CN108764332A - A kind of Channel Quality analysis method, computing device and storage medium - Google Patents
A kind of Channel Quality analysis method, computing device and storage medium Download PDFInfo
- Publication number
- CN108764332A CN108764332A CN201810516872.1A CN201810516872A CN108764332A CN 108764332 A CN108764332 A CN 108764332A CN 201810516872 A CN201810516872 A CN 201810516872A CN 108764332 A CN108764332 A CN 108764332A
- Authority
- CN
- China
- Prior art keywords
- user
- channel
- attribute
- investment
- value
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Probability & Statistics with Applications (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of Channel Quality analysis method, computing device and storage medium, methods to include：Overall score based on user and investment type attribute ratings, cluster the user of single channel, obtain first predetermined number user's value category of the channel；The ratio of the channel total number of users is accounted for based on the user under predesignated subscriber's value category in single channel, calculates ineffective investment accounting；Input cost based on single channel and number of users calculate the single user cost of single channel；And the single user cost based on channel and ineffective investment accounting, all channels are clustered, the classification of the second predetermined number Channel Quality is obtained.Channel Quality can be analyzed from multiple dimensions through the above scheme, can quickly filter out second-rate channel, guide channel operation to carry out business reorganization in time.
Description
Technical field
The present invention relates to big data analysis technical field more particularly to a kind of Channel Quality analysis method, computing device and
Storage medium.
Background technology
With the continuous development of internet and big data, more and more Internet companies be proposed it is various for users to use
Application or platform, each user has a corresponding registration channel in registration, and has for the quality evaluation for registering channel
Helping Internet company's selection, preferably the corresponding distributor of registration channel cooperates.
Common practice is simple from several dimensions from single dimension progress quantitative evaluation or channel to Channel Quality
Comprehensive assessment.For example, the data such as registration amount, installation, the amount of logging in, activation amount are based primarily upon for the assessment for registering channel, this
A little data the case where there are brush amounts, real commercial conversion cannot be brought, and these indexs can only illustrate register channel to interconnect
Net company brings how many flow, can not obtain the value of registration channel user.
Therefore, it is necessary to a kind of comprehensively and accurately channel analysis methods, can simultaneously consider from multiple dimensions, to data into
Row analysis.
Invention content
For this purpose, the present invention provides a kind of Channel Quality analysis method, computing device and storage medium, to try hard to solve or
At least alleviate above there are the problem of.
According to an aspect of the present invention, a kind of Channel Quality analysis method is provided, is executed in computing device, calculating is set
The a plurality of user data of intended application is stored in standby, every user data includes user identifier, the registration channel of user, user
Investment type attribute ratings and user the corresponding overall score of whole attributes, method includes：Overall score based on user and investment
Generic attribute scores, and is clustered to the user of single channel, obtains first predetermined number user's value category of the channel；Base
User in single channel under predesignated subscriber's value category accounts for the ratio of the channel total number of users, calculates the invalid throwing of the channel
Enter accounting；Input cost based on single channel and number of users calculate the single user cost of single channel；And it is based on channel
Single user cost and ineffective investment accounting, all channels are clustered, obtain the second predetermined number Channel Quality classification.
By obtaining user's value analysis to user clustering from multiple dimensions as a result, based on user's value analysis as a result, again
Channel is clustered from multiple dimensions to obtain Channel Quality analysis result.It can more objectively reflect the fact in this way, obtain compared with can
The evaluation criterion leaned on.
Optionally, first predetermined number user's value category includes high-value user, middle value user, low value user
And inactive users.
Optionally, predesignated subscriber's value category includes low value user and inactive users, and the ineffective investment accounting of channel is：
The channel low value user and inactive users account for the ratio of the channel total number of users.
Optionally, the second predetermined number Channel Quality classification includes high quality channel, middle quality channel and low quality canal
Road.
Optionally, the attribute of user includes essential attribute, invests generic attribute, behavior property, fund attribute, terminal attribute,
Wherein, essential attribute includes at least one in gender, age, area, and investment generic attribute includes investment number, investment amount, throwing
At least one in money interval time, behavior property is at least one in number of days, login frequency including continuously logging in, and fund attribute includes
At least one in income, work, terminal attribute includes at least one in device type, model, network, operator, Regional Distribution.
Optionally, user and/or channel are clustered using K-means clustering algorithms.
Optionally, the boundary obtained based on cluster obtains user's value category and/or Channel Quality classification.
Optionally, it often increases a channel newly, calculates the single user cost and ineffective investment accounting of the channel；By newly-increased channel
Single user input cost and the boundary that clusters of ineffective investment accounting and channel compare, determine the quality classification of the channel.
Optionally, user randomly selects in channel registers user, and user includes multiple user properties, and user property includes
Multiple attribute values, each attribute value correspond to one and score, and the investment type attribute ratings of user's overall score and user pass through with lower section
Formula obtains：It is at predetermined time intervals that the corresponding scoring of whole attribute values of user is cumulative, the overall score of user is obtained, by user's
The corresponding scoring of investment type attribute value is cumulative, obtains the investment type attribute ratings of user.
According to an aspect of the present invention, a kind of computing device is provided, including：One or more processors；And memory；
One or more programs, wherein one or more programs store in memory and are configured as being held by one or more processors
Row, one or more programs include the instruction for executing Channel Quality analysis method.
According to an aspect of the present invention, a kind of computer-readable storage medium of the one or more programs of storage is also provided
Matter, one or more programs include instruction, when computing device executes instruction so that computing device executes Channel Quality analysis side
Method.
Multiple attributes of user are quantified, can be embodied by obtaining user data according to technical solution of the present invention
The value of user, and user is divided into the different customers for being worth classifications by the clustering that multiple dimensions are carried out to user, then
Clustering is carried out from multiple dimensions to channel based on user's value, channel is divided into different quality classification.This method can
Channel Quality analysis result quickly is obtained, to guide channel operation to carry out business reorganization, improves the effect of Channel Quality assessment
Rate and accuracy.
Description of the drawings
To the accomplishment of the foregoing and related purposes, certain illustrative sides are described herein in conjunction with following description and drawings
Face, these aspects indicate the various modes that can put into practice principles disclosed herein, and all aspects and its equivalent aspect
It is intended to fall in the range of theme claimed.Read following detailed description in conjunction with the accompanying drawings, the disclosure it is above-mentioned
And other purposes, feature and advantage will be apparent.Throughout the disclosure, identical reference numeral generally refers to identical
Component or element.
Fig. 1 shows the structure chart of computing device 100 according to an embodiment of the invention；
Fig. 2 shows the flow charts of channel analysis method 200 according to an embodiment of the invention.
Specific implementation mode
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Completely it is communicated to those skilled in the art.
Internet channels quantity is excessive at present, and the good and bad jumbled together, it is desirable to pick out high-quality channel and be not easy actually, one outstanding
Channels not only to have it is stable Add User and any active ues, should also in the true behavioral data in the current family in data upper body,
So that operator continues to optimize product.User's download or registration amount, user's registration cannot be concerned only with when evaluating Channel Quality
And it activates using just meaningful.Therefore multiple indexs can be added when analyzing Channel Quality, such as activation user volume, actively
User volume, user's retention ratio, terminal attribute etc., these indexs can be obtained from user journal data.To channel and user into
Row comprehensive assessment, it can be found that there are the problem of and take Optimized Measures.
Fig. 1 shows the structure diagram of computing device 100 according to an embodiment of the invention.In basic configuration 102
In, computing device 100 typically comprises system storage 106 and one or more processor 104.Memory bus 108 can
For the communication between processor 104 and system storage 106.
Depending on desired configuration, processor 104 can be any kind of processing, including but not limited to：Microprocessor
(μ P), microcontroller (μ C), digital information processor (DSP) or any combination of them.Processor 104 may include such as
The cache of one or more rank of on-chip cache 110 and second level cache 112 etc, processor core
114 and register 116.Exemplary processor core 114 may include arithmetic and logical unit (ALU), floating-point unit (FPU),
Digital signal processing core (DSP core) or any combination of them.Exemplary Memory Controller 118 can be with processor
104 are used together, or in some implementations, and Memory Controller 118 can be an interior section of processor 104.
Depending on desired configuration, system storage 106 can be any type of memory, including but not limited to：Easily
The property lost memory (RAM), nonvolatile memory (ROM, flash memory etc.) or any combination of them.System stores
Device 106 may include operating system 120, one or more program 122 and program data 124.In some embodiments,
Program 122 may be arranged to be operated using program data 124 on an operating system.
Computing device 100 can also include contributing to from various interface equipments (for example, output equipment 142, Peripheral Interface
144 and communication equipment 146) to basic configuration 102 via the communication of bus/interface controller 130 interface bus 140.Example
Output equipment 142 include graphics processing unit 148 and audio treatment unit 150.They can be configured as contribute to via
One or more port A/V 152 is communicated with the various external equipments of such as display or loud speaker etc.Outside example
If interface 144 may include serial interface controller 154 and parallel interface controller 156, they, which can be configured as, contributes to
Via one or more port I/O 158 and such as input equipment (for example, keyboard, mouse, pen, voice-input device, touch
Input equipment) or the external equipment of other peripheral hardwares (such as printer, scanner etc.) etc communicated.Exemplary communication is set
Standby 146 may include network controller 160, can be arranged to convenient for via one or more communication port 164 and one
The communication that other a or multiple computing devices 162 pass through network communication link.
Network communication link can be an example of communication media.Communication media can be usually presented as in such as carrier wave
Or the computer-readable instruction in the modulated data signal of other transmission mechanisms etc, data structure, program module, and can
To include any information delivery media." modulated data signal " can such signal, one in its data set or more
It is a or it change can the mode of coding information in the signal carry out.As unrestricted example, communication media can be with
Include the wire medium of such as cable network or private line network etc, and such as sound, radio frequency (RF), microwave, infrared
(IR) the various wireless mediums or including other wireless mediums.Term computer-readable medium used herein may include depositing
Both storage media and communication media.
Computing device 100 can be implemented as server, such as file server, database server, application program service
Device and WEB server etc., can also be a part for portable (or mobile) electronic equipment of small size, these electronic equipments can be with
It is that such as cellular phone, personal digital assistant (PDA), personal media player device, wireless network browsing apparatus, individual wear
Equipment, application specific equipment or may include any of the above function mixing apparatus.Computing device 100 is also implemented as
Personal computer including desktop computer and notebook computer configuration.In some embodiments, computing device 100 can by with
It is set to and executes Channel Quality analysis method according to the present invention.Wherein, one or more programs 122 of computing device 100 include
Instruction for executing Channel Quality analysis method according to the present invention.
The a plurality of user data of intended application can be prestored in computing device 100.Wherein intended application is, for example,
The application of financial service is provided.In order to promote and apply, operator generally provides a variety of registration channels to the user, such as downloads APP
It registers, scans the two-dimensional code concern wechat public platform, obtains using account online application registration etc..In order to obtain the more of intended application
User data can be based on business objective and collect user data, for example, pass through flume (result collection system) collect it is local
Journal file, and daily record is dumped in HDFS, Kafka distributed data platform, the reality of data collection can be improved in this way
The disk of Shi Xing, flume real time monitoring write-in daily record will pass daily record in form of a message as long as there is new daily record write-in
Pass Kafka distributed file system.The above big data processing scheme is schematical, and the data of other modes may be used
Collection scheme does not limit herein.
A certain number of users are randomly selected in the user that there can be the behavior of logging in 1 year to analyze as Channel Quality
Sample client.It uses any one data collection plan to collect the information of sample client again, obtains a plurality of user data.Every
User data may include user identifier, user registration channel, the investment type attribute ratings of user and whole attributes of user
Corresponding overall score etc..
User identifier can avoid data overlap with the identity of the unique mark user, can be each according to business demand
User sets multiple attributes, such as in financial services industry, can set the essential attribute of user, invest generic attribute, behavior category
Property, fund attribute, terminal attribute etc., can generally excavate 200 user properties.Wherein, essential attribute may include gender, year
Age, area etc., terminal attribute may include device type and model, network and operator, Regional Distribution etc., and investment generic attribute can
To include investment number, investment amount, investment interval time, behavior property may include continuously logging in number of days, login frequency, money
Metallicity may include income, work etc..
Each attribute includes multiple attribute values, such as the attribute value in area may include Beijing, Shanghai, Guangzhou etc., equipment
The attribute value of type can be apple, Android, other, the attribute value of equipment type includes Samsung, millet, Huawei etc., in order into
One step number can be that each attribute value sets a score value, the scoring of attribute value can manually be set by experience according to statistics
It is fixed.General setting attribute value scoring in the section [0-100], such as apple attribute value scoring be 90, Android attribute value scoring
It is 80, other attribute value scorings are 70；The attribute value scoring at age 1-18 Sui is 50, the attribute value at age 19-25 Sui scores
It is 90 for the scoring of 26-40 Sui attribute value of 70, age, such, score value is higher, and customer value is higher.
Can be cumulative by the corresponding scoring of whole attribute values of user at predetermined time intervals, the overall score of user is obtained, also
Can be cumulative by the corresponding scoring of the investment type attribute value of user at predetermined time intervals according to business demand, obtain the throwing of user
Provide generic attribute scoring.
It is generally the period with one week or one month, the scoring of user's whole attribute adds up at some time point daily
Obtain user's overall score and the corresponding cumulative score of a certain attribute.It is generally acknowledged that the customer flow of weekend video class website compares work
The customer flow for making day is big.Therefore a Channel Quality analysis can be carried out for time span with one week, reduces different channels and uses
The influence that family flow different band is come.
There are enough, reliable data, also to have the model of science, could more effectively support analysis result.Fig. 2 shows
The flow chart of Channel Quality analysis method 200 according to an embodiment of the invention is gone out.As shown in Fig. 2, in step S210,
Overall score and investment type attribute ratings that can be based on user, cluster the user of single channel, obtain the of the channel
One predetermined number user's value category.
According to one embodiment of present invention, user can be clustered using K-means Dynamic Clustering Algorithms.Dynamically
Clustering procedure is first to presort, and is then gradually adjusted again, until class get comparison it is reasonable until, mainly for large sample number
According to classification, wherein K-means algorithms are the clustering algorithms based on distance, using evaluation index of the distance as similitude, are had
Body process can be as follows：
Arbitrarily select k object as initial cluster center from n data object first；And for remaining other right
As then according to the similarity (distance) of they and these cluster centres, assigning these to respectively most like with it (in cluster
Representated by the heart) cluster；Then each cluster centre (mean values of all objects in the cluster) newly clustered is calculated again；Constantly weight
This multiple process is until canonical measure function starts convergence.The result of k cluster has the characteristics that：Each cluster itself is to the greatest extent
It is possible compact, and it is separated as far as possible between respectively clustering.
Using two dimensional pointer (user's overall score and investment type attribute ratings) as sample in the embodiment of the present invention, using K-
First predetermined number is set as 4 by means algorithms, i.e. K=4 (needs the cluster number divided), is configured by empirical value initial
Barycenter [15000,5000], [10000,3500], [6000,2000], [2000,600] can be gathered after successive ignition
The boundary of class, such as when inconsistent coefficient of some cluster is more than a certain threshold value, is then considered as cluster boundary, disconnects from here poly-
Class is calculated as one kind.In this way, just having obtained the first predetermined number (being 4 in this example) user's value category, each user's value point
Class corresponds to a cluster boundary.
It is then possible to determine that the corresponding user of each classification is worth according to artificial mark, it is as a result as follows：
As shown in the above data, first predetermined number user's value category may include high-value user, middle value use
Family, low value user and inactive users.Wherein inactive users may be considered wool party, that is, refers to and be specifically chosen each internet channels
Preferential advertising campaign, with relatively low cost even zero cost exchange crowd economical on substance for.
In step S220, it is total that channel user can be accounted for based on the user under predesignated subscriber's value category in single channel
Several ratios calculates the ineffective investment accounting of the channel.
For example, predesignated subscriber's value category may include low value user and inactive users, low value user, invalid is taken out
Two class user of user accounts for the ratio R of whole cluster user data counts.Such as the accounting per class is as follows：High value A=
0.11256, middle value B=0.22454, low value C=0.57867, invalid D=0.08423.Then ineffective investment accounting R=(C+
D)。
In step S230, input cost and number of users that can be based on single channel calculate being applied alone for single channel
Family cost.
For example, the continuous one week input cost of some channel is x1...x7, continuous one week registration number of users is
y1...y7.Calculating single user cost in this channel one week is：(y1+y2+y3...+y7)/(x1+x2+x3...+x7).
It is also based on ineffective investment accounting and single user cost calculation ineffective investment cost, for example, cost input 100,000,
Ineffective investment cost=R* single users cost=(0.57867+0.08423) * 100000=66290 members.
In step S240, single user cost and ineffective investment accounting that can be based on channel gather all channels
Class obtains the classification of the second predetermined number Channel Quality, each corresponding cluster boundary of Channel Quality classification.Wherein, second
Predetermined number could be provided as 3, and correspondingly, 3 Channel Quality classification may include high quality channel, middle quality channel and low-quality
Measure channel.
Likewise it is possible to be clustered to channel using K-means clustering algorithms.K=3 can be set, with two dimensional pointer
(single user cost and ineffective investment accounting) is used as sample, carries out three boundaries that successive ignition is clustered, classification results are such as
Under：
According to data above as can be seen that having 3 groupings after the completion of cluster result：(DF), (BGAC), (E).Then, root
The Channel Quality of each classification is determined according to artificial annotation results, for example, DF groups are low quality channels, E groups are high quality channels,
BGAC groups are middle quality channels.
Lasting tracking can be carried out to registration channel can calculate this in the same way for each newly-increased channel
The single user cost and ineffective investment accounting of channel, analyze the single user input cost for increasing channel newly and ineffective investment accounting is fallen
The cluster boundary of the Channel Quality entered determines the quality classification of the channel.In this way, the channel being newly added can quickly obtain matter
Analysis result is measured, the market operation is swift in response.
It is also based on the total input cost and number of users of whole channels, calculates total single user cost；Based on user
Scoring and investment type attribute ratings, cluster the user of whole channels, calculate total ineffective investment accounting；It can will be single
The single user cost of channel, ineffective investment accounting and total single user cost, ineffective investment accounting are compared, and canal is tentatively obtained
Road quality analysis results.For example, by the single user cost of single channel be less than total single user cost channel be determined as it is high-quality
Measure channel, or by the ineffective investment accounting of single channel be less than total ineffective investment accounting channel be determined as high quality canal
Road.
Further, it is also possible to carry out channel user quality analysis from other multiple dimensions, conversion ratio is such as registered, user's revenue and expenditure is closed
On the one hand system, subscriber lifecycle etc. can evaluate Channel Quality, on the one hand can mark off user's valence of different channels
Value.Different dispensing strategies can be carried out according to user's feature of different channels.
Through the above technical solutions, by obtaining user data, multiple attributes of user are quantified, use can be embodied
The value at family, and clustering is carried out to user, user is divided into the different customers for being worth classifications, then be worth based on user
Clustering is carried out to channel, channel is divided into different quality classification.It in this way can be according to the practical business valence brought of user
The effect of value assessment marketing.This method can quickly obtain Channel Quality analysis result, to guide channel operation to carry out
Business reorganization improves the efficiency and accuracy of Channel Quality assessment.
A8, the method as described in A7, wherein further include：Often increase newly a channel, calculate the channel single user cost and
Ineffective investment accounting；The boundary pair that the single user input cost of newly-increased channel and ineffective investment accounting are clustered with channel
Than determining the quality classification of the channel.In the instructions provided here, numerous specific details are set forth.However, can manage
Solution, the embodiment of the present invention can be put into practice without these specific details.In some instances, do not show in detail
Go out well known method, structure and technology, so as not to obscure the understanding of this description.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of each inventive aspect,
Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the method for the disclosure should be construed to reflect following intention：It is i.e. required to protect
Shield the present invention claims the feature more features than being expressly recited in each claim.More precisely, as following
As claims reflect, inventive aspect is all features less than single embodiment disclosed above.Therefore, it abides by
Thus the claims for following specific implementation mode are expressly incorporated in the specific implementation mode, wherein each claim itself
As a separate embodiment of the present invention.
Those skilled in the art should understand that the module of the equipment in example disclosed herein or unit or groups
Part can be arranged in equipment as depicted in this embodiment, or alternatively can be positioned at and the equipment in the example
In different one or more equipment.Module in aforementioned exemplary can be combined into a module or be segmented into addition multiple
Submodule.
Those skilled in the art, which are appreciated that, to carry out adaptively the module in the equipment in embodiment
Change and they are arranged in the one or more equipment different from the embodiment.It can be the module or list in embodiment
Member or component be combined into a module or unit or component, and can be divided into addition multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it may be used any
Combination is disclosed to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so to appoint
Where all processes or unit of method or equipment are combined.Unless expressly stated otherwise, this specification (including adjoint power
Profit requires, abstract and attached drawing) disclosed in each feature can be by providing the alternative features of identical, equivalent or similar purpose come generation
It replaces.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other feature, but the combination of the feature of different embodiments means in of the invention
Within the scope of and form different embodiments.For example, in the following claims, embodiment claimed is appointed
One of meaning mode can use in any combination.
In addition, be described as herein can be by the processor of computer system or by executing for some in the embodiment
The combination of method or method element that other devices of the function are implemented.Therefore, have for implementing the method or method
The processor of the necessary instruction of element forms the device for implementing this method or method element.In addition, device embodiment
Element described in this is the example of following device：The device is used to implement performed by the element by the purpose in order to implement the invention
Function.
As used in this, unless specifically stated, come using ordinal number " first ", " second ", " third " etc.
Description plain objects are merely representative of the different instances for being related to similar object, and are not intended to imply that the object being described in this way must
Must have the time it is upper, spatially, in terms of sequence or given sequence in any other manner.
Although the embodiment according to limited quantity describes the present invention, above description, the art are benefited from
It is interior it is clear for the skilled person that in the scope of the present invention thus described, it can be envisaged that other embodiments.It should be noted that this theory
The language that is used in bright book primarily to readable and introduction purpose and select, rather than in order to explain or limit this
The theme of invention and select.Therefore, without departing from the scope and spirit of the appended claims, for this technology
Many modifications and changes will be apparent from for the those of ordinary skill in field.For the scope of the present invention, to the present invention
The disclosure done is illustrative and not restrictive, and it is intended that the scope of the present invention be defined by the claims appended hereto.
Claims (10)
1. a kind of Channel Quality analysis method, executes in computing device, the more of intended application are stored in the computing device
User data, every user data include user identifier, the registration channel of user, the investment type attribute ratings of user and user
The corresponding overall score of whole attributes, the method includes：
Overall score based on user and investment type attribute ratings, cluster the user of single channel, obtain the of the channel
One predetermined number user's value category；
The ratio that the channel total number of users is accounted for based on the user under predesignated subscriber's value category in single channel, calculates the channel
Ineffective investment accounting；
Input cost based on single channel and number of users calculate the single user cost of single channel；And
Single user cost based on channel and ineffective investment accounting, cluster all channels, obtain the second predetermined number
Channel Quality is classified.
2. the method for claim 1, wherein
First predetermined number user's value category includes high-value user, middle value user, low value user and invalid
User.
3. method as claimed in claim 2, wherein
Predesignated subscriber's value category includes low value user and inactive users, and the ineffective investment accounting of channel is：The channel
Low value user and inactive users account for the ratio of the channel total number of users.
4. the method for claim 1, wherein
The second predetermined number Channel Quality classification includes high quality channel, middle quality channel and low quality channel.
5. the method for claim 1, wherein
The attribute of user includes essential attribute, investment generic attribute, behavior property, fund attribute, terminal attribute, the essential attribute
Including at least one in gender, age, area, the investment generic attribute includes investment number, investment amount, investment interval time
In it is at least one, the behavior property include it is continuous log at least one in number of days, login frequency, the fund attribute includes receiving
Enter, work in it is at least one, the terminal attribute includes at least one in device type, model, network, operator, Regional Distribution
It is a.
6. the method for claim 1, wherein
User and/or channel are clustered using K-means clustering algorithms.
7. method as claimed in claim 6, wherein further include：
Based on the boundary that cluster obtains, user's value category and/or Channel Quality classification are obtained.
8. the method for claim 1, wherein
The user randomly selects in channel registers user, and user includes multiple user properties, and user property includes multiple categories
Property value, each attribute value corresponds to a scoring, and the investment type attribute ratings of user's overall score and user are in the following manner
It obtains：
It is at predetermined time intervals that the corresponding scoring of whole attribute values of user is cumulative, the overall score of user is obtained, by the throwing of user
It is cumulative to provide the corresponding scoring of generic attribute value, obtains the investment type attribute ratings of user.
9. a kind of computing device, including：
One or more processors；With
Memory；
One or more programs, wherein one or more of programs are stored in the memory and are configured as by described one
A or multiple processors execute, and one or more of programs include for executing according in claim 1-8 the methods
The instruction of either method.
10. a kind of computer readable storage medium of the one or more programs of storage, one or more of programs include instruction,
Described instruction is when mobile terminal execution so that the computing device executes appointing in the method according to claim 1-8
One method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810516872.1A CN108764332A (en) | 2018-05-25 | 2018-05-25 | A kind of Channel Quality analysis method, computing device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810516872.1A CN108764332A (en) | 2018-05-25 | 2018-05-25 | A kind of Channel Quality analysis method, computing device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108764332A true CN108764332A (en) | 2018-11-06 |
Family
ID=64006339
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810516872.1A Withdrawn CN108764332A (en) | 2018-05-25 | 2018-05-25 | A kind of Channel Quality analysis method, computing device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108764332A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110460876A (en) * | 2019-08-15 | 2019-11-15 | 网易（杭州）网络有限公司 | Processing method, device and the electronic equipment of log is broadcast live |
| CN110648180A (en) * | 2019-09-27 | 2020-01-03 | 上海淇玥信息技术有限公司 | Method and device for adjusting delivery channel and electronic equipment |
| CN110659931A (en) * | 2019-08-29 | 2020-01-07 | 中至数据集团股份有限公司 | Channel quality evaluation method, system, readable storage medium and computer equipment |
| 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 |
| CN111506615A (en) * | 2020-04-22 | 2020-08-07 | 深圳前海微众银行股份有限公司 | Method and device for determining occupation degree of invalid user |
| CN111738608A (en) * | 2020-06-28 | 2020-10-02 | 中国联合网络通信集团有限公司 | Channel scoring method and system |
| CN113065899A (en) * | 2021-04-12 | 2021-07-02 | 上海明略人工智能(集团)有限公司 | User life cycle value calculation method, system, device and storage medium |
| CN117541293A (en) * | 2023-11-23 | 2024-02-09 | 广州优加市场调研有限公司 | Market research data analysis method and system based on big data |
| CN117541293B (en) * | 2023-11-23 | 2024-06-07 | 广州优加市场调研有限公司 | Market research data analysis method and system based on big data |
-
2018
- 2018-05-25 CN CN201810516872.1A patent/CN108764332A/en not_active Withdrawn
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110460876A (en) * | 2019-08-15 | 2019-11-15 | 网易（杭州）网络有限公司 | Processing method, device and the electronic equipment of log is broadcast live |
| CN110659931A (en) * | 2019-08-29 | 2020-01-07 | 中至数据集团股份有限公司 | Channel quality evaluation method, system, readable storage medium and computer equipment |
| CN110648180A (en) * | 2019-09-27 | 2020-01-03 | 上海淇玥信息技术有限公司 | Method and device for adjusting delivery channel and electronic equipment |
| 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 |
| CN110648180B (en) * | 2019-09-27 | 2023-05-12 | 上海淇玥信息技术有限公司 | Method and device for adjusting delivery channel and electronic equipment |
| CN111506615A (en) * | 2020-04-22 | 2020-08-07 | 深圳前海微众银行股份有限公司 | Method and device for determining occupation degree of invalid user |
| CN111738608A (en) * | 2020-06-28 | 2020-10-02 | 中国联合网络通信集团有限公司 | Channel scoring method and system |
| CN113065899A (en) * | 2021-04-12 | 2021-07-02 | 上海明略人工智能(集团)有限公司 | User life cycle value calculation method, system, device and storage medium |
| CN117541293A (en) * | 2023-11-23 | 2024-02-09 | 广州优加市场调研有限公司 | Market research data analysis method and system based on big data |
| CN117541293B (en) * | 2023-11-23 | 2024-06-07 | 广州优加市场调研有限公司 | Market research data analysis method and system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108764332A (en) | A kind of Channel Quality analysis method, computing device and storage medium | |
| Meade et al. | Forecasting in telecommunications and ICT—A review | |
| US20200252423A1 (en) | Systems and methods for vulnerability assessment and remedy identification | |
| CN109615487A (en) | Products Show method, apparatus, equipment and storage medium based on user behavior | |
| CN109636490A (en) | Real-time predicting method, the advertisement valuation method and system of ad conversion rates | |
| CN103049452A (en) | Method and device for performing application sequencing based on estimated download rate | |
| CN109033408A (en) | Information-pushing method and device, computer readable storage medium, electronic equipment | |
| CN109543940B (en) | Activity evaluation method, activity evaluation device, electronic equipment and storage medium | |
| CN107026750A (en) | A kind of user's online QoE evaluation methods and device | |
| CN112184046A (en) | Advertisement service user value evaluation method, device, equipment and storage medium | |
| CN106991577A (en) | A kind of method and device for determining targeted customer | |
| CN115345530A (en) | Market address recommendation method, device and equipment and computer readable storage medium | |
| Badran | Young people and the digital divide in Egypt: An empirical study | |
| US11704705B2 (en) | Systems and methods for an intelligent sourcing engine for study participants | |
| CN111159541A (en) | Method and device for determining account behavior preference | |
| CN110348717A (en) | Base station value methods of marking and device based on grid granularity | |
| CN109472312A (en) | Application assessment method, apparatus, computer equipment and storage medium | |
| CN116151872B (en) | Product characteristic analysis method and device | |
| CN112449002A (en) | Method, device and equipment for pushing object to be pushed and storage medium | |
| WO2023205713A2 (en) | Systems and methods for improved user experience participant selection | |
| GB2517358A (en) | Recommendation creation system | |
| Azam et al. | MOBILE PHONE USAGE IN BANGLADESH: THE EFFECTS OF ATTITUDE TOWARDS BEHAVIOUR AND SUBJECTIVE NORM. | |
| CN114266625A (en) | Recommendation method, device and equipment based on new user and storage medium | |
| CN113408817A (en) | Traffic distribution method, device, equipment and storage medium | |
| CN109472455B (en) | Activity evaluation method, activity evaluation device, electronic equipment and storage medium |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20181106 |
|
| WW01 | Invention patent application withdrawn after publication |