CN110020895A - A kind of dispensing object determines method, apparatus, equipment and medium - Google Patents
A kind of dispensing object determines method, apparatus, equipment and medium Download PDFInfo
- Publication number
- CN110020895A CN110020895A CN201910286206.8A CN201910286206A CN110020895A CN 110020895 A CN110020895 A CN 110020895A CN 201910286206 A CN201910286206 A CN 201910286206A CN 110020895 A CN110020895 A CN 110020895A
- Authority
- CN
- China
- Prior art keywords
- dispensing
- channel
- total
- launching
- vector
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- 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
- G06Q30/0202—Market predictions or forecasting for commercial activities
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Computational Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Physics (AREA)
- Evolutionary Biology (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Probability & Statistics with Applications (AREA)
- Operations Research (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application provides a kind of dispensing objects to determine method, apparatus, equipment and medium, this method comprises: obtaining for each dispensing total resources value for launching channel；Based on the corresponding prediction total flow of the dispensing total resources value and the corresponding dispensing ratio of each dispensing channel, each predicted flow rate for launching channel is determined；Based on each predicted flow rate for launching channel and each transformation ratio for launching channel, determine each dispensing for launching channel to vector.Accuracy of the dispensing that the application can be improved to vector.
Description
Technical field
This application involves technical field of data processing, determine method, apparatus in particular to a kind of dispensing object, set
Standby and medium.
Background technique
Currently, for line service on vehicle (e.g., used car, new car etc.), user generally passes through under line or (e.g., net on line
Stand, terminal applies etc.) mode of registration, the online vehicle for needing to sell on corresponding service platform, and for service platform
For, the vehicle for having registered user not necessarily can satisfy the demand that automobile-used family is purchased in service platform, and therefore, prediction is flat in service
The amount of the online vehicle of platform is particularly important.
The prior art is in the online vehicle of adjustment service platform, the online vehicle or shadow that often obtain to historical time section
The factor of sound is analyzed, and then determines the online factor of vehicle that influences, still, wider above by the analysis to historical data
It is general, it is unable to the quantity of the online vehicle of Accurate Prediction.
Summary of the invention
In view of this, a kind of dispensing object of being designed to provide of the application determines method, apparatus, equipment and medium, with
Convenient for improving accuracy of the obtained dispensing to vector.
In a first aspect, the embodiment of the present application, which provides a kind of dispensing object, determines method, this method comprises:
It obtains for each dispensing total resources value for launching channel；
Based on the corresponding prediction total flow of the dispensing total resources value and the corresponding dispensing ratio of each dispensing channel
Example determines each predicted flow rate for launching channel；
Based on each predicted flow rate for launching channel and each transformation ratio for launching channel, determine each described
The dispensing of channel is launched to vector.
Optionally, it is determined according to following manner and launches the corresponding prediction total flow of total resources value:
The dispensing total resources value is input to flux prediction model, it is total to obtain the corresponding prediction of the dispensing total resources value
Flow.
Optionally, the flux prediction model is determined according to following manner:
It obtains history and launches total resources value and corresponding history total flow；
Total resources value is launched to the history using regression algorithm and corresponding history total flow does recurrence processing, obtains institute
State flux prediction model.
Optionally, described to be based on the corresponding prediction total flow of the dispensing total resources value and each dispensing channel pair
The dispensing ratio answered determines each predicted flow rate for launching channel, comprising:
For each dispensing channel, by multiplying for the prediction total flow and the corresponding dispensing ratio of dispensing channel
Product, the predicted flow rate as the dispensing channel.
Optionally, the transformation ratio based on each predicted flow rate for launching channel and each dispensing channel,
Determine each dispensing for launching channel to vector, comprising:
The product of the predicted flow rate of the dispensing channel and corresponding transformation ratio is made for each dispensing channel
For the dispensing channel dispensing to vector.
Optionally, after each dispensing for launching channel of the determination is to vector, further includes:
If each dispensing for launching channel to vector and it is default launch to the value of vector and value and be less than setting launch pair
Vector threshold value adjusts each dispensing for launching channel to vector then based on the priority for launching channel.
Second aspect, the embodiment of the present application provide a kind of dispensing object determining device, which includes:
Module is obtained, is directed to each dispensing total resources value for launching channel for obtaining；
First determining module, for being based on the corresponding prediction total flow of the dispensing total resources value and each dispensing
The corresponding dispensing ratio of channel determines each predicted flow rate for launching channel；
Second determining module, for based on each predicted flow rate for launching channel and each turn for launching channel
Change coefficient, determines each dispensing for launching channel to vector.
Optionally, first determining module, which is also used to be determined according to following manner, launches the corresponding prediction of total resources value always
Flow:
The dispensing total resources value is input to flux prediction model, it is total to obtain the corresponding prediction of the dispensing total resources value
Flow.
The third aspect, the embodiment of the present application provide a kind of computer equipment, including memory, processor and are stored in institute
The computer program that can be run on memory and on the processor is stated, the processor executes real when the computer program
The step of existing above method.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, the computer-readable storage
The step of being stored with computer program on medium, the above method executed when the computer program is run by processor.
Dispensing object provided by the present application determines method, after obtaining for each dispensing total resources value for launching channel, base
In launching the corresponding prediction total flow of total resources value, and the corresponding dispensing ratio of each dispensing channel, each dispensing channel is determined
Predicted flow rate further based on each predicted flow rate for launching channel, and each transformation ratio for launching channel, determines each dispensing
The dispensing of channel is to vector.In this way, accuracy of the dispensing that can be improved by prediction total flow to vector, meanwhile,
It improves to launch and accuracy is applied to vector.
To enable the above objects, features, and advantages of the application to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
Technical solution in ord to more clearly illustrate embodiments of the present application, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only some embodiments of the application, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is a kind of flow diagram launched object and determine method provided by the embodiments of the present application；
Fig. 2 is a kind of relation schematic diagram launched between resource value and actual flow increment provided by the embodiments of the present application；
Fig. 3 is provided by the embodiments of the present application a kind of to obtain the schematic diagram of predicted flow rate based on historical traffic；
Fig. 4 is a kind of the first structural schematic diagram for launching object determining device provided by the embodiments of the present application；
Fig. 5 is a kind of second of structural schematic diagram for launching object determining device provided by the embodiments of the present application；
Fig. 6 is a kind of structural schematic diagram of computer equipment provided by the embodiments of the present application.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
Middle attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only
It is some embodiments of the present application, instead of all the embodiments.The application being usually described and illustrated herein in the accompanying drawings is real
The component for applying example can be arranged and be designed with a variety of different configurations.Therefore, below to the application's provided in the accompanying drawings
The detailed description of embodiment is not intended to limit claimed scope of the present application, but is merely representative of the selected reality of the application
Apply example.Based on embodiments herein, those skilled in the art institute obtained without making creative work
There are other embodiments, shall fall in the protection scope of this application.
The embodiment of the present application provides a kind of dispensing object and determines method, as shown in Figure 1, method includes the following steps:
S101 is obtained for each dispensing total resources value for launching channel；
Here, launching channel includes but is not limited to terminal applies, Web page push etc., wherein terminal applies can be but not
Video Applications, music application, the outside application etc. being limited in mobile terminal, web application can be but not limited to be applied to calculate
Free search and webpage (SEO), own website in machine equipment etc., the application not limits this；Launching total resources value is usually
Obtained according to historical data analysis, the dispensing total resources value characterize it is each launch channel dispensings resource and value, for example, dispensing
Resource can be the value of acquisition desired flow.
S102 is based on the corresponding prediction total flow of the dispensing total resources value and the corresponding throwing of each dispensing channel
Ratio is put, determines each predicted flow rate for launching channel；
Here, prediction total flow is the corresponding total predicted flow rate of each dispensing channel, for example, note of the user in each default channel
Volume amount；What dispensing ratio was generally determined based on the historical traffic of each default channel, it launches ratio characterization and each presets channel
Flow accounts for the ratio of the flow of all default channels, and the flow accounting of the bigger characterization of the ratio default channel is bigger.
In specific implementation, for each dispensing channel, the prediction total flow is corresponding with the dispensing channel
The product of dispensing ratio, the predicted flow rate as the dispensing channel.
For example, launching channel is respectively A, B, C, D, it is that 0.5, B dispensing channel is corresponding that A, which launches the corresponding dispensing ratio of channel,
Dispensing ratio be that launch the corresponding dispensing ratio of channel be the corresponding dispensing ratio of 0.1, D dispensing channel to 0.3, C is 0.1, in advance
Surveying total flow is 10000, then the predicted flow rate for launching channel A is 10000*0.5=5000, and the predicted flow rate for launching channel B is
10000*0.3=3000, the predicted flow rate for launching channel C is 10000*0.1=1000, and the predicted flow rate for launching channel D is
10000*0.1=1000.
After getting dispensing total resources value, it can determine that launching the corresponding prediction of total resources value always flows according to following manner
Amount:
The dispensing total resources value is input to flux prediction model, it is total to obtain the corresponding prediction of the dispensing total resources value
Flow.
Wherein, the flux prediction model is determined according to following manner:
It obtains history and launches total resources value and corresponding history total flow；
Total resources value is launched to the history using regression algorithm and corresponding history total flow does recurrence processing, obtains institute
State flux prediction model.
Here, regression algorithm can be but not limited to linear regression algorithm, Exponential Backoff Algorithm, multivariate regression algorithm etc.,
The application can be used novel regression algorithm and carry out recurrence processing, return the process of processing in existing skill by regression algorithm
Have detailed introduction in art, is no longer excessively illustrated herein.
In specific implementation, mode one, the history for obtaining historical time section launches total resources value and historical time section is corresponding
History total flow, with history total flow to history launch total resources value carry out regression analysis, obtain flux prediction model.Its
In, at the time of historical time section can launch total resources value for what is obtained before a week, continuous multiple weeks, one
The moon, a season etc., for example, the acquisition moment for launching resource is in December, 2018, historical time section can be in October, 2018.
Mode two, the history for obtaining multiple historical time sections launches total resources value and the corresponding history of historical time section always flows
Amount launches total resources value to opposite history with history total flow undulating value and carries out regression analysis, obtains flux prediction model.Its
In, history total flow undulating value can in two neighboring historical time section, the history total flow of next historical time section with
The ratio of the history total flow of a upper historical time section, it can be two neighboring historical time that opposite history, which launches total resources value,
Duan Zhong, the history of next historical time section launches total resources value and the history of a upper historical time section launches total resources value
The ratio for launching the maximum value in total resources value in difference, with two historical time sections.
Mode three, the history for obtaining multiple historical time sections launches total resources value and the corresponding history of historical time section always flows
Amount launches total resources value to opposite history with history total flow increasing value and carries out regression analysis, obtains flux prediction model.Its
In, history total flow increasing value can in two neighboring historical time section, the history total flow of next historical time section with
The difference of the history total flow of a upper historical time section, it can be two neighboring historical time that opposite history, which launches total resources value,
Duan Zhong, the history of next historical time section launches total resources value and the history of a upper historical time section launches total resources value
The ratio for launching the maximum value in total resources value in difference, with two historical time sections.
It is illustrated for the case where total resources value carries out regression analysis is launched to history with history total flow.It is total with history
Flow y launches total resources value x to history1It returns, obtains predicted flow rate value yt:
yt=β0+β1x
Wherein, ytTo be fitted predicted flow rate value, x1Total resources value, β are launched for history0To β1Total resources value is launched for history
Weight.
It is exemplified below and the process returned is done to history dispensing total resources value x with history total flow y, it is assumed that history is total
Flow sequence is { y1, y2 }, and it is { x1, x2 } that corresponding history, which launches total resources value, respectively launches history total flow and history
Total resources value has to regression analysis formula:
y1=β0+β1x1
y2=β0+β1x1
The weight that history launches total resources value is obtained to above-mentioned two solving simultaneous equation.Here it returns and divides for convenience of explanation
The case where analysis formula is only illustrated with two data instances, other two ways carry out regression analysis, is not described herein.
For the flux prediction model that mode one obtains, mode will be updated to for each dispensing total resources value for launching channel
In one obtained flux prediction model, obtain for each corresponding prediction total flow of dispensing total resources value for launching channel.
For example, being s for each dispensing total resources value for launching channel, β is being obtained0、β1Afterwards, total resources value will be launched to substitute into
yt=β0+β1X obtains prediction total flow.
For the flux prediction model that mode two obtains, by the current dispensing resource total value of calculating and upper dispensing resource
The ratio of total value is updated in the flux prediction model that mode two obtains, and is obtained for each dispensing resource total value pair for launching channel
The predicted flow rate undulating value answered, using the product of the predicted flow rate undulating value and a upper flow as current prediction total flow.
For the flux prediction model that mode three obtains, by the current dispensing resource total value of calculating and upper dispensing resource
The difference of total value is updated in the flux prediction model that mode two obtains, and is obtained for each dispensing resource total value pair for launching channel
The predicted flow rate undulating value answered, by the predicted flow rate difference and a upper flow and be worth as current prediction total flow.
S103 is determined each based on each predicted flow rate for launching channel and each transformation ratio for launching channel
The dispensing for launching channel is to vector.
Here, transformation ratio characterization predicted flow rate is converted into the ratio launched to vector, and the ratio is higher, characterizes current throw
Put channel switch to launch object probability it is bigger, wherein transformation ratio includes first transformation ratio and work of the flow to work order amount
Single amount is to dispensing to the second transformation ratio of vector.
Based on each predicted flow rate for launching channel and each transformation ratio for launching channel, each institute is determined
When stating the dispensing for launching channel to vector, specifically includes the following steps:
The product of the predicted flow rate of the dispensing channel and corresponding transformation ratio is made for each dispensing channel
For the dispensing channel dispensing to vector.
In specific implementation, for each dispensing channel, by the predicted flow rate of the dispensing channel and corresponding first conversion
The product of coefficient and the second transformation ratio, the dispensing as the dispensing channel is to vector.
For example, launching channel includes A, B, C, the predicted flow rate that A launches channel is S1, and the predicted flow rate that B launches channel is
The predicted flow rate that S2, C launch channel is S3, and corresponding first transformation ratio of A dispensing channel is α 1, the second transformation ratio is β 1, B
Corresponding first transformation ratio of dispensing channel is α 2, the second transformation ratio is β 2, and C launches corresponding first transformation ratio of channel and is
α 3, the second transformation ratio are β 3, and the dispensing that A launches channel is S1* α 1* β 1 to vector, and the dispensing that B launches channel is to vector
The dispensing that S2* α 2* β 2, C launch channel is S3* α 3* β 3 to vector.
In the specific implementation process, further include other than obtaining each dispensing for launching channel to vector by predicted flow rate
For the specific dispensing resource value for launching channel, specific dispensing channel includes that channel is launched in navigation, information flow launches channel, search
Engine launches channel, channel is launched in own operation, recalls and launches channel etc., and the corresponding dispensing resource value of specific dispensing channel can be with
Determines according to actual conditions, practical need may not be able to be met to vector by the dispensing that predicted flow rate obtains each dispensing channel
It asks, therefore, it is necessary to adjust each dispensing for launching channel to vector, when adjusting each dispensing for launching channel to vector, further includes
Following steps:
If each dispensing for launching channel to vector and it is default launch to the value of vector and value and be less than setting launch pair
Vector threshold value adjusts each dispensing for launching channel to vector then based on the priority for launching channel.
Here, it presets and launches for vector is to launch channel for feature, which can be logical to vector
Cross the product determination of flow the first transformation ratio corresponding with specific channel and the second transformation ratio that calculate specific channel；It throws
Put it is generally preset to vector threshold value, e.g., 10000,20000 etc., can be determines according to actual conditions；Launch the excellent of channel
First grade can determine that flow is higher, then the priority for launching channel is higher according to the flow for launching channel.
In specific implementation, calculate each dispensing for launching channel to vector and value, by this and value as first and value, meter
Calculate this first and value and default injected volume second and value, if second and value be less than and set dispensing to vector threshold value, calculate the
One and value and setting launch to the difference between vector, according to setting ratio, which is assigned to priority from high to low
The dispensing of channel is launched in vector.
For example, launching channel includes A, B, C, it is B, C, A that A, B, C, which are launched after channel according to priority sorts from high to low, if
Fixed launch to vector threshold value is T0, and the dispensing that A launches channel is T1 to vector, and the dispensing that B launches channel is T2 to vector, and C is thrown
The dispensing for putting channel is T3 to vector, and presetting dispensing is T to vectorf, A, B, C launch channel and it is specific launch channel and value be
TWith=T1+T2+T3+Tf, when should and be worth less than T0, calculate T0-TWith, it is γ 1: γ that A, B, C, which launch the corresponding setting ratio of channel,
2: γ 3, then launching adjusted launch to vector of channel A is 1 (T0-T of T1+ γWith), launch channel B dispensing object adjusted
Amount is 2 (T0-T of T2+ γWith), launching adjusted launch to vector of channel C is 3 (T0-T of T3+ γWith)。
For launching channel and include A, B, C, corresponding launch of each dispensing channel can refer to following table to vector:
In actual application, for such as free search and webpage (SEO) of brand class, own website are launched
It is illustrated, brand class launches the relational graph between resource value and actual flow increment, and can refer to 2, (figure is by history number
According to determining), it is real at 2016 to 2017 to determine that method is based on brand class using dispensing object provided by the embodiments of the present application
Border volume forecasting obtains the diagram of predicted flow rate in 2018, can refer to Fig. 3.
Dispensing object provided by the present application determines method, after obtaining for each dispensing total resources value for launching channel, base
In launching the corresponding prediction total flow of total resources value, and the corresponding dispensing ratio of each dispensing channel, each dispensing channel is determined
Predicted flow rate further based on each predicted flow rate for launching channel, and each transformation ratio for launching channel, determines each dispensing
The dispensing of channel is to vector.In this way, accuracy of the dispensing that can be improved by prediction total flow to vector, meanwhile,
It improves to launch and accuracy is applied to vector.
The embodiment of the present application provides a kind of dispensing object determining device, as shown in figure 4, the device includes:
Module 41 is obtained, is directed to each dispensing total resources value for launching channel for obtaining；
First determining module 42, for being based on the corresponding prediction total flow of the dispensing total resources value and each throwing
The corresponding dispensing ratio of channel is put, determines each predicted flow rate for launching channel；
Second determining module 43, for based on each predicted flow rate for launching channel and each described launching channel
Transformation ratio determines each dispensing for launching channel to vector.
Optionally, first determining module 42, which is also used to be determined according to following manner, launches the corresponding prediction of total resources value
Total flow:
The dispensing total resources value is input to flux prediction model, it is total to obtain the corresponding prediction of the dispensing total resources value
Flow.
Optionally, first determining module 42 is also used to determine the flux prediction model according to following manner:
It obtains history and launches total resources value and corresponding history total flow；
Total resources value is launched to the history using regression algorithm and corresponding history total flow does recurrence processing, obtains institute
State flux prediction model.
Optionally, first determining module 42 is specifically used for:
For each dispensing channel, by multiplying for the prediction total flow and the corresponding dispensing ratio of dispensing channel
Product, the predicted flow rate as the dispensing channel.
Optionally, second determining module 43 is specifically used for:
The product of the predicted flow rate of the dispensing channel and corresponding transformation ratio is made for each dispensing channel
For the dispensing channel dispensing to vector.
The embodiment of the present application provides a kind of dispensing object determining device again, as shown in figure 5, the dress in the device and Fig. 4
It sets and compares, further includes: adjustment module 44, the adjustment module 44 are used for:
If each dispensing for launching channel to vector and it is default launch to the value of vector and value and be less than setting launch pair
Vector threshold value adjusts each dispensing for launching channel to vector then based on the priority for launching channel.
Method is determined corresponding to the dispensing object in Fig. 1, and the embodiment of the present application also provides a kind of computer equipments, such as scheme
Shown in 6, which includes memory 1000, processor 2000 and is stored on the memory 1000 and can be in the processor 2000
The computer program of upper operation, wherein above-mentioned processor 2000 realizes that above-mentioned dispensing object is true when executing above-mentioned computer program
The step of determining method.
Specifically, above-mentioned memory 1000 and processor 2000 can be general memory and processor, not do here
It is specific to limit, when the computer program of 2000 run memory 1000 of processor storage, it is true to be able to carry out above-mentioned dispensing object
Determine method, for solving the problems, such as that dispensing obtained in the prior art is low to the accuracy of vector, dispensing pair provided by the present application
As determining method, after obtaining for each dispensing total resources value for launching channel, based on launching, the corresponding prediction of total resources value is total
Flow, and the corresponding dispensing ratio of each dispensing channel, determine each predicted flow rate for launching channel, further, are based on each dispensing
The predicted flow rate of channel, and each transformation ratio for launching channel determine each dispensing for launching channel to vector.In this way, passing through
Accuracy of the dispensing that prediction total flow can be improved to vector, meanwhile, it is accurate to also improve the application launched to vector
Degree.
Method is determined corresponding to the dispensing object in Fig. 1, and the embodiment of the present application also provides a kind of computer-readable storages
Medium is stored with computer program on the computer readable storage medium, executes when which is run by processor
It states and launches the step of object determines method.
Specifically, which can be general storage medium, such as mobile disk, hard disk, on the storage medium
Computer program when being run, be able to carry out above-mentioned dispensing object and determine method, for solving throwing obtained in the prior art
The low problem of accuracy to vector is put, dispensing object provided by the present application determines method, is obtaining for each channel of launching
After launching total resources value, based on the corresponding prediction total flow of dispensing total resources value, and the corresponding dispensing ratio of channel is respectively launched,
Each predicted flow rate for launching channel is determined, further, based on each predicted flow rate for launching channel, and each conversion for launching channel
Coefficient determines each dispensing for launching channel to vector.In this way, the dispensing that can be improved by prediction total flow is to vector
Accuracy, meanwhile, it also improves to launch and accuracy is applied to vector.
In embodiment provided by the present invention, it should be understood that disclosed device and method, it can be by others side
Formula is realized.The apparatus embodiments described above are merely exemplary, for example, the division of the unit, only one kind are patrolled
Function division is collected, there may be another division manner in actual implementation, in another example, multiple units or components can combine or can
To be integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Coupling, direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some communication interfaces, device or unit
It connects, can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in embodiment provided by the invention can integrate in one processing unit, it can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing, in addition, term " the
One ", " second ", " third " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.
Finally, it should be noted that embodiment described above, only a specific embodiment of the invention, to illustrate the present invention
Technical solution, rather than its limitations, scope of protection of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, those skilled in the art should understand that: anyone skilled in the art
In the technical scope disclosed by the present invention, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features；And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of technical solution of the embodiment of the present invention.Should all it cover in protection of the invention
Within the scope of.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. a kind of dispensing object determines method, which is characterized in that this method comprises:
It obtains for each dispensing total resources value for launching channel；
Based on the corresponding prediction total flow of the dispensing total resources value and the corresponding dispensing ratio of each dispensing channel, really
Fixed each predicted flow rate for launching channel；
Based on each predicted flow rate for launching channel and each transformation ratio for launching channel, each dispensing is determined
The dispensing of channel is to vector.
2. the method as described in claim 1, which is characterized in that determined according to following manner and launch the corresponding prediction of total resources value
Total flow:
The dispensing total resources value is input to flux prediction model, obtains the total stream of the corresponding prediction of the dispensing total resources value
Amount.
3. method according to claim 2, which is characterized in that determine the flux prediction model according to following manner:
It obtains history and launches total resources value and corresponding history total flow；
Total resources value is launched to the history using regression algorithm and corresponding history total flow does recurrence processing, obtains the stream
Measure prediction model.
4. the method as described in claim 1, which is characterized in that described based on the total stream of the corresponding prediction of the dispensing total resources value
Amount and the corresponding dispensing ratio of each dispensing channel determine each predicted flow rate for launching channel, comprising:
The product of the prediction total flow and the corresponding dispensing ratio of the dispensing channel is made for each dispensing channel
For the predicted flow rate of the dispensing channel.
5. the method as described in claim 1, which is characterized in that it is described based on each predicted flow rate for launching channel, and
Each transformation ratio for launching channel determines each dispensing for launching channel to vector, comprising:
For each dispensing channel, by the product of the predicted flow rate of the dispensing channel and corresponding transformation ratio, as this
The dispensing of channel is launched to vector.
6. the method as described in claim 1, which is characterized in that the determination it is each it is described launch channel dispensing to vector it
Afterwards, further includes:
If each dispensing for launching channel launches launching less than setting to vector with value to the value of vector with default to vector
Threshold value adjusts each dispensing for launching channel to vector then based on the priority for launching channel.
7. a kind of dispensing object determining device, which is characterized in that the device includes:
Module is obtained, is directed to each dispensing total resources value for launching channel for obtaining；
First determining module, for being based on the corresponding prediction total flow of the dispensing total resources value and each dispensing channel
Corresponding dispensing ratio determines each predicted flow rate for launching channel；
Second determining module, for based on each predicted flow rate for launching channel and each transformation system for launching channel
Number determines each dispensing for launching channel to vector.
8. device as claimed in claim 7, which is characterized in that first determining module is also used to be determined according to following manner
Launch the corresponding prediction total flow of total resources value:
The dispensing total resources value is input to flux prediction model, obtains the total stream of the corresponding prediction of the dispensing total resources value
Amount.
9. a kind of computer equipment, including memory, processor and it is stored on the memory and can be on the processor
The computer program of operation, which is characterized in that the processor realized when executing the computer program the claims 1 to
The step of 6 described in any item methods.
10. a kind of computer readable storage medium, computer program, feature are stored on the computer readable storage medium
The step of being, the described in any item methods of the claims 1 to 6 executed when the computer program is run by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910286206.8A CN110020895A (en) | 2019-04-10 | 2019-04-10 | A kind of dispensing object determines method, apparatus, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910286206.8A CN110020895A (en) | 2019-04-10 | 2019-04-10 | A kind of dispensing object determines method, apparatus, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110020895A true CN110020895A (en) | 2019-07-16 |
Family
ID=67190988
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910286206.8A Pending CN110020895A (en) | 2019-04-10 | 2019-04-10 | A kind of dispensing object determines method, apparatus, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110020895A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110659943A (en) * | 2019-09-27 | 2020-01-07 | 上海淇玥信息技术有限公司 | Method and device for adjusting delivery channel based on user structure characteristics and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101365153A (en) * | 2007-08-08 | 2009-02-11 | 上海亿动信息技术有限公司 | Method and system distributing mobile phone advertisement publishing information according to time period |
| CN106504012A (en) * | 2016-09-18 | 2017-03-15 | 北京三快在线科技有限公司 | A kind of method of adjustment of characteristic parameter, device and electronic equipment |
| CN108537605A (en) * | 2018-04-19 | 2018-09-14 | 北京奇艺世纪科技有限公司 | A kind of advertisement placement method and device based on budget |
| CN108805623A (en) * | 2018-06-11 | 2018-11-13 | 浙江工业大学 | Supply prediction method for fast-selling products |
| CN109360012A (en) * | 2018-08-22 | 2019-02-19 | 中国平安人寿保险股份有限公司 | The selection method and device, storage medium, electronic equipment of advertisement dispensing channel |
-
2019
- 2019-04-10 CN CN201910286206.8A patent/CN110020895A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101365153A (en) * | 2007-08-08 | 2009-02-11 | 上海亿动信息技术有限公司 | Method and system distributing mobile phone advertisement publishing information according to time period |
| CN106504012A (en) * | 2016-09-18 | 2017-03-15 | 北京三快在线科技有限公司 | A kind of method of adjustment of characteristic parameter, device and electronic equipment |
| CN108537605A (en) * | 2018-04-19 | 2018-09-14 | 北京奇艺世纪科技有限公司 | A kind of advertisement placement method and device based on budget |
| CN108805623A (en) * | 2018-06-11 | 2018-11-13 | 浙江工业大学 | Supply prediction method for fast-selling products |
| CN109360012A (en) * | 2018-08-22 | 2019-02-19 | 中国平安人寿保险股份有限公司 | The selection method and device, storage medium, electronic equipment of advertisement dispensing channel |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110659943A (en) * | 2019-09-27 | 2020-01-07 | 上海淇玥信息技术有限公司 | Method and device for adjusting delivery channel based on user structure characteristics and electronic equipment |
| CN110659943B (en) * | 2019-09-27 | 2023-03-31 | 上海淇玥信息技术有限公司 | Method and device for adjusting delivery channel based on user structure characteristics and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102880688B (en) | A kind of method for webpage is estimated, device and equipment | |
| CN108665064B (en) | Neural network model training and object recommending method and device | |
| CN104123284B (en) | The method and server of a kind of recommendation | |
| CN104317806B (en) | Financial data inquiry method and financial data system | |
| CN106156878A (en) | Ad click rate antidote and device | |
| CN110110201A (en) | A kind of content recommendation method and system | |
| CN102811371A (en) | Method, system and device for recommending intelligent television application program | |
| CN103246985A (en) | Advertisement click rate predicting method and device | |
| CN112819210B (en) | Online single-point task allocation method capable of being rejected by workers in space crowdsourcing | |
| CN106651213A (en) | Processing method and device for service orders | |
| CN109614347A (en) | Processing method, device, storage medium and the server of multi-level buffer data | |
| CN109697636A (en) | Merchant recommendation method, merchant recommendation device, electronic equipment and medium | |
| CN108933743A (en) | A kind of method for allocating network flow and device based on DSP | |
| CN106595692A (en) | Method and device for providing weather information | |
| CN106455056A (en) | Positioning method and device | |
| CN102945273B (en) | A kind of for providing the method and apparatus of Search Results | |
| CN111369137A (en) | Distribution method, distribution device, server and storage medium of distribution tasks | |
| CN109711875A (en) | Content recommendation method and device | |
| CN110766513A (en) | Information sorting method and device, electronic equipment and readable storage medium | |
| CN112129315B (en) | Method and device for recommending parking lot, electronic equipment and storage medium | |
| CN109711610A (en) | A kind of order allocation method of 3D printing platform | |
| CN110020895A (en) | A kind of dispensing object determines method, apparatus, equipment and medium | |
| CN110454910A (en) | Method and equipment for defrosting of air conditioner | |
| CN111460301A (en) | Object pushing method and device, electronic equipment and storage medium | |
| CN105681089B (en) | Networks congestion control clustering method, device and terminal |
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: 20190716 |
|
| RJ01 | Rejection of invention patent application after publication |