CN109740822A - A kind of prediction processing method that OTT device is actively measured, system and storage medium - Google Patents
A kind of prediction processing method that OTT device is actively measured, system and storage medium Download PDFInfo
- Publication number
- CN109740822A CN109740822A CN201910060227.8A CN201910060227A CN109740822A CN 109740822 A CN109740822 A CN 109740822A CN 201910060227 A CN201910060227 A CN 201910060227A CN 109740822 A CN109740822 A CN 109740822A
- Authority
- CN
- China
- Prior art keywords
- month
- monthly
- amount
- current year
- year
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of prediction processing method that OTT device is actively measured, system and storage mediums, the method calculates the newly-increased activation equipment amount in current year N month to next year N-1 month month by month first, and it monthly enliven old equipment amount and retains coefficient and constant term, then it calculates the monthly of current year N month and enlivens old equipment amount, and calculate the monthly active device amount in month in current year N, the monthly active device amount for then calculating following each month month by month, until calculating the monthly active device amount in next year N-1 month.Method provided by the present invention, the upper monthly active device amount in old equipment amount and N-2 month in January previous year to the current year can be enlivened according to the newly-increased activation equipment amount in the N month in January previous year to the current year in historical data, the monthly of N-1 month 2 month to current year previous year, the monthly active device amount in following each month is calculated, compensates for the defect that the prior art lacks the prediction processing method that effective OTT device is actively measured.
Description
Technical field
The present invention relates to technical field of data processing, more particularly to a kind of prediction processing method that OTT device is actively measured,
System and storage medium.
Background technique
In daily service company's business activities, user in predicting and business revenue prediction are that company formulates future-oriented strategy plan
Major tasks；It can know the mobility scale of company's future operating results, by prediction to run adjustable strategies, resource adjustment
Data are provided to support.In OTT industry, user in predicting is the first step of business revenue prediction, and the influence to business revenue prediction is most important；But
The prediction processing method still actively measured without effective OTT device at present causes the raising of company's whole work efficiency to encounter bottleneck,
It is unfavorable for reducing entreprise cost.
As it can be seen that the existing technology needs to be improved and developed.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of prediction processing method that OTT device is actively measured, be
System and storage medium, it is intended to it solves the prior art and lacks the prediction processing method that effective OTT device is actively measured, lead to company
Whole work efficiency raising encounters bottleneck, is unfavorable for the problem of reducing entreprise cost.
Technical scheme is as follows:
A kind of prediction processing method that OTT device is actively measured comprising step:
The newly-increased activation equipment amount data in N-1 month in previous year N month to the current year are obtained respectively, and according to acquired
Data calculate separately the newly-increased activation equipment amount from month in current year N to next year each moon in N-1 month；The N month is
It is presently in month；
The monthly of N-1 month 2 month to current year previous year is obtained respectively and enlivens old equipment amount data, and is obtained respectively
The upper monthly active device amount data for taking N-2 month in January previous year to the current year are set always according to acquired monthly enliven
Standby amount data and upper monthly active device amount data, calculating is monthly to enliven old equipment amount retention coefficient and constant term；
According to calculating the gained newly-increased activation equipment amount in month in current year N, constant term and monthly enliven old equipment amount and retain
Coefficient and the monthly of month in current year N-1 enliven old equipment amount, calculate the monthly of current year N month and enliven old equipment amount；And
Monthly according to the newly-increased activation equipment amount and gained current year N month for calculating current year N month enlivens old equipment amount, calculates this
The monthly active device amount in annual N month；
According to calculating the gained newly-increased activation equipment amount in month in current year N+1, constant term, monthly enliven old equipment amount and retain
Coefficient and the monthly of month in current year N enliven old equipment amount, calculate the monthly of current year N+1 month and enliven old equipment amount；And root
Monthly according to the newly-increased activation equipment amount and month in current year N+1 for calculating gained month in current year N+1 enlivens old equipment amount, calculates
The monthly active device amount in month in current year N+1；And so on, until the monthly active of next year N-1 month is calculated
Equipment amount.
It is described to obtain the newly-increased sharp of N-1 month in previous year N month to the current year respectively in further preferred embodiment
Equipment amount data living, and calculated separately according to acquired data new from month in current year N to next year each moon in N-1 month
The step of increasing activation equipment amount specifically:
Current year N month to next year N-1 month is calculated one by one according to formula d [p]=a [q] * (1+b) * (1+c)
Newly-increased activation equipment amount, wherein d [p] is the newly-increased activation equipment amount in p month, and the value range in p month is current year N month
To next year N-1 month；A [q] is the newly-increased activation equipment amount in q month, and the value range in q month is previous year N month
To month in current year N-1；B is the monthly average year-on-year growth rate of newly-increased activation equipment, and c is shadow of company's future-oriented strategy to growth rate
Ring coefficient.
In further preferred embodiment, increases the monthly average year-on-year growth rate of activation equipment newly and calculated according to formula b=x/y
It obtains, x is the newly-increased activation equipment total amount in January in the current year to N-1 month, and y is the new of January previous year to N-1 month
Increase activation equipment total amount.
In further preferred embodiment, the monthly active old of N-1 month 2 month to current year previous year is obtained respectively
Equipment amount data, and the upper monthly active device amount data in N-2 month in January previous year to the current year, root are obtained respectively
According to it is acquired it is monthly enliven old equipment amount data and upper monthly active device amount data, calculate and monthly enliven old equipment amount and retain
The step of coefficient and constant term specifically:
Old equipment amount is enlivened as dependent variable using monthly, upper monthly active device amount is independent variable, linear regression model (LRM) is established,
It calculates and monthly enliven old equipment amount and retain coefficient and constant term.
In further preferred embodiment, the calculation formula of the linear regression model (LRM) is e=m0+m1*f, wherein e is
Monthly to enliven old equipment amount, f is upper monthly active device amount, and m0 is constant term, and m1 enlivens old equipment amount retention coefficient to be monthly.
It is described according to the newly-increased activation equipment amount, the constant that calculate gained month in current year N in further preferred embodiment
And it is monthly enliven that old equipment amount retains coefficient and the monthly of month in current year N-1 enlivens old equipment amount, calculate current year N
The monthly of month enlivens old equipment amount；And according to the newly-increased activation equipment amount and gained current year N month for calculating current year N month
Monthly the step of enlivening old equipment amount, calculating the monthly active device amount in current year N month specifically include:
The monthly of current year N month, which is calculated, according to formula h [n]=d [n]+m0+f [n-1] * m1 enlivens old equipment amount,
In, h [n] is that the monthly of current year N month enlivens old equipment amount, and d [n] is the newly-increased activation equipment amount in current year N month, and m0 is
The constant term, m1 be it is described it is monthly enliven old equipment amount and retain coefficient, f [n-1] is the monthly active old of current year N-1 month
Equipment amount；
The monthly active device amount in current year N month is calculated according to formula L [n]=d [n]+h [n], L [n] is current year N
The monthly active device amount in month.
In further preferred embodiment, it is described according to calculate gained month in current year N+1 newly-increased activation equipment amount, often
It is several, monthly to enliven that old equipment amount retains coefficient and the monthly of month in current year N enlivens old equipment amount, calculate the current year N+1 month
The monthly of part enlivens old equipment amount；And according to the newly-increased activation equipment amount and the month in current year N+1 for calculating gained month in current year N+1
The monthly of part enlivens old equipment amount, calculates the monthly active device amount in current year N+1 month；And so on, until being calculated
Next year the step of monthly active device amount in N-1 month specifically:
The monthly of current year N+1 month, which is calculated, according to formula h [n+1]=d [n+1]+m0+f [n] * m1 enlivens old equipment amount,
Wherein, h [n+1] is that the monthly of current year N+1 month enlivens old equipment amount, and d [n+1] is the newly-increased activation in current year N+1 month
Equipment amount, m0 are the constant term, m1 be it is described it is monthly enliven old equipment amount and retain coefficient, f [n] is current year N parts monthly
Enliven old equipment amount；
The monthly active device amount in current year N+1 month, L [n+1] are calculated according to formula L [n+1]=d [n+1]+h [n+1]
For the monthly active device amount in month in current year N+1；And so on, until the monthly work in next year N-1 month is calculated
Jump equipment amount.
A kind of prediction processing system that OTT device is actively measured comprising:
Newly-increased activation equipment amount predicts processing module, for obtaining N-1 month month to current year previous year N respectively
Newly-increased activation equipment amount data, and calculated separately according to acquired data each from month in current year N to next year N-1 month
The newly-increased activation equipment amount of the moon；The N month is to be presently in month；
Coefficients calculation block is retained, for obtaining the monthly active old of N-1 month 2 month to current year previous year respectively
Equipment amount data, and the upper monthly active device amount data in N-2 month in January previous year to the current year, root are obtained respectively
According to it is acquired it is monthly enliven old equipment amount data and upper monthly active device amount data, calculate and monthly enliven old equipment amount and retain
Coefficient and constant term；
With the newly-increased activation equipment amount prediction processing module and that retains that coefficients calculation block is connected monthly actively set
Standby amount prediction processing module, for according to calculating the newly-increased activation equipment amount in gained month in current year N, constant term and monthly active
Old equipment amount retains coefficient and the monthly of month in current year N-1 enlivens old equipment amount, calculates the monthly work in current year N month
Jump old equipment amount；And according to the monthly active old of the newly-increased activation equipment amount and gained current year N month for calculating current year N month
Equipment amount calculates the monthly active device amount in current year N month；And for according to calculate gained month in current year N+1 it is new
Increase activation equipment amount, constant term, it is monthly enliven that old equipment amount retains coefficient and the monthly of month in current year N enlivens old equipment amount,
It calculates the monthly of current year N+1 month and enlivens old equipment amount；And according to the newly-increased activation equipment for calculating gained month in current year N+1
Amount and the monthly of month in current year N+1 enliven old equipment amount, calculate the monthly active device amount in current year N+1 month；Successively class
It pushes away, until the monthly active device amount in next year N-1 month is calculated.
In further preferred embodiment, the prediction processing system that the OTT device is actively measured is connect with server, is used for
The historical data come transmitted by server is received, the historical data includes: the new of N month in January previous year to the current year
Increase activation equipment amount, the monthly of N-1 month 2 month to current year previous year enlivens old equipment amount and January previous year extremely
The upper monthly active device amount in month in current year N-2.
A kind of storage medium is stored thereon with computer program, realizes such as when the computer program is executed by processor
The step of prediction processing method that the upper OTT device is actively measured.
Compared with prior art, the prediction processing method that OTT device provided by the invention is actively measured calculates this month by month first
It the newly-increased activation equipment amount in annual N month to next year N-1 month and monthly enliven old equipment amount and retains coefficient and constant
, it then calculates the monthly of current year N month and enlivens old equipment amount, and old equipment amount is enlivened according to the monthly of month in current year N
The monthly active device amount in current year N month is calculated, then calculates the monthly active device amount in following each month month by month, until meter
Calculate the monthly active device amount in next year N-1 month.The prediction processing side that OTT device provided by the present invention is actively measured
Method, can newly-increased activation equipment amount according to the N month in January previous year to the current year in historical data, 2 month of previous year
Monthly to month in current year N-1 enlivens the upper of old equipment amount and N-2 month in January previous year to the current year and monthly actively sets
The monthly active device amount in following each month is calculated in standby amount, compensates for the prior art and lacks effective OTT device and actively measures
Prediction processing method defect, cause the raising of company whole work efficiency to encounter drive, being unfavorable for, which reduces entreprise cost, asks
Topic.
Detailed description of the invention
Fig. 1 is the flow chart for the prediction processing method that OTT device is actively measured in one embodiment.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the present invention, not
For limiting the present invention.
As shown in Figure 1, the prediction processing method that OTT device provided by the present invention is actively measured, comprising steps of
S100, the newly-increased activation equipment amount data for obtaining N-1 month in previous year N month to the current year respectively, and according to
Acquired data calculate separately the newly-increased activation equipment amount from month in current year N to next year each moon in N-1 month；The N
Month is to be presently in month.
Newly-increased activation equipment amount refers to the number of devices of initial activation equipment.Calculating the data used is server system
The historical data of meter is actual value；Calculating obtained data is predicted value, which is calculated according to preset rules.
It should be understood that N can be any number in 1 to 12；When N is 1, then used data are previous year
The newly-increased activation equipment amount in January to December, and it is calculated be January in the current year to December newly-increased activation equipment
Amount；When N is numerical value such as 10 between 1 to 12, used data include: October previous year to current year September part
Newly-increased activation equipment amount, and calculated is newly-increased activation equipment amount of the October in the current year to next year September part；When N is
When 12, used data are the newly-increased activation equipment amount in November in December previous year to the current year, and calculated are
The newly-increased activation equipment amount in December in the current year to next year November.
The step S100 specifically: current year N month is calculated according to formula d [p]=a [q] * (1+b) * (1+c) one by one
To the newly-increased activation equipment amount in next year N-1 month, wherein d [p] is the newly-increased activation equipment amount in p month, is taken in p month
Value range is current year N month to next year N-1 month；A [q] is the newly-increased activation equipment amount in q month, the value in q month
Range is N-1 month in previous year N month to the current year；B is the monthly average year-on-year growth rate of newly-increased activation equipment, and c is company
Influence coefficient of the future-oriented strategy to growth rate.
In the specific implementation, it increases the monthly average year-on-year growth rate of activation equipment newly to be calculated according to formula b=x/y, x is
The newly-increased activation equipment total amount in January in the current year to N-1 month, y are that the newly-increased activation in January previous year to N-1 month is set
Standby total amount.
| Days | Newly-increased activation equipment amount | Days | Newly-increased activation equipment amount |
| In January, 2017 | 44706 | In January, 2018 | 32836 |
| 2 months 2017 | 16745 | 2 months 2018 | 40274 |
| In March, 2017 | 15901 | In March, 2018 | 19764 |
| In April, 2017 | 17298 | In April, 2018 | 17713 |
| In May, 2017 | 16897 | In May, 2018 | 20026 |
| In June, 2017 | 16441 | In June, 2018 | 23840 |
| In July, 2017 | 20235 | In July, 2018 | 26071 |
| In August, 2017 | 21536 | In August, 2018 | 24342 |
| In September, 2017 | 22095 | In September, 2018 | 24414 |
| In October, 2017 | 24174 | In October, 2018 | 29009 |
| In November, 2017 | 24815 | In November, 2018 | 29778 |
| In December, 2017 | 26899 | In December, 2018 | 32279 |
Illustrate for the above table: 2018 monthly compared with newly-increased activation equipment in 2017 averagely to increase by a year-on-year basis
Rate is 20%, if influence coefficient of company's future-oriented strategy to growth rate is 10%, the newly-increased activation of estimated each moon in 2019 is set
Standby amount is in monthly, 2018 newly-increased activation equipment amount * (1+0.2) * (1+0.1), shown in table specific as follows:
S200, the monthly of N-1 month 2 month to current year previous year is obtained respectively enliven old equipment amount data, and
The upper monthly active device amount data for obtaining N-2 month in January previous year to the current year respectively, according to acquired monthly work
The old equipment amount data that jump and upper monthly active device amount data, calculating is monthly to enliven old equipment amount retention coefficient and constant term.
Upper monthly active device amount, which refers to spend in the month before, is at least previously used primary number of devices, such as 2018
For the data in year March, if certain equipment was previously used primary or more at 2 months 2018, which will be calculated as 2018
The upper monthly active device amount in March in year.
Monthly active device amount then refers to that this month is at least previously used primary number of devices, still in March, 2018 data
For, if certain equipment is previously used primary or more in March, 2018, which will be calculated as the monthly of in March, 2018
Active device amount.
It is monthly to enliven old equipment amount and subtract monthly newly-increased activation equipment amount equal to monthly active device amount.
In ground preferred embodiment of the invention, the step specifically: old equipment amount is enlivened as dependent variable using monthly, it is upper monthly
Active device amount is independent variable, establishes linear regression model (LRM), and calculating is monthly to enliven old equipment amount retention coefficient and constant term.
The calculation formula of the linear regression model (LRM) is e=m0+m1*f, wherein e enlivens old equipment amount to be monthly, and f is upper
Monthly active device amount, m0 are constant term, and m1 enlivens old equipment amount retention coefficient to be monthly.
In the specific implementation, which can pass through the retention coefficient meter in prediction processing system that OTT device is actively measured
It calculates module to complete, can also complete (by data and Formula Input Technology matlab, then to receive with calculation procedures such as external matlab
The result that matlab is exported).
According to upper table data carry out it is that regression analysis obtains the result is that: constant term m0 is 10350.28, and monthly active old
It is 0.9498 that equipment amount, which retains Coefficient m 1,.
S300, according to calculating the gained newly-increased activation equipment amount in month in current year N, constant term and monthly enliven old equipment amount
It retains coefficient and the monthly of month in current year N-1 enlivens old equipment amount, calculate the monthly of current year N month and enliven old equipment
Amount；And old equipment amount is enlivened according to the newly-increased activation equipment amount and the monthly of gained current year N month that calculate current year N month,
Calculate the monthly active device amount in current year N month.
In the specific implementation, S300 includes following two step:
The monthly of current year N month, which is calculated, according to formula h [n]=d [n]+m0+f [n-1] * m1 enlivens old equipment amount,
In, h [n] is that the monthly of current year N month enlivens old equipment amount, and d [n] is the newly-increased activation equipment amount in current year N month, and m0 is
The constant term, m1 be it is described it is monthly enliven old equipment amount and retain coefficient, f [n-1] is the monthly active old of current year N-1 month
Equipment amount.
The monthly active device amount in current year N month is calculated according to formula L [n]=d [n]+h [n], L [n] is current year N
The monthly active device amount in month.
S400, according to calculating the gained newly-increased activation equipment amount in month in current year N+1, constant term, monthly enliven old equipment
Amount retains coefficient and the monthly of month in current year N enlivens old equipment amount, calculates the monthly of current year N+1 month and enlivens old equipment
Amount；And old equipment is enlivened according to the newly-increased activation equipment amount and the monthly of month in current year N+1 that calculate gained month in current year N+1
Amount calculates the monthly active device amount in current year N+1 month；And so on, until the moon in next year N-1 month is calculated
Spend active device amount.
In the specific implementation, S400 includes following two step:
The monthly of current year N+1 month, which is calculated, according to formula h [n+1]=d [n+1]+m0+f [n] * m1 enlivens old equipment amount,
Wherein, h [n+1] is that the monthly of current year N+1 month enlivens old equipment amount, and d [n+1] is the newly-increased activation in current year N+1 month
Equipment amount, m0 are the constant term, m1 be it is described it is monthly enliven old equipment amount and retain coefficient, f [n] is current year N parts monthly
Enliven old equipment amount；
The monthly active device amount in current year N+1 month, L [n+1] are calculated according to formula L [n+1]=d [n+1]+h [n+1]
For the monthly active device amount in month in current year N+1；And so on, until the monthly work in next year N-1 month is calculated
Jump equipment amount.
According to newly-increased activation equipment amount, the constant term 10350.28, the moon in each month that above-mentioned second table is calculated
Degree enliven that old equipment amount retains in coefficient 0.9498 and third table it is monthly enliven old equipment amount, available each moon in 2019
It is part monthly to enliven old equipment amount and the specific value of monthly active device amount is as follows:
In the present invention further preferred embodiment, the prediction processing method that the OTT device is actively measured further includes step
Rapid: monthly according to each month being calculated enlivens the monthly interior average daily active device amount of old equipment amount, history and history is monthly
Active device amount calculates the monthly interior average daily active device amount in current year N month to next year N-1 month one by one；It is specific public
Formula is K [n]=h [n] * j, wherein the monthly interior average daily monthly active device amount of active device amount/history of j=history.
The present invention also provides a kind of prediction processing systems that OTT device is actively measured comprising:
Newly-increased activation equipment amount predicts processing module, for obtaining N-1 month month to current year previous year N respectively
Newly-increased activation equipment amount data, and calculated separately according to acquired data each from month in current year N to next year N-1 month
The newly-increased activation equipment amount of the moon；The N month is to be presently in month；Specifically as described in above method embodiment；
Coefficients calculation block is retained, for obtaining the monthly active old of N-1 month 2 month to current year previous year respectively
Equipment amount data, and the upper monthly active device amount data in N-2 month in January previous year to the current year, root are obtained respectively
According to it is acquired it is monthly enliven old equipment amount data and upper monthly active device amount data, calculate and monthly enliven old equipment amount and retain
Coefficient and constant term, specifically as described in above method embodiment；
With the newly-increased activation equipment amount prediction processing module and that retains that coefficients calculation block is connected monthly actively set
Standby amount prediction processing module, for according to calculating the newly-increased activation equipment amount in gained month in current year N, constant term and monthly active
Old equipment amount retains coefficient and the monthly of month in current year N-1 enlivens old equipment amount, calculates the monthly work in current year N month
Jump old equipment amount；And according to the monthly active old of the newly-increased activation equipment amount and gained current year N month for calculating current year N month
Equipment amount calculates the monthly active device amount in current year N month；And for according to calculate gained month in current year N+1 it is new
Increase activation equipment amount, constant term, it is monthly enliven that old equipment amount retains coefficient and the monthly of month in current year N enlivens old equipment amount,
It calculates the monthly of current year N+1 month and enlivens old equipment amount；And according to the newly-increased activation equipment for calculating gained month in current year N+1
Amount and the monthly of month in current year N+1 enliven old equipment amount, calculate the monthly active device amount in current year N+1 month；Successively class
It pushes away, until the monthly active device amount in next year N-1 month is calculated, specifically as described in above method embodiment.
In further preferred embodiment, the prediction processing system that the OTT device is actively measured is connect with server, is used for
The historical data come transmitted by server is received, the historical data includes: the new of N month in January previous year to the current year
Increase activation equipment amount, the monthly of N-1 month 2 month to current year previous year enlivens old equipment amount and January previous year extremely
The upper monthly active device amount in month in current year N-2, specifically as described in above method embodiment.
The present invention also provides a kind of storage mediums, are stored thereon with computer program, wherein the computer program quilt
The step of processor realizes the prediction processing method that OTT device as described above is actively measured when executing.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided by the present invention,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (SyNchliNk) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to protection of the invention
Range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (10)
1. a kind of prediction processing method that OTT device is actively measured, which is characterized in that comprising steps of
The newly-increased activation equipment amount data in N-1 month in previous year N month to the current year are obtained respectively, and according to acquired new
Increase activation equipment amount data and calculate separately the newly-increased activation equipment amount from month in current year N to next year each moon in N-1 month,
In, the N month is to be presently in month；
The monthly of N-1 month 2 month to current year previous year is obtained respectively and enlivens old equipment amount data, and is obtained respectively
The upper monthly active device amount data in one annual N-2 month in January to the current year monthly enliven old equipment amount according to acquired
Data and upper monthly active device amount data, calculating is monthly to enliven old equipment amount retention coefficient and constant term；
According to calculate the gained newly-increased activation equipment amount in month in current year N, constant term and it is monthly enliven old equipment amount and retain coefficient,
And the monthly of month in current year N-1 enlivens old equipment amount, calculates the monthly of current year N month and enlivens old equipment amount；And according to
It calculates the newly-increased activation equipment amount in current year N month and the monthly of gained current year N month enlivens old equipment amount, calculate the current year
The monthly active device amount in N month；
According to calculating the gained newly-increased activation equipment amount in month in current year N+1, constant term, monthly enliven old equipment amount and retain coefficient
And the monthly of month in current year N enlivens old equipment amount, calculates the monthly of current year N+1 month and enlivens old equipment amount；And according to meter
It calculates the newly-increased activation equipment amount in gained month in current year N+1 and the monthly of month in current year N+1 enlivens old equipment amount, calculate this year
Spend the monthly active device amount in N+1 month；And so on, until the monthly active device in next year N-1 month is calculated
Amount, and export prediction processing and prompted accordingly.
2. the prediction processing method that OTT device according to claim 1 is actively measured, which is characterized in that described to obtain respectively
The newly-increased activation equipment amount data in N-1 month month to current year previous year N, and according to acquired data calculate separately from
The step of month in current year N to next year newly-increased activation equipment amount of each moon in N-1 month specifically:
Calculate the newly-increased of current year N month to next year N-1 month one by one according to formula d [p]=a [q] * (1+b) * (1+c)
Activation equipment amount, wherein d [p] is the newly-increased activation equipment amount in p month, and the value range in p month is current year N month under
One N-1 month in year；A [q] is the newly-increased activation equipment amount in q month, and the value range in q month is previous year N month to originally
Annual N-1 month；B is the monthly average year-on-year growth rate of newly-increased activation equipment, and c is influence system of company's future-oriented strategy to growth rate
Number.
3. the prediction processing method that OTT device according to claim 2 is actively measured, which is characterized in that newly-increased activation equipment
Monthly average year-on-year growth rate is calculated according to formula b=x/y, and x is that the newly-increased activation in January in the current year to N-1 month is set
Standby total amount, y are the newly-increased activation equipment total amount in January previous year to N-1 month.
4. the prediction processing method that OTT device according to claim 1 is actively measured, which is characterized in that obtain upper one respectively
Annual the monthly of N-1 month in 2 months to the current year enlivens old equipment amount data, and obtains January previous year respectively to originally
The upper monthly active device amount data in annual N-2 month monthly enliven old equipment amount data and upper monthly work according to acquired
Jump equipment amount data, calculates monthly the step of enlivening old equipment amount retention coefficient and constant term specifically:
Old equipment amount is enlivened as dependent variable using monthly, and upper monthly active device amount is independent variable, establishes linear regression model (LRM), is calculated
It is monthly to enliven old equipment amount retention coefficient and constant term.
5. the prediction processing method that OTT device according to claim 4 is actively measured, which is characterized in that the linear regression
The calculation formula of model is e=m0+m1*f, wherein e enlivens old equipment amount to be monthly, and f is upper monthly active device amount, and m0 is
Constant term, m1 enliven old equipment amount retention coefficient to be monthly.
6. the prediction processing method that OTT device according to claim 1 is actively measured, which is characterized in that described according to calculating
It the newly-increased activation equipment amount in gained current year N month, constant term and monthly enliven old equipment amount and retains coefficient and current year N-
The monthly of January enlivens old equipment amount, calculates the monthly of current year N month and enlivens old equipment amount；And according to the calculating current year N month
The newly-increased activation equipment amount of part and the monthly of gained current year N month enliven old equipment amount, calculate the monthly work in current year N month
The step of equipment amount that jumps, specifically includes:
The monthly of current year N month is calculated according to formula h [n]=d [n]+m0+f [n-1] * m1 and enlivens old equipment amount, wherein h
[n] is that the monthly of current year N month enlivens old equipment amount, and d [n] is the newly-increased activation equipment amount in current year N month, and m0 is described
Constant term, m1 be it is described it is monthly enliven old equipment amount and retain coefficient, f [n-1] is that the monthly of current year N-1 month enlivens old equipment
Amount；
The monthly active device amount in current year N month is calculated according to formula L [n]=d [n]+h [n], L [n] is current year N month
Monthly active device amount.
7. the prediction processing method that OTT device according to claim 6 is actively measured, which is characterized in that
It is described according to calculating the gained newly-increased activation equipment amount in month in current year N+1, constant term, monthly enliven old equipment amount and retain
Coefficient and the monthly of month in current year N enliven old equipment amount, calculate the monthly of current year N+1 month and enliven old equipment amount；And root
Monthly according to the newly-increased activation equipment amount and month in current year N+1 for calculating gained month in current year N+1 enlivens old equipment amount, calculates
The monthly active device amount in month in current year N+1；And so on, until the monthly active of next year N-1 month is calculated
The step of equipment amount specifically:
The monthly of current year N+1 month, which is calculated, according to formula h [n+1]=d [n+1]+m0+f [n] * m1 enlivens old equipment amount,
In, h [n+1] is that the monthly of current year N+1 month enlivens old equipment amount, and d [n+1] is that the newly-increased activation in current year N+1 month is set
Standby amount, m0 are the constant term, and m1 is described monthly to enliven old equipment amount and retain coefficient, the monthly work that f [n] is current year N parts
Jump old equipment amount；
The monthly active device amount in current year N+1 month is calculated according to formula L [n+1]=d [n+1]+h [n+1], L [n+1] is this
The monthly active device amount in annual N+1 month；And so on, it is actively set until next year the monthly of N-1 month is calculated
Standby amount.
8. a kind of prediction processing system that OTT device is actively measured, which is characterized in that the prediction processing that the OTT device is actively measured
System includes:
Newly-increased activation equipment amount predicts processing module, for obtaining the newly-increased of N-1 month month to current year previous year N respectively
Activation equipment amount data, and calculated separately according to acquired data from month in current year N to next year each moon in N-1 month
Newly-increased activation equipment amount；The N month is to be presently in month；
Coefficients calculation block is retained, enlivens old equipment for obtaining the monthly of N-1 month 2 month to current year previous year respectively
Data are measured, and obtain the upper monthly active device amount data in N-2 month in January previous year to the current year respectively, according to institute
The monthly of acquisition enlivens old equipment amount data and upper monthly active device amount data, and calculating is monthly to enliven old equipment amount retention coefficient
And constant term；
The monthly active device amount being connected with the newly-increased activation equipment amount prediction processing module and retention coefficients calculation block
Processing module is predicted, for setting always according to the newly-increased activation equipment amount, constant term and monthly enliven that calculate gained month in current year N
Standby amount retains coefficient and the monthly of month in current year N-1 enlivens old equipment amount, calculates the monthly active old of current year N month
Equipment amount；And old equipment is enlivened according to the newly-increased activation equipment amount and the monthly of gained current year N month that calculate current year N month
Amount calculates the monthly active device amount in current year N month；And for sharp according to increasing newly for gained month in current year N+1 is calculated
Living equipment amount, constant term, it is monthly enliven that old equipment amount retains coefficient and the monthly of month in current year N enlivens old equipment amount, calculate
The monthly of month in current year N+1 enlivens old equipment amount；And according to calculate gained month in current year N+1 newly-increased activation equipment amount and
The monthly of month in current year N+1 enlivens old equipment amount, calculates the monthly active device amount in current year N+1 month；And so on, directly
To the monthly active device amount that next year N-1 month is calculated.
9. the prediction processing system that OTT device according to claim 8 is actively measured, which is characterized in that the OTT device is living
The prediction processing system of jump amount is connect with server, for receiving the historical data come transmitted by server, the historical data
It include: newly-increased activation equipment amount, the N-1 month 2 month to current year previous year in N month in January previous year to the current year
The monthly upper monthly active device amount for enlivening old equipment amount and N-2 month in January previous year to the current year.
10. a kind of storage medium, is stored thereon with computer program, which is characterized in that the computer program is held by processor
The step of prediction processing method that the OTT device as described in any one of claims 1 to 7 is actively measured is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910060227.8A CN109740822A (en) | 2019-01-22 | 2019-01-22 | A kind of prediction processing method that OTT device is actively measured, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910060227.8A CN109740822A (en) | 2019-01-22 | 2019-01-22 | A kind of prediction processing method that OTT device is actively measured, system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109740822A true CN109740822A (en) | 2019-05-10 |
Family
ID=66365632
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910060227.8A Pending CN109740822A (en) | 2019-01-22 | 2019-01-22 | A kind of prediction processing method that OTT device is actively measured, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109740822A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105787039A (en) * | 2016-02-25 | 2016-07-20 | 四川长虹电器股份有限公司 | Method for multi-period calculation and display of user retention rate |
| CN106600344A (en) * | 2016-12-30 | 2017-04-26 | 广州虎牙信息科技有限公司 | Method and apparatus for obtaining active user data of target product |
| CN106845722A (en) * | 2017-02-06 | 2017-06-13 | 腾讯科技（深圳）有限公司 | A kind of method and apparatus for predicting customer volume |
| 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 |
| CN108596652A (en) * | 2018-03-28 | 2018-09-28 | 麒麟合盛网络技术股份有限公司 | Active users prediction technique and device |
-
2019
- 2019-01-22 CN CN201910060227.8A patent/CN109740822A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105787039A (en) * | 2016-02-25 | 2016-07-20 | 四川长虹电器股份有限公司 | Method for multi-period calculation and display of user retention rate |
| CN106600344A (en) * | 2016-12-30 | 2017-04-26 | 广州虎牙信息科技有限公司 | Method and apparatus for obtaining active user data of target product |
| CN106845722A (en) * | 2017-02-06 | 2017-06-13 | 腾讯科技（深圳）有限公司 | A kind of method and apparatus for predicting customer volume |
| 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 |
| CN108596652A (en) * | 2018-03-28 | 2018-09-28 | 麒麟合盛网络技术股份有限公司 | Active users prediction technique and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3179319B1 (en) | Method for irrigation planning and system for its implementation | |
| CN109885469B (en) | Capacity expansion method, prediction model creation method, device, equipment and medium | |
| CN108446795B (en) | Power system load fluctuation analysis method and device and readable storage medium | |
| US20160357195A1 (en) | Water supplying method | |
| CN108154267A (en) | The fertilizer parameter regulation means and device of a kind of fertilizer applicator | |
| EP3769612A1 (en) | Irrigation water amount measurement device, irrigation water amount measurement method, and computer-readable recording medium | |
| CN112070284A (en) | Screening method, device, equipment and storage medium for component prediction | |
| KR101793625B1 (en) | Evaluation method and system of rainfall quantile considering climate change in nonstationary regional frequency analysis | |
| CN113344282A (en) | Method, system and computer readable medium for capacity data processing and allocation | |
| CN110390563A (en) | Quantization method, device, computer equipment and the storage medium of user's value | |
| CN109740822A (en) | A kind of prediction processing method that OTT device is actively measured, system and storage medium | |
| Morkisz et al. | Randomized derivative-free Milstein algorithm for efficient approximation of solutions of SDEs under noisy information | |
| CN108802860B (en) | Data correction method and data correction device | |
| CN109740799A (en) | Budget data generation method, device, computer equipment and storage medium | |
| CN110555082A (en) | data processing method, data processing device, computer equipment and storage medium | |
| Byrum et al. | Genetic gain performance metric accelerates agricultural productivity | |
| CN109800975A (en) | A kind of stock assessment method, apparatus, computer equipment and storage medium | |
| WO2023015615A1 (en) | Multi-channel fund transfer method and apparatus based on prediction model, and device and medium | |
| CN107480165A (en) | A kind of method and apparatus of page ranking | |
| US20180259916A1 (en) | Method and apparatus for operating a technical system | |
| CN115238940A (en) | Training method and device of power grid load prediction model | |
| CN108828342B (en) | Power equipment state detection method and device, computer equipment and storage medium | |
| CN112883590A (en) | System reliability verification test scheme determination method | |
| JP2006277093A (en) | Energy demand variation risk prediction system | |
| JPWO2018179117A1 (en) | Operation support system, operation support method and program |
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: 20190510 |
|
| RJ01 | Rejection of invention patent application after publication |