CN109978304A - The appraisal procedure and device of object-oriented - Google Patents
The appraisal procedure and device of object-oriented Download PDFInfo
- Publication number
- CN109978304A CN109978304A CN201711459997.7A CN201711459997A CN109978304A CN 109978304 A CN109978304 A CN 109978304A CN 201711459997 A CN201711459997 A CN 201711459997A CN 109978304 A CN109978304 A CN 109978304A
- Authority
- CN
- China
- Prior art keywords
- channel
- value
- index
- characteristic index
- value characteristic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Accounting & Taxation (AREA)
- Economics (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of appraisal procedure of object-oriented and devices, are related to field of computer technology.Wherein, this method comprises: choosing Channel Value characteristic index and multiple value influence indexs；By include Channel Value characteristic index statistical data and belong to same preset time period value influence indicator-specific statistics data training sample input regression model, with training obtain corresponding channel assessment models；Channel is assessed based on the channel assessment models.By above step, the accuracy of channel assessment result can be improved, reduce channel and assess difficulty.
Description
Technical field
The present invention relates to field of computer technology more particularly to the appraisal procedures and device of a kind of object-oriented.
Background technique
With the development of internet technology, various APP (application software) are emerged one after another, and operator can pass through multiple channel
Promote APP.Currently, APP channels mainly include several big types such as prepackage, application shop, Wireless Consortion under line.Each popularization
Type may include many payment channels again.How APP channels are assessed, and then selects good channels, it is right
Internet company is most important.
Currently, Internet company is (for example, game company, internet financing corporation, OTA (online tourism society), online shopping
Company) operation personnel when assessing APP channels, needs to see many indexs.Since index is numerous, lead to channel
Evaluation work is tedious, work difficulty is big.In addition, there may be inconsistent feelings for the Channel Value reflected by different indexs
Condition further increases assessment difficulty.By taking the class APP that does shopping as an example, for two channels of A, B, it is understood that there may be: A canal
The returning rate index in road is higher than B channel, however the shopping rate index of A channel is lower than B channel.
Channel is assessed in order to solve the above technical problems, the prior art generallys use following method, comprising: general first
The weight of each index is determined by operation personnel's subjectivity, standardization then is made to each index, finally to multiple after standardization
The score of index is weighted summation, obtains the comprehensive assessment score of channel.
In realizing process of the present invention, at least there are the following problems in the prior art for inventor's discovery:
The first, artificial, subjective to determine each index weights, it is likely that cause channel assessment result inaccurate.For example, certain is referred to
Target weight is set as 0.4 or 0.5, will have a direct impact on the comprehensive assessment score of channel.
Second, over time, Channel Quality may change, and each index can also to the importance of same channel
It can change.For example, installing in one week in APP, first purchase rate (number of users/activation equipment number for carrying out first purchase) is higher,
The index is larger to the importance of channel；It is installed after two months in APP, first purchase rate reduces, which drops the importance of channel
It is low.Therefore, when assessing the same channel in different time sections, the weight to each index is needed to be changed, this into
One step increases assessment difficulty.
Summary of the invention
In view of this, the present invention provides the appraisal procedure and device of a kind of object-oriented, channel assessment result can be improved
Accuracy, reduce channel assess difficulty.
To achieve the above object, according to an aspect of the invention, there is provided a kind of appraisal procedure of object-oriented.
The appraisal procedure of object-oriented of the invention includes: that selection Channel Value characteristic index and multiple value influences refer to
Mark；It will include Channel Value characteristic index statistical data and the value influence index system for belonging to same preset time period
The training sample input regression model counted, obtains corresponding channel assessment models with training；Mould is assessed based on the channel
Type assesses channel.
Optionally, the selection Channel Value characteristic index and the step of multiple value influence indexs, include: and first determine to close
Key operational indicator, then it is based on correlation analysis and/or principal component analysis, Channel Value is filtered out from the key business index
Characteristic index and multiple value influence indexs.
Optionally, the selection Channel Value characteristic index and the step of multiple value influence indexs include: according to APP institute
The type of service of category inquires index list, to obtain Channel Value characteristic index corresponding with the type of service and multiple values
Influence index.
Optionally, the regression model includes: that multiple linear regression model, random forest regression model or decision tree return
Model.
Optionally, described to be based on the step of channel assessment models assess channel to include: including ownership
Corresponding channel assessment models are inputted in the test sample of the value influence indicator-specific statistics data of same preset time period, to obtain
The predicted value of Channel Value characteristic index；And the input and output rate of channel is calculated according to the following formula, and according to the investment
Output capacity assesses different channels；
Wherein, ROI indicates the input and output rate of channel, and V indicates the predicted value of Channel Value characteristic index, and P indicates single
The channel of equipment activates expense.
Optionally, the Channel Value characteristic index includes: the shopping of average each activation equipment in first time period
The amount of money；The value influence index includes: the head of average each activation equipment in second time period and/or in the third period
Purchase number of users, the shopping amount of money of average each activation equipment and visitor's unit price；Wherein, second time period, the third period when
It is long to be respectively less than first time period.
To achieve the above object, according to another aspect of the present invention, a kind of assessment device of object-oriented is provided.
The assessment device of object-oriented of the invention includes: selection module, for choosing Channel Value characteristic index and more
A value influence index；Training module, for that will include Channel Value characteristic index statistical data and belong to same pre-
If the training sample of the value influence indicator-specific statistics data of period inputs regression model, corresponding channel assessment is obtained with training
Model；Evaluation module, for being assessed based on the channel assessment models channel.
Optionally, the selection module chooses Channel Value characteristic index and multiple value influence indexs include: the choosing
Modulus block first determines key business index, then is based on correlation analysis and/or principal component analysis, from the key business index
Filter out Channel Value characteristic index and multiple value influence indexs.
Optionally, the selection module chooses Channel Value characteristic index and multiple value influence indexs include: the choosing
Modulus root tuber inquires index list according to type of service belonging to APP, to obtain Channel Value table corresponding with the type of service
Levy index and multiple value influence indexs.
Optionally, the evaluation module carries out assessment to include: including same based on the channel assessment models to channel
The test sample of the value influence indicator-specific statistics data of one preset time period inputs corresponding channel assessment models, to obtain channel
It is worth the predicted value of characteristic index；And the input and output rate of channel is calculated according to the following formula, and according to the input and output
Rate assesses different channels；
Wherein, ROI indicates the input and output rate of channel, and V indicates the predicted value of Channel Value characteristic index, and P indicates single
The channel of equipment activates expense.
To achieve the above object, according to a further aspect of the invention, a kind of server is provided.
Server of the invention, comprising: one or more processors；And storage device, for storing one or more
Program；When one or more of programs are executed by one or more of processors, so that one or more of processors
Realize the appraisal procedure of object-oriented of the invention.
To achieve the above object, according to a further aspect of the invention, a kind of computer-readable medium is provided.
Computer-readable medium of the invention is stored thereon with computer program, real when described program is executed by processor
The appraisal procedure of existing object-oriented of the invention.
One embodiment in foregoing invention has the following advantages that or the utility model has the advantages that the present invention passes through selection Channel Value table
Sign index and multiple value influence indexs will include Channel Value characteristic index statistical data and belong to same default
The training sample of the value influence indicator-specific statistics data of period inputs regression model, obtains corresponding channel assessment mould with training
Type, and channel is assessed based on the channel assessment models, it can be improved the accuracy of channel assessment result, reduce channel
Assess difficulty.
Further effect possessed by above-mentioned non-usual optional way adds hereinafter in conjunction with specific embodiment
With explanation.
Detailed description of the invention
Attached drawing for a better understanding of the present invention, does not constitute an undue limitation on the present invention.Wherein:
Fig. 1 is the basic step schematic diagram of the appraisal procedure of object-oriented according to an embodiment of the present invention；
Fig. 2 is the idiographic flow schematic diagram of the appraisal procedure of object-oriented according to an embodiment of the present invention；
Fig. 3 is the main modular schematic diagram of the assessment device of object-oriented according to an embodiment of the present invention；
Fig. 4 is that the embodiment of the present invention can be applied to exemplary system architecture figure therein；
Fig. 5 is adapted for the structural schematic diagram for the computer system for realizing the server of the embodiment of the present invention.
Specific embodiment
Below in conjunction with attached drawing, an exemplary embodiment of the present invention will be described, including the various of the embodiment of the present invention
Details should think them only exemplary to help understanding.Therefore, those of ordinary skill in the art should recognize
It arrives, it can be with various changes and modifications are made to the embodiments described herein, without departing from scope and spirit of the present invention.Together
Sample, for clarity and conciseness, descriptions of well-known functions and structures are omitted from the following description.
It should be pointed out that in the absence of conflict, the feature in embodiment and embodiment in the present invention can be with
It is combined with each other.
Fig. 1 is the basic step schematic diagram of the appraisal procedure of object-oriented according to an embodiment of the present invention.As shown in Figure 1,
The appraisal procedure of the object-oriented of the embodiment of the present invention includes:
Step S101, Channel Value characteristic index and multiple value influence indexs are chosen.
Wherein, the channel includes APP channels, the Channel Value characteristic index be embody channel it is long-term (such as
1 year) value index, the value influence index be to Channel Value have an impact it is short-term (such as one week, one month or
Two months) index.
In an optional embodiment, which includes: first to determine key business index based on business demand, then be based on phase
The analysis of closing property and/or principal component analysis, filter out Channel Value characteristic index and multiple valences from the key business index
It is worth influence index.
In the optional embodiment, by carrying out correlation analysis, principal component analysis to data, it can filter out to canal
Road long-term value influences that big and the small several indexs of correlation are used as value influence index each other, and then reduces when modeling
Data processing amount, improve channel assess efficiency.
In another optional embodiment, the step include: the type of service according to belonging to APP (for example, shopping type,
Type of play etc.) inquiry index list, to obtain Channel Value characteristic index corresponding with the type of service and multiple values
Influence index.For example, corresponding Channel Value characteristic index is in 1 year when the type of service belonging to the APP is shopping type
The shopping amount of money of average each activation equipment, corresponding value influence index are as follows: new user's shopping rate, channel in one week in one week
Value and visitor's unit price in one week.
In the optional embodiment, by by Channel Value characteristic index needed for the various APP filtered out in advance and
Multiple value influence indexs are summarised in a list, to can directly inquire the list when carrying out channel assessment every time
Index needed for obtaining improves the efficiency of channel assessment without repeating data analysis, index screening work.
Step S102, it will include Channel Value characteristic index statistical data and belong to same preset time period
The training sample of value influence indicator-specific statistics data inputs regression model, obtains corresponding channel assessment models with training.
Wherein, the Channel Value characteristic index statistical data, i.e., the value of the described Channel Value characteristic index；The value
Influence index statistical data, i.e. value influence refer to target value.The regression model can include: multiple linear regression model, random
Forest regression model, decision tree regression model or Boosting regression model.
Illustratively, when the Channel Value characteristic index is to embody the index being worth in channel 1 year, the value shadow
It, then can be based on the historical data of last year each channel when snap mark includes: one week, one month or bimestrial value influence index
Building training sample is specifically included with being trained to regression model: based on including the Channel Value characteristic index statistical number
According to and belong to last year one week value influence indicator-specific statistics data training sample training obtain in one week channel assessment
Model；Alternatively, based on including the Channel Value characteristic index statistical data and belonging to last year one month value influence
The training sample training of indicator-specific statistics data obtains the channel assessment models in January；Alternatively, based on including the Channel Value
Characteristic index statistical data and the training sample training for belonging to last year bimestrial value influence indicator-specific statistics data obtain
Channel assessment models in two months.
In embodiments of the present invention, due to being commented when constructing channel assessment models in different time periods with unified value
Estimate index, therefore is comparable based on the assessment result that channel assessment models in different time periods obtain, and then can facilitate,
Dynamically assess the variation tendency of Channel Quality.
Step S103, channel is assessed based on the channel assessment models.
In embodiments of the present invention, by choosing Channel Value characteristic index and value influence index, and referred to based on these
The training of target historical data obtains channel assessment models, can be assessed automatically Channel Quality, and channel appraiser is reduced
Workload.Further, channel assessment models are obtained by training regression model due to the present invention, determines each index without subjective
Weight, therefore can be improved the accuracy of channel assessment result, reduce channel and assess difficulty.In addition, due to different in building
With unified value assessment index when the channel assessment models of period, therefore it is based on channel assessment models in different time periods
Obtained assessment result is comparable, and then can conveniently, dynamically assess the variation tendency of Channel Quality.
Fig. 2 is the idiographic flow schematic diagram of the appraisal procedure of object-oriented according to an embodiment of the present invention.As shown in Fig. 2,
The appraisal procedure of the object-oriented of the embodiment of the present invention includes:
Step S201, key business index is first determined based on business demand, then based on correlation analysis and/or principal component point
Analysis, filters out Channel Value characteristic index and multiple value influence indexs from the key business index.
Wherein, the channel includes APP channels, the Channel Value characteristic index be embody channel it is long-term (such as
1 year) value index, the value influence index be to Channel Value have an impact it is short-term (such as one week, one month or
Two months) index.
For example, the business demand of a certain shopping class APP operator are as follows: it is total to shopping long-term on the APP to investigate each channel
The influence of the amount of money and profit, then the key business index chosen include: the shopping of channel average each activation equipment in 1 year
The amount of money, in one week average each activation equipment first purchase number of users (referred to as " new user's shopping rate in one week ", may be defined as:
The activation equipment number in number of users/mono- week to do shopping for the first time in one week), in one week average each activation equipment the shopping amount of money
It (referred to as " Channel Value in one week ", may be defined as: by the activation in channel bring shopping total amount/mono- week in one week
Number of devices), (it may be defined as visitor's unit price: interior by the channel by channel bring shopping total amount/mono- week in one week in one week
Bring order numbers), (it may be defined as next day returning rate: the activation equipment after activation in second day playback appliances number/mono- week
Number), returning rate (it may be defined as: the activation equipment number after activation in the 7th day playback appliances number/mono- week) on the 7th, one week
The non-first purchase number of users of interior average each activation equipment (referred to as " old user's shopping rate in one week ", may be defined as: in one week
Activation equipment number in non-number of users/mono- week to do shopping for the first time).
Specifically, the Channel Value characteristic index chosen in the example can be defined as follows:
Wherein, s indicates Channel Value characteristic index, GMViIt indicates in 1 year by channel i bring shopping total amount, ni
It indicates in 1 year by channel i bring activation equipment number.
It should be pointed out that the Channel Value characteristic index of selection, value influence index can also when business demand difference
It can be different.For example, when the new ability of the drawing that a certain shopping class APP operator more values channel, it can be by following customized finger
It is denoted as Channel Value characteristic index:
In formula, s indicates Channel Value characteristic index, GMVnewIndicate in 1 year by the new user of channel bring (i.e. for the first time
The user of shopping) shopping total amount, GMVoldIt indicates in 1 year by channel bring old user (the i.e. non-user to do shopping for the first time)
Shopping total amount, niIt indicates in 1 year by the channel bring activation equipment number.
It further, in this example, can be average each sharp in First Year by channel after determining key business index
The shopping amount of money of equipment living is as Channel Value characteristic index.Also, pass through the analysis of the data such as correlation analysis, principal component analysis
Method, filtering out from the key business index influences big and small several of correlation each other to channel long-term value
Index is as value influence index.For example, in a certain shopping class APP company when carrying out channel assessment, by step S201
Correlation analysis and principal component analysis, by user's shopping rate new in one week, Channel Value in one week, visitor's unit price in one week, make
For value influence index.
In addition, in the specific implementation, before carrying out correlation analysis and principal component analysis, may also include that each canal
The data in road are cleaned.For example, the data of the channel can be deleted if the activation equipment number of channel is very few, to guarantee
The validity of data.For another example, it can judge whether occur by the data distribution of key business index on each channel of statistics
Exceptional value, and exceptional value is handled.
Step S202, it will include Channel Value characteristic index statistical data and belong to same preset time period
The training sample of value influence indicator-specific statistics data inputs multiple linear regression model, obtains corresponding channel assessment mould with training
Type.
In embodiments of the present invention, when the Channel Value characteristic index is to embody channel long-term (such as 1 year) to be worth
Index, the value influence index include: the value shadow for belonging to preset time period (for example, one week, one month or two months)
When snap mark, then model training can be carried out based on the historical data of last year, specifically: it will include the Channel Value table of last year
Sign indicator-specific statistics data and belong to last year one week value influence indicator-specific statistics data the trained multiple linear of training sample
Regression model, to obtain the channel assessment models in one week.And based on the Channel Value characteristic index system for including last year
Count and belong to the training sample training multiple linear regression mould of last year one month value influence indicator-specific statistics data
Type, to obtain the channel assessment models in January.And based on include last year the Channel Value characteristic index statistical data,
And the training sample training multiple linear regression model of last year bimestrial value influence indicator-specific statistics data is belonged to, with
Channel assessment models in by two months.
Illustratively, when the shopping amount of money statistical data that training sample includes: average each activation equipment in the whole of last year,
New user's shopping rate statistical data, Channel Value statistical data, visitor's unit price statistical number in one week in one week last year in one week last year
According to when, can Channel Value characteristic index statistical data value influence indicator-specific statistics data obtain the channel in following one week assessment
Model: s=a+b*x1+cx2.Wherein, s indicates the shopping amount of money index of average each activation equipment in 1 year, and a, b, c indicate logical
Cross the constant that model training obtains, x1Indicate Channel Value in one week, x2Indicate new user's shopping rate in one week.Similarly, channel
Channel assessment models and channel valence in January can be obtained in value characteristic index statistical data value influence indicator-specific statistics data
The channel assessment models being worth in characteristic index statistical data value influence indicator-specific statistics data January.
It step S203, will include the test sample for belonging to the value influence indicator-specific statistics data of same preset time period
Corresponding channel assessment models are inputted, to obtain the predicted value of Channel Value characteristic index.
For example, after obtaining the channel assessment models in one week, it can be by each channel in recent one week of acquisition
Test sample data input the model, to obtain value characteristic index predicted value of each channel in recent one week, in order to right
The quality of each channel is assessed in recent one week.In addition, after obtaining the channel assessment models in January, it can be by acquisition
The test sample data of each channel in recent January input the model, to obtain value of each channel in recent one month
Characteristic index predicted value, in order to which the quality to each channel in recent January is assessed.
In embodiments of the present invention, due to being commented when constructing channel assessment models in different time periods with unified value
Estimate index (such as shopping amount of money of channel average each activation equipment in 1 year), therefore is commented based on channel in different time periods
Estimate the assessment result that model obtains to be comparable, and then can conveniently, dynamically assess the variation tendency of Channel Quality.
Step S204, the input and output rate of channel is calculated, and different channels are assessed according to the input and output rate.
Illustratively, the input and output rate of channel can be calculated according to the following formula；
Wherein, ROI indicates the input and output rate of channel, and V indicates the predicted value of Channel Value characteristic index, and P indicates single
The channel of equipment activates expense.
In embodiments of the present invention, by calculating the ROI of channel, APP operator can be made preferably to assess Channel Quality.
In addition, in some embodiments, after step S203 and before step S204, can comprise the further steps of:
Whether the Channel Value characteristic index predicted value of judgment models output exceeds default value interval, and (for example default value interval is
[0,500]), if it is, this is preset the maximum value (such as 500) of value interval as final predicted value, and for walking
In rapid S204；If it is not, then using the predicted value of model output as final predicted value, and in step S204.
In embodiments of the present invention, by above step can the quality to APP channels assessed automatically, reduce
The workload of channel appraiser improves the accuracy of channel assessment result, reduces channel and assesses difficulty.In addition, due in structure
With unified value assessment index when building channel assessment models in different time periods, therefore commented based on channel in different time periods
Estimate the assessment result that model obtains to be comparable, and then can conveniently, dynamically assess the variation tendency of Channel Quality.
Fig. 3 is the main modular schematic diagram of the assessment device of object-oriented according to an embodiment of the present invention.As shown in figure 3,
The assessment device 300 of the object-oriented of the embodiment of the present invention includes: to choose module 301, training module 302, evaluation module 303.
Module 301 is chosen, for choosing Channel Value characteristic index and multiple value influence indexs.
Wherein, the channel includes: APP channels, the Channel Value characteristic index be embody channel it is long-term (such as
1 year) value index, the value influence index be to Channel Value have an impact it is short-term (such as one week, one month or
Two months) index.
In an optional embodiment, chooses module 301 and choose Channel Value characteristic index and multiple value influence indexs
It include: to choose module 301 first to determine key business index based on business demand, then divide based on correlation analysis and/or principal component
Analysis, filters out Channel Value characteristic index and multiple value influence indexs from the key business index.
In the optional embodiment, module 301 is chosen by carrying out correlation analysis, principal component analysis, energy to data
Enough filter out on channel long-term value influence it is big and each other the small several indexs of correlation as value influence index, into
And data processing amount when modeling is reduced, it improves channel and assesses efficiency.
In another optional embodiment, chooses the selection Channel Value characteristic index of module 301 and multiple value influences refer to
Mark includes: to choose the type of service according to belonging to APP of module 301 (for example, shopping type, type of play etc.) inquiry index column
Table, to obtain Channel Value characteristic index corresponding with the type of service and multiple value influence indexs.For example, working as APP institute
When the type of service of category is shopping type, corresponding Channel Value characteristic index is the shopping of average each activation equipment in 1 year
The amount of money, corresponding value influence index are as follows: new user's shopping rate, Channel Value and visitor's unit price in one week in one week in one week.
In the optional embodiment, by by Channel Value characteristic index needed for the various APP filtered out in advance and
Multiple value influence indexs are summarised in a list, so that choosing module 301 can be direct when carrying out channel assessment every time
Index needed for the list obtains is inquired, without repeating data analysis, index screening work, improves the effect of channel assessment
Rate.
Training module 302, when for that will include Channel Value characteristic index statistical data and belong to same default
Between the training sample of value influence indicator-specific statistics data of section input regression model, corresponding channel assessment mould is obtained with training
Type.
Wherein, the regression model can include: multiple linear regression model, random forest regression model, decision tree return
Model or Boosting regression model.
Illustratively, when the Channel Value characteristic index is to embody the index being worth in channel 1 year, the value shadow
It, then can be based on the historical data of last year each channel when snap mark includes: one week, one month or bimestrial value influence index
Building training sample is specifically included with being trained to regression model: based on including the Channel Value characteristic index statistical number
According to and belong to last year one week value influence indicator-specific statistics data training sample training obtain in one week channel assessment
Model；Alternatively, based on including the Channel Value characteristic index statistical data and belonging to last year one month value influence
The training sample training of indicator-specific statistics data obtains the channel assessment models in January；Alternatively, based on including the Channel Value
Characteristic index statistical data and the training sample training for belonging to last year bimestrial value influence indicator-specific statistics data obtain
Channel assessment models in two months.
In embodiments of the present invention, due to being commented when constructing channel assessment models in different time periods with unified value
Estimate index, therefore is comparable based on the assessment result that channel assessment models in different time periods obtain, and then can facilitate,
Dynamically assess the variation tendency of Channel Quality.
Evaluation module 303, for being assessed based on the channel assessment models channel.
Illustratively, evaluation module 303 is based on the channel assessment models and carries out assessment to channel to include: evaluation module
303 will include that the test samples of the value influence indicator-specific statistics data for belonging to same preset time period inputs corresponding channel
Assessment models, to obtain the predicted value of Channel Value characteristic index；Then, evaluation module 303 calculates the input and output rate of channel,
And different channels are compared according to the input and output rate.
For example, evaluation module 303 can be by each canal in recent one week after obtaining the channel assessment models in one week
The test sample data in road input the model, to obtain the value characteristic index predicted value of each channel in recent one week.In addition,
After obtaining the channel assessment models in January, evaluation module 303 can be by the test sample number of each channel in recent January
According to the model is inputted, to obtain the value characteristic index predicted value of each channel in recent one month.
Further, evaluation module 303 can calculate the input and output rate of channel according to the following formula；
Wherein, ROI indicates the input and output rate of channel, and V indicates the predicted value of Channel Value characteristic index, and P indicates single
The channel of equipment activates expense.In embodiments of the present invention, it by calculating the ROI of channel, is preferably assessed convenient for APP operator
Channel Quality.
The device of the embodiment of the present invention can assess automatically Channel Quality, reduce the work of channel appraiser
Amount improves the accuracy of channel assessment result, reduces channel and assesses difficulty.In addition, due to constructing channel in different time periods
With unified value assessment index when assessment models, therefore the assessment knot obtained based on channel assessment models in different time periods
Fruit is comparable, and then can conveniently, dynamically assess the variation tendency of Channel Quality.
Fig. 4 is shown can be using the appraisal procedure of the object-oriented of the embodiment of the present invention or the assessment device of object-oriented
Exemplary system architecture 400.
As shown in figure 4, system architecture 400 may include terminal device 401,402,403, network 404 and server 405.
Network 404 between terminal device 401,402,403 and server 405 to provide the medium of communication link.Network 404 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 401,402,403 and be interacted by network 404 with server 405, to receive or send out
Send message etc..Terminal device 401,402,403 can be the various electronic equipments with display screen and supported web page browsing, packet
Include but be not limited to smart phone, tablet computer, pocket computer on knee and desktop computer etc..
Server 405 can be to provide the server of various services, such as utilize terminal device 401,402,403 to user
Transmitted request provides the back-stage management server supported.Back-stage management server can analyze the request received
Deng processing, and processing result (such as channel assessment result) is fed back into terminal device.
It should be noted that the appraisal procedure of object-oriented provided by the embodiment of the present invention is generally held by server 405
Row, correspondingly, the assessment device of object-oriented is generally positioned in server 405.
It should be understood that the number of terminal device, network and server in Fig. 4 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
In addition, in some cases it may using the appraisal procedure or object-oriented of the object-oriented of the embodiment of the present invention
The exemplary system architecture of assessment device can not also include terminal device 401,402,403 and network 404, that is, only include clothes
Business device 405.It should be understood that in these cases, server 405 can be with display screen and support program operation it is various
Electronic equipment.
Fig. 5 shows the structural schematic diagram for being suitable for the computer system 500 for the server for being used to realize the embodiment of the present invention.
Computer system shown in Fig. 5 is only an example, should not function to the embodiment of the present invention and use scope bring it is any
Limitation.
As shown in figure 5, computer system 500 includes central processing unit (CPU) 501, it can be read-only according to being stored in
Program in memory (ROM) 502 or be loaded into the program in random access storage device (RAM) 503 from storage section 508 and
Execute various movements appropriate and processing.In RAM 503, also it is stored with system 500 and operates required various programs and data.
CPU 501, ROM 502 and RAM 503 are connected with each other by bus 504.Input/output (I/O) interface 505 is also connected to always
Line 504.
I/O interface 505 is connected to lower component: the importation 506 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 507 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 508 including hard disk etc.；
And the communications portion 509 of the network interface card including LAN card, modem etc..Communications portion 509 via such as because
The network of spy's net executes communication process.Driver 510 is also connected to I/O interface 505 as needed.Detachable media 511, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 510, in order to read from thereon
Computer program be mounted into storage section 508 as needed.
Particularly, disclosed embodiment, the process described above with reference to flow chart may be implemented as counting according to the present invention
Calculation machine software program.For example, embodiment disclosed by the invention includes a kind of computer program product comprising be carried on computer
Computer program on readable medium, the computer program include the program code for method shown in execution flow chart.?
In such embodiment, which can be downloaded and installed from network by communications portion 509, and/or from can
Medium 511 is dismantled to be mounted.When the computer program is executed by central processing unit (CPU) 501, system of the invention is executed
The above-mentioned function of middle restriction.
It should be noted that computer-readable medium shown in the present invention can be computer-readable signal media or meter
Calculation machine readable storage medium storing program for executing either the two any combination.Computer readable storage medium for example can be --- but not
Be limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.Meter
The more specific example of calculation machine readable storage medium storing program for executing can include but is not limited to: have the electrical connection, just of one or more conducting wires
Taking formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only storage
Device (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device,
Or above-mentioned any appropriate combination.In the present invention, computer readable storage medium can be it is any include or storage journey
The tangible medium of sequence, the program can be commanded execution system, device or device use or in connection.And at this
In invention, computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to: wireless, electric wire, optical cable, RF etc. are above-mentioned
Any appropriate combination.
Flow chart and block diagram in attached drawing are illustrated according to the system of various embodiments of the invention, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of above-mentioned module, program segment or code include one or more
Executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in box
The function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practical
On can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it wants
It is noted that the combination of each box in block diagram or flow chart and the box in block diagram or flow chart, can use and execute rule
The dedicated hardware based systems of fixed functions or operations is realized, or can use the group of specialized hardware and computer instruction
It closes to realize.
Being described in module involved in the embodiment of the present invention can be realized by way of software, can also be by hard
The mode of part is realized.Described module also can be set in the processor, for example, can be described as: a kind of processor packet
It includes and chooses module, training module, evaluation module.Wherein, the title of these modules is not constituted under certain conditions to the module
The restriction of itself is also described as " choosing the mould of Channel Value characteristic index and value influence index for example, choosing module
Block ".
As on the other hand, the present invention also provides a kind of computer-readable medium, which be can be
Included in equipment described in above-described embodiment；It is also possible to individualism, and without in the supplying equipment.Above-mentioned calculating
Machine readable medium carries one or more program, when said one or multiple programs are executed by the equipment, makes
It obtains the equipment and executes following below scheme: choosing Channel Value characteristic index and multiple value influence indexs；It will include Channel Value
Characteristic index statistical data and belong to same preset time period value influence indicator-specific statistics data training sample input
Regression model obtains corresponding channel assessment models with training；Channel is assessed based on the channel assessment models.
Above-mentioned specific embodiment, does not constitute a limitation on the scope of protection of the present invention.Those skilled in the art should be bright
It is white, design requirement and other factors are depended on, various modifications, combination, sub-portfolio and substitution can occur.It is any
Made modifications, equivalent substitutions and improvements etc. within the spirit and principles in the present invention, should be included in the scope of the present invention
Within.
Claims (12)
1. a kind of appraisal procedure of object-oriented, which is characterized in that the described method includes:
Choose Channel Value characteristic index and multiple value influence indexs；
It will include Channel Value characteristic index statistical data and the value influence index system for belonging to same preset time period
The training sample input regression model counted, obtains corresponding channel assessment models with training；
Channel is assessed based on the channel assessment models.
2. the method according to claim 1, wherein the selection Channel Value characteristic index and multiple value shadows
Snap target step includes:
It first determines key business index, then is based on correlation analysis and/or principal component analysis, sieved from the key business index
Select Channel Value characteristic index and multiple value influence indexs.
3. the method according to claim 1, wherein the selection Channel Value characteristic index and multiple value shadows
Snap target step includes:
The type of service according to belonging to APP inquires index list, to obtain Channel Value characterization corresponding with the type of service
Index and multiple value influence indexs.
4. the method according to claim 1, wherein the regression model include: multiple linear regression model, with
Machine forest regression model or decision tree regression model.
5. the method according to claim 1, wherein described comment channel based on the channel assessment models
The step of estimating include:
It will include the corresponding canal of test sample input for the value influence indicator-specific statistics data for belonging to same preset time period
Road assessment models, to obtain the predicted value of Channel Value characteristic index；And
The input and output rate of channel is calculated according to the following formula, and different channels are assessed according to the input and output rate；
Wherein, ROI indicates the input and output rate of channel, and V indicates the predicted value of Channel Value characteristic index, and P indicates individual equipment
Channel activate expense.
6. the method according to claim 1, wherein the Channel Value characteristic index includes: at the first time
The shopping amount of money of average each activation equipment in section；The value influence index includes: in second time period and/or third time
In section, the first of average each activation equipment purchases number of users, the shopping amount of money of average each activation equipment and visitor's unit price；Wherein,
Second time period, the duration of third period are respectively less than first time period.
7. a kind of assessment device of object-oriented, which is characterized in that described device includes:
Module is chosen, for choosing Channel Value characteristic index and multiple value influence indexs；
Training module, for that will include Channel Value characteristic index statistical data and belong to same preset time period
The training sample of value influence indicator-specific statistics data inputs regression model, obtains corresponding channel assessment models with training；
Evaluation module, for being assessed based on the channel assessment models channel.
8. device according to claim 7, which is characterized in that the selection module chooses Channel Value characteristic index and more
A value influence index includes:
The selection module first determines key business index, then is based on correlation analysis and/or principal component analysis, from the key
Channel Value characteristic index and multiple value influence indexs are filtered out in operational indicator.
9. device according to claim 7, which is characterized in that the selection module chooses Channel Value characteristic index and more
A value influence index includes:
Selection module type of service according to belonging to APP inquires index list, corresponding with the type of service to obtain
Channel Value characteristic index and multiple value influence indexs.
10. device according to claim 7, which is characterized in that the evaluation module is based on the channel assessment models pair
Channel carries out assessment
It will include the corresponding canal of test sample input for the value influence indicator-specific statistics data for belonging to same preset time period
Road assessment models, to obtain the predicted value of Channel Value characteristic index；
And
The input and output rate of channel is calculated according to the following formula, and different channels are assessed according to the input and output rate；
Wherein, ROI indicates the input and output rate of channel, and V indicates the predicted value of Channel Value characteristic index, and P indicates individual equipment
Channel activate expense.
11. a kind of server characterized by comprising
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now method as described in any in claim 1 to 6.
12. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that described program is held by processor
The method as described in any in claim 1 to 6 is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711459997.7A CN109978304A (en) | 2017-12-28 | 2017-12-28 | The appraisal procedure and device of object-oriented |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711459997.7A CN109978304A (en) | 2017-12-28 | 2017-12-28 | The appraisal procedure and device of object-oriented |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109978304A true CN109978304A (en) | 2019-07-05 |
Family
ID=67074771
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711459997.7A Pending CN109978304A (en) | 2017-12-28 | 2017-12-28 | The appraisal procedure and device of object-oriented |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109978304A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111612366A (en) * | 2020-05-27 | 2020-09-01 | 中国联合网络通信集团有限公司 | Channel quality evaluation method and device, electronic equipment and storage medium |
| CN115713224A (en) * | 2022-11-28 | 2023-02-24 | 四川京龙光电科技有限公司 | Multi-time meta-evaluation method and system suitable for LCD assembly process |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886168A (en) * | 2012-12-19 | 2014-06-25 | 腾讯科技（深圳）有限公司 | Multi-channel analysis method and device based on analytic hierarchy process |
| CN104112221A (en) * | 2014-07-02 | 2014-10-22 | 百度在线网络技术（北京）有限公司 | Method and device for determining value of channel |
| CN106355432A (en) * | 2016-08-19 | 2017-01-25 | 焦点科技股份有限公司 | Method for monitoring effectiveness of television advertisements |
| CN106845767A (en) * | 2016-12-16 | 2017-06-13 | 浙江大学 | A kind of industry development in science and technology power quantitative estimation method and assessment system |
| US20170213237A1 (en) * | 2016-01-25 | 2017-07-27 | Adobe Systems Incorporated | Simulation-based evaluation of a marketing channel attribution model |
-
2017
- 2017-12-28 CN CN201711459997.7A patent/CN109978304A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886168A (en) * | 2012-12-19 | 2014-06-25 | 腾讯科技（深圳）有限公司 | Multi-channel analysis method and device based on analytic hierarchy process |
| CN104112221A (en) * | 2014-07-02 | 2014-10-22 | 百度在线网络技术（北京）有限公司 | Method and device for determining value of channel |
| US20170213237A1 (en) * | 2016-01-25 | 2017-07-27 | Adobe Systems Incorporated | Simulation-based evaluation of a marketing channel attribution model |
| CN106355432A (en) * | 2016-08-19 | 2017-01-25 | 焦点科技股份有限公司 | Method for monitoring effectiveness of television advertisements |
| CN106845767A (en) * | 2016-12-16 | 2017-06-13 | 浙江大学 | A kind of industry development in science and technology power quantitative estimation method and assessment system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111612366A (en) * | 2020-05-27 | 2020-09-01 | 中国联合网络通信集团有限公司 | Channel quality evaluation method and device, electronic equipment and storage medium |
| CN115713224A (en) * | 2022-11-28 | 2023-02-24 | 四川京龙光电科技有限公司 | Multi-time meta-evaluation method and system suitable for LCD assembly process |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108985809A (en) | Motivate method, apparatus, electronic equipment and the storage medium of push | |
| CN107885796A (en) | Information recommendation method and device, equipment | |
| CN103150696A (en) | Method and device for selecting potential customer of target value-added service | |
| CN109976997A (en) | Test method and device | |
| CN109961299A (en) | The method and apparatus of data analysis | |
| CN110163705A (en) | Method and apparatus for pushed information | |
| CN106911801A (en) | The method and information transmission system of association user information | |
| CN110020162A (en) | User identification method and device | |
| CN110109901A (en) | The method and apparatus for screening target object | |
| CN110400184A (en) | Method and apparatus for generating information | |
| CN108154311A (en) | Top-tier customer recognition methods and device based on random forest and decision tree | |
| CN111626767B (en) | Resource data issuing method, device and equipment | |
| CN109657998A (en) | A kind of resource allocation methods, device, equipment and storage medium | |
| CN109492863A (en) | The automatic generation method and device of financial document | |
| CN109961199A (en) | A kind of method and apparatus for analyzing data fluctuations | |
| CN109978304A (en) | The appraisal procedure and device of object-oriented | |
| WO2015101983A1 (en) | Method and system for monetizing products and services usage | |
| CN109993566A (en) | A kind of method and apparatus for predicting product objective data | |
| CN110020876A (en) | A kind of information generating method and device | |
| CN109948773A (en) | The method and apparatus for generating information | |
| CN110110197A (en) | Information acquisition method and device | |
| KR20180082214A (en) | Risk value evaluating system for unclaimed construction and risk value evaluating apparatus for unclaimed construction | |
| CN112884497A (en) | Method and device for determining user type, electronic equipment and storage medium | |
| CN110209883A (en) | A kind of method and device of user's history data validity judgement | |
| CN110020364A (en) | The method and apparatus for determining the traffic source of page access |
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 |