retention ratio anticipation function adjustment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810267284.9A CN108596652A (en) | 2018-03-28 | 2018-03-28 | Active users prediction technique and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810267284.9A CN108596652A (en) | 2018-03-28 | 2018-03-28 | Active users prediction technique and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108596652A true CN108596652A (en) | 2018-09-28 |
Family
ID=63623878
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810267284.9A Pending CN108596652A (en) | 2018-03-28 | 2018-03-28 | Active users prediction technique and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108596652A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109360031A (en) * | 2018-11-16 | 2019-02-19 | 北京奇虎科技有限公司 | A kind of prediction technique and device of active users |
| CN109711897A (en) * | 2018-12-29 | 2019-05-03 | 贵州创鑫旅程网络技术有限公司 | Day any active ues quantity prediction technique and device |
| CN109740822A (en) * | 2019-01-22 | 2019-05-10 | 深圳市酷开网络科技有限公司 | A kind of prediction processing method that OTT device is actively measured, system and storage medium |
| CN109858694A (en) * | 2019-01-28 | 2019-06-07 | 上海连尚网络科技有限公司 | A kind of method and apparatus of day active users prediction |
| CN111291936A (en) * | 2020-02-21 | 2020-06-16 | 北京金山安全软件有限公司 | Method and device for generating product life cycle estimation model and electronic equipment |
| CN111563026A (en) * | 2020-04-28 | 2020-08-21 | 浙江每日互动网络科技股份有限公司 | Data processing method and device, electronic equipment and computer readable storage medium |
| CN111767520A (en) * | 2020-06-12 | 2020-10-13 | 北京奇艺世纪科技有限公司 | User retention rate calculation method and device, electronic equipment and storage medium |
| CN112070533A (en) * | 2020-08-28 | 2020-12-11 | 上海连尚网络科技有限公司 | Method and equipment for predicting user retention |
| CN112116381A (en) * | 2020-08-31 | 2020-12-22 | 北京基调网络股份有限公司 | Moon life prediction method based on LSTM neural network, storage medium and computer equipment |
| CN112884503A (en) * | 2021-01-21 | 2021-06-01 | 百果园技术(新加坡)有限公司 | User scale prediction method, device, equipment and medium |
| CN113269370A (en) * | 2021-06-18 | 2021-08-17 | 腾讯科技(成都)有限公司 | Active user prediction method and device, electronic equipment and readable storage medium |
| CN113610555A (en) * | 2021-07-02 | 2021-11-05 | 北京达佳互联信息技术有限公司 | Target application delivery method and device, electronic equipment and storage medium |
| CN113763022A (en) * | 2021-02-08 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Method, device and equipment for determining number of touch users and storage medium |
| 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 |
|---|---|---|---|---|
| US20140310060A1 (en) * | 2006-07-27 | 2014-10-16 | Columbia Insurance Company | Method and System for Indicating Customer Information |
| CN105095646A (en) * | 2015-06-29 | 2015-11-25 | 北京京东尚科信息技术有限公司 | Data prediction method and electronic device |
| CN106897904A (en) * | 2017-02-24 | 2017-06-27 | 北京金山安全软件有限公司 | Product life cycle modeling method and device and electronic equipment |
| CN107038604A (en) * | 2017-03-30 | 2017-08-11 | 腾讯科技（深圳）有限公司 | The methods of exhibiting and device of product object number of users |
-
2018
- 2018-03-28 CN CN201810267284.9A patent/CN108596652A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140310060A1 (en) * | 2006-07-27 | 2014-10-16 | Columbia Insurance Company | Method and System for Indicating Customer Information |
| CN105095646A (en) * | 2015-06-29 | 2015-11-25 | 北京京东尚科信息技术有限公司 | Data prediction method and electronic device |
| CN106897904A (en) * | 2017-02-24 | 2017-06-27 | 北京金山安全软件有限公司 | Product life cycle modeling method and device and electronic equipment |
| CN107038604A (en) * | 2017-03-30 | 2017-08-11 | 腾讯科技（深圳）有限公司 | The methods of exhibiting and device of product object number of users |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109360031A (en) * | 2018-11-16 | 2019-02-19 | 北京奇虎科技有限公司 | A kind of prediction technique and device of active users |
| CN109711897A (en) * | 2018-12-29 | 2019-05-03 | 贵州创鑫旅程网络技术有限公司 | Day any active ues quantity prediction technique and device |
| CN109740822A (en) * | 2019-01-22 | 2019-05-10 | 深圳市酷开网络科技有限公司 | A kind of prediction processing method that OTT device is actively measured, system and storage medium |
| CN109858694A (en) * | 2019-01-28 | 2019-06-07 | 上海连尚网络科技有限公司 | A kind of method and apparatus of day active users prediction |
| CN111291936A (en) * | 2020-02-21 | 2020-06-16 | 北京金山安全软件有限公司 | Method and device for generating product life cycle estimation model and electronic equipment |
| CN111291936B (en) * | 2020-02-21 | 2023-10-17 | 北京金山安全软件有限公司 | Product life cycle prediction model generation method and device and electronic equipment |
| CN111563026A (en) * | 2020-04-28 | 2020-08-21 | 浙江每日互动网络科技股份有限公司 | Data processing method and device, electronic equipment and computer readable storage medium |
| CN111563026B (en) * | 2020-04-28 | 2023-07-14 | 每日互动股份有限公司 | Data processing method and device, electronic equipment and computer readable storage medium |
| CN111767520B (en) * | 2020-06-12 | 2023-07-04 | 北京奇艺世纪科技有限公司 | User retention rate calculation method and device, electronic equipment and storage medium |
| CN111767520A (en) * | 2020-06-12 | 2020-10-13 | 北京奇艺世纪科技有限公司 | User retention rate calculation method and device, electronic equipment and storage medium |
| CN112070533A (en) * | 2020-08-28 | 2020-12-11 | 上海连尚网络科技有限公司 | Method and equipment for predicting user retention |
| CN112116381A (en) * | 2020-08-31 | 2020-12-22 | 北京基调网络股份有限公司 | Moon life prediction method based on LSTM neural network, storage medium and computer equipment |
| 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 |
| CN112884503A (en) * | 2021-01-21 | 2021-06-01 | 百果园技术(新加坡)有限公司 | User scale prediction method, device, equipment and medium |
| CN113763022A (en) * | 2021-02-08 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Method, device and equipment for determining number of touch users and storage medium |
| CN113269370A (en) * | 2021-06-18 | 2021-08-17 | 腾讯科技(成都)有限公司 | Active user prediction method and device, electronic equipment and readable storage medium |
| CN113269370B (en) * | 2021-06-18 | 2023-12-12 | 腾讯科技(成都)有限公司 | Active user prediction method and device, electronic equipment and readable storage medium |
| CN113610555A (en) * | 2021-07-02 | 2021-11-05 | 北京达佳互联信息技术有限公司 | Target application delivery method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108596652A (en) | Active users prediction technique and device | |
| TWI745623B (en) | Model integration method and device | |
| US9031826B2 (en) | Method and apparatus for simulating operation in a data processing system | |
| CN104182801B (en) | A kind of method and apparatus for predicting website visiting amount | |
| EP3543922A1 (en) | Method and device for identifying risk of service to be processed and electronic device | |
| US20220146995A1 (en) | Determining causal models for controlling environments | |
| CN104281582B (en) | Pagination Display control method and device | |
| TWI714113B (en) | Method and device for forecasting foreign exchange transaction volume | |
| CN104361415B (en) | A kind of choosing method and device for showing information | |
| US20190325451A1 (en) | Information security system with risk assessment based on multi-level aggregations of risk predictors | |
| CN107437199A (en) | Platform earnings forecast method and device | |
| WO2017000828A1 (en) | Rule-based data object verification method, apparatus, system and electronic device | |
| CN109741177A (en) | Appraisal procedure, device and the intelligent terminal of user credit | |
| CN109284301A (en) | Verification of data method and device | |
| CN110020741A (en) | The method, apparatus and electronic equipment of data prediction | |
| CN106656662A (en) | Method and system for determining abnormal bandwidth, and electronic device | |
| WO2023029680A1 (en) | Method and apparatus for determining usable duration of magnetic disk | |
| CN110503235A (en) | The prediction technique and system of time series | |
| CN104424294A (en) | Information processing method and information processing device | |
| CN111835536B (en) | Flow prediction method and device | |
| CN111598425A (en) | Order flow control method and device | |
| CN105512564B (en) | A kind of anti-tamper verification method of data and device | |
| Audrino et al. | Oracle Properties, Bias Correction, and Bootstrap Inference for Adaptive Lasso for Time Series M‐Estimators | |
| CN110008386B (en) | Data generation, processing and evaluation method, device, equipment and medium | |
| Mölls et al. | Decision-making in sequential projects: expected time-to-build and probability of failure |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180928 |
|
| RJ01 | Rejection of invention patent application after publication |