CN106548375A - Method and apparatus for building product portrait - Google Patents
Method and apparatus for building product portrait Download PDFInfo
- Publication number
- CN106548375A CN106548375A CN201610964911.5A CN201610964911A CN106548375A CN 106548375 A CN106548375 A CN 106548375A CN 201610964911 A CN201610964911 A CN 201610964911A CN 106548375 A CN106548375 A CN 106548375A
- Authority
- CN
- China
- Prior art keywords
- characteristic
- weight
- user
- dimension
- consumption user
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present disclosure discloses a kind of method and apparatus for building product portrait.Methods described includes：The characteristic of the consumption user of target product is classified according to multiple dimensions；The weight of each dimension is determined according to the characteristic of the consumption user；According to the weight of characteristic each dimension with determined by of the consumption user, the scoring of each consumption user in the consumption user is determined；The feature user in the consumption user is determined according to the scoring；According to the characteristic of the feature user, the product portrait of the target product is determined.So, on the basis of the weight of each dimension of user characteristic data is considered, construct more accurate product portrait, be conducive to consumption user be accurately positioned and product improvement, increase product benefit.
Description
Technical field
It relates to computer realm, in particular it relates to a kind of method and apparatus for building product portrait.
Background technology
Product portrait is a kind of positioning to product, can include the colony of the portrait and product user of product self attributes
Portrait.Drawn a portrait by product, can be in product promotion, the characteristic of the user group of analysis product excavates potential customers
Colony, carries out targetedly product improvement, reaches the demand of the high speed development steady in a long-term of enterprise.
The method for building product portrait conventional at present includes simple filtration method and artificial point system.
In simple filtration method, if user has a condition not meet, just it is filtered very much.For example, in recruitment industry,
User is filtered generally by the attribute of input user.Such as company's recruitment con dition is：Specialty is software, academic for master, work
Make experience more than 5 years, and the keyword of resume includes big data.The user group's scope for so filtering out is little, Hen Duoyong
Only have a wherein rule not meet (for example, educational background is undergraduate course) in family.For this resume, by simple filtration method just quilt completely
Filter out.
In the method for artificial scoring, each dimension of user is manually given a mark, such as region, the age, keyword,
Each dimension such as interest is giving a mark.This method is given a mark with artificial experience, and the product portrait of structure is often inaccurate.
The content of the invention
The purpose of the disclosure is to provide a kind of simple method and apparatus for building product portrait.
To achieve these goals, the disclosure provides a kind of method for building product portrait.Methods described includes：Will
The characteristic of the consumption user of target product is classified according to multiple dimensions；It is true according to the characteristic of the consumption user
The weight of fixed each dimension；According to the weight of characteristic each dimension with determined by of the consumption user, each is determined
The scoring of consumption user；The feature user in the consumption user is determined according to the scoring；According to the spy of the feature user
Data are levied, the product portrait of the target product is determined.
Alternatively, the step of characteristic according to the consumption user determines the weight of each dimension includes：Point
Do not calculate its characteristic include characteristic corresponding with each dimension consumption user number and the consumption user
Total number ratio, obtain correspondence dimension data frequency；Calculated in the total number and its characteristic of overall user respectively
Including the logarithm of the ratio of the number of the overall user of characteristic corresponding with each dimension, the reverse frequency of correspondence dimension is obtained
Rate, wherein, the overall user includes the consumption user and non-consumption user；Respectively the data frequency of each dimension is multiplied by
Reverse frequency, obtains the weight of correspondence dimension.
Alternatively, the step of characteristic according to the consumption user determines the weight of each dimension includes：Week
Interval weight of each dimension in current period is determined according to the characteristic of the consumption user phase property；According to each dimension
The history interval weight and current interval weight of degree, determines the weight of each dimension.
Alternatively, the weight of the characteristic according to the consumption user each dimension with determined by, it is determined that often
The step of scoring of individual consumption user, includes：The weight of each characteristic is determined according to the characteristic of the consumption user；
According to the weight of weight each dimension with determined by of each characteristic, the scoring of each consumption user is determined.
Alternatively, the step of characteristic according to the consumption user determines the weight of each characteristic is wrapped
Include：Calculate its characteristic include fisrt feature data consumption user number and the total number of the consumption user ratio
Value, obtains the data frequency of the fisrt feature data；The total number of the overall user of calculating includes described with its characteristic
The logarithm of the ratio of the number of the overall user of fisrt feature data, obtains the reverse frequency of the fisrt feature data, wherein,
The overall user includes the consumption user and non-consumption user；The data frequency of the fisrt feature data is multiplied by described
The reverse frequency of fisrt feature data, obtains the weight of the fisrt feature data.
Alternatively, the step of characteristic in the consumption user by target product is classified according to multiple dimensions
Before, methods described also includes：It is determined that the like product similar to the target product；By the consumption user of the like product
It is defined as the consumption user of the target product.
The disclosure also provides a kind of device for building product portrait.Described device includes：Sort module, for by mesh
The characteristic of the consumption user of mark product is classified according to multiple dimensions；Weight determination module, for according to the consumption
The characteristic of user determines the weight of each dimension；Scoring determining module, for the characteristic according to the consumption user
The weight of each dimension with determined by, determines the scoring of each consumption user；Feature user's determining module, for according to described
Scoring determines the feature user in the consumption user；Product portrait determining module, for the feature according to the feature user
Data, determine the product portrait of the target product.
By above-mentioned technical proposal, the weight of each dimension is determined based on the characteristic of consumption user itself so that
The weight of dimension more accurately embodies the feature of consumption user.Therefore, the disclosure is considering each of user characteristic data
On the basis of the weight of individual dimension, more accurate product portrait is constructed, is conducive to being accurately positioned and producing to consumption user
The improvement of product, increases product benefit.
Other feature and advantage of the disclosure will be described in detail in subsequent specific embodiment part.
Description of the drawings
Accompanying drawing is, for providing further understanding of the disclosure, and to constitute the part of specification, with following tool
Body embodiment is used for explaining the disclosure together, but does not constitute restriction of this disclosure.In the accompanying drawings：
Fig. 1 is the flow chart for building the method for product portrait that an exemplary embodiment is provided；
Fig. 2 is the flow chart of the weight of determination each dimension that an exemplary embodiment is provided；
Fig. 3 is the flow chart of the weight of determination each dimension that another exemplary embodiment is provided；
Fig. 4 is the flow chart for building the method for product portrait that another exemplary embodiment is provided；
Fig. 5 is the block diagram for building the device of product portrait that an exemplary embodiment is provided.
Specific embodiment
It is described in detail below in conjunction with accompanying drawing specific embodiment of this disclosure.It should be appreciated that this place is retouched
The specific embodiment stated is merely to illustrate and explains the disclosure, is not limited to the disclosure.
As described above, when using simple filter method, even if there was only wherein one in the characteristic of user not meeting
Preset rules, are also filtered completely.But in fact, do not meet for wherein one, but it is particularly pertinent in terms of other
Resume, many companies are also what is thought favourably of.In view of the above problems, inventor expects, when building product and drawing a portrait, Ke Yicong
The characteristic of consumption user itself is set out, and determines the weight of each dimension that characteristic is divided into, so that according to power
The feature user for determining again is more accurate, finally makes product portrait more accurate.
Fig. 1 is the flow chart for building the method for product portrait that an exemplary embodiment is provided.As shown in figure 1, institute
The method of stating may comprise steps of.
In step s 11, the characteristic of the consumption user of target product is classified according to multiple dimensions.
Wherein, consumption user can be the user for being consumed to target product (for example, bought target product).
The characteristic of consumption user can include the characteristic of multiple dimensions (or species).For example, can include for describing people
The aspects such as mouth attribute, behavior, hobby, business：The dimensions such as age, sex, occupation, region, collection, thumb up.
In step s 12, the weight of each dimension is determined according to the characteristic of consumption user.
In the characteristic of a consumption user, not necessarily have in each dimension.The feature of certain dimension
Data occur more in consumption user, show that the dimension is more important for the description of feature user, and the weights of the dimension are just
It is higher.
Simply, can calculate its characteristic respectively includes the consumption user of characteristic corresponding with each dimension
Number and consumption user total number ratio, obtain the weight of correspondence dimension.For example, the total number of consumption user is 100,
Its characteristic includes that the number of the consumption user of man or female's (characteristic corresponding with sex dimension) is 20, then sex dimension
The weight of degree is 0.2 (20/100).
In step s 13, according to the characteristic of consumption user and determined by each dimension weight, determine that each disappears
The scoring at expense family.
Simply, predetermined value can be given by each characteristic included by each dimension, the predetermined value is for example
Can be set according to the tendentiousness of itself wish by user, it is also possible to set according to experiment or experience.One consumption is being used
When family is scored, the value of characteristic that can be by the consumption user in each dimension is weighted (place dimension
Weight) summation, obtain the scoring of the consumption user.What the scoring embodied the feature of consumption user and target product associates journey
Degree.
In step S14, the feature user in consumption user is determined according to scoring.
As described above, consumption user can be the user for being consumed to target product.In consumption user, can wrap
Include feature user and other users.Wherein, feature user can be the user of its feature and target product highlights correlations, or
Say, be the easy consumer groups of target product.And the other users outside feature user can be with the target product degree of association less
High user, in other words, is the accidental consumer group of target product.The colony is only because accidental cause has consumed target product
Product, therefore, when product portrait is carried out, can be excluded.It is, in the disclosure, filtering out from consumption user and easily disappearing
Take crowd, the analysis of characteristic is then carried out by the easy consumer groups to the target product, the product of target product is obtained
Portrait.
For example, score more high, represent that the consumption user is easier and consume the target product, can be by scoring higher than predetermined
Scoring threshold value consumption user determine be characterized user.
In step S15, according to the characteristic of feature user, the product portrait of target product is determined.
After determining feature user, the characteristic of feature user can be analyzed using various methods.Simply, may be used
Method to adopt statistics accounting.It is, in each dimension, its characteristic includes that the consumption of a certain characteristic is used
With its characteristic, amount mesh includes that the accounting of the number of the consumption user of arbitrary characteristic in the dimension exceedes predetermined threshold
It is worth or more than the accounting of other characteristics, it is possible to the part that this feature data are drawn a portrait as product.
For example, in all 100 consumption users, 80 consumption users include the data characteristics of age dimension.Wherein,
Its characteristic includes that the consumption user of 20-30 year data characteristics has 50 people, and its characteristic includes 30-40 ages according to spy
The consumption user levied has 20 people, and its characteristic includes that the consumption user of 40-50 year data characteristics has 10 people.Then its characteristic
Include any data feature in age dimension with its characteristic according to the consumption user for including 20-30 year data characteristics
The accounting (50/80) of the number of consumption user, it is more than 30-40 year corresponding accounting (20/80) and corresponding more than 40-50 year
Accounting (10/80), the then part that the data characteristics of 20-30 year can be drawn a portrait as product.
By above-mentioned technical proposal, the weight of each dimension is determined based on the characteristic of consumption user itself so that
The weight of dimension more accurately embodies the feature of consumption user.Therefore, the disclosure is considering each of user characteristic data
On the basis of the weight of individual dimension, more accurate product portrait is constructed, is conducive to being accurately positioned and producing to consumption user
The improvement of product, increases product benefit.
Word frequency-reverse document-frequency (Term Frequency-Inverse Document Frequency, TF-IDF) is calculated
Method, is a kind of weighting technique that can be used for information retrieval and data mining.In one embodiment of the disclosure, the calculation can be applied
The weight conceived to determine each dimension of method.
Specifically, Fig. 2 is the flow chart of the weight of determination each dimension that an exemplary embodiment is provided.As shown in Fig. 2
The step of determining the weight of each dimension according to the characteristic of consumption user (step S12) may comprise steps of.
In step S121, calculating its characteristic respectively includes that the consumption of characteristic corresponding with each dimension is used
The number at family and the ratio of the total number of consumption user, obtain the data frequency of correspondence dimension.
Wherein, characteristic corresponding with each dimension data value namely in this dimension, corresponding with each dimension
Characteristic can include multiple characteristics.For example, characteristic corresponding with sex dimension can include man and female, with
The corresponding characteristic of age dimension can include 20-30 year, 30-40 year and 40-50 year.
In the characteristic of a consumption user, not necessarily have in each dimension.The feature of certain dimension
Data occur more in consumption user, show that the dimension is more important for the description of feature user, and the weights of the dimension are just
It is higher.
For example, the total number of consumption user is 100, and its characteristic includes characteristic corresponding with sex dimension
The number of the consumption user of (man or female) is 20, then the data frequency of sex dimension is 0.2 (20/100).
In step S122, with its characteristic, the total number for calculating overall user respectively includes that each dimension is corresponding
The logarithm (for example, with ten as bottom) of the ratio of the number of the overall user of characteristic, obtains the reverse frequency of correspondence dimension.
Wherein, overall user can include consumption user and non-consumption user (user of non-post-consumer target product).Can
To be understood by, its characteristic includes that the number of the overall user of characteristic corresponding with dimension is more, then the dimension
The difference degree of degree is lower, and corresponding weights are lower.
For example, the total number of overall user is 10,000,000, and its characteristic includes spy corresponding with sex dimension
The number for levying the overall user of data (man or female) is 10,000, then the reverse frequency of sex dimension is
In step S123, the data frequency of each dimension is multiplied by into reverse frequency respectively, obtains the weight of correspondence dimension.
In the disclosure, data frequency and reverse frequency be respectively equivalent to the word frequency in word frequency-reverse document-frequency algorithm and
Reverse document-frequency.According to the design of the algorithm, the weight of each dimension can be multiplied by reverse frequency for the data frequency of the dimension
Rate.On the basis of above-mentioned example, the weight of sex dimension can be 0.2 × 3=0.6.
So far, for each dimension, its corresponding weight can be calculated.In the embodiment, according to word frequency-reverse text
Part frequency algorithm calculates the weight of each dimension, embodies each dimension exactly for the importance of feature user, simply
Easy, availability is good.
As time goes on, a large amount of accumulations of data volume, may impact to the accuracy of result.Also, it is special
The relevance that the fixed time period is likely between the characteristic to some users and target product has considerable influence.For example, exist
During Europe Cup football match, there are a large amount of puppet football fans, consumed a large amount of football products.And compete after, these pseudo- football fans for
The interest of the football product of post-consumer greatly can weaken before, or even disappear.In consideration of it, in the another embodiment of the disclosure
In, it may be considered that the historical development of weight in each dimension, determine its weight.
Fig. 3 is the flow chart of the weight of determination each dimension that another exemplary embodiment is provided.As shown in figure 3, according to
The step of characteristic of consumption user determines the weight of each dimension (step S12) may comprise steps of.
In step S124, periodically determine each dimension in current period according to the characteristic of consumption user
Interval weight.
It is, each dimension can be determined in this week according to the consumption user in each cycle (for example, one month)
Weight in phase, i.e. interval weight.Interval weight is obtained by the data in the cycle, embodies the dimension and target in specific period
The correlation degree of product.
In step s 125, the history interval weight and current interval weight according to each dimension, determines each dimension
Weight.
It is determined that the weight of the dimension after the interval weight of dimension, can be drawn accordingly, the step of after being applied to.Examine
Consider under normal conditions, time nearer data can more embody the trend of current development, for example can be to history interval weight
Predetermined less and larger weight is given respectively with current interval weight, by both history interval weight and current interval weight
Weighted sum obtains the weight of the dimension.
For example, it is obtained by the characteristic of nearest month, the corresponding interval weight of sex dimension is 0.6
(current interval weight).And be obtained according to a month characteristic before, the weight of sex dimension is 0.4 (history interval
Weight).Predetermined 0.8 and 0.2 weight are given respectively can to current interval weight and history interval weight, then sex dimension
Weight can be 0.6 × 0.8+0.4 × 0.2=0.56.
And for example, it is obtained by the characteristic of a month period of Europe Cup football match, the corresponding interval power of sex dimension
Weight is 0.6 (current interval weight).And be obtained according to a month characteristic before, the weight of sex dimension (is gone through for 0.9
History interval weight).In view of during football match, as propaganda strength is strong, phenomenon of following the wind is serious, emerges a large amount of puppet balls
Fan.So, the weight of current interval weight could be arranged to less, and the weight of history interval weight could be arranged to larger.Example
Such as, predetermined 0.1 and 0.9 weight can be given respectively to current interval weight and history interval weight, then sex dimension
Weight can be 0.6 × 0.1+0.9 × 0.9=0.87.
In the embodiment, it is contemplated that the historical development of dimension weight, the weight of dimension is determined in the way of increment so that
Determined by the weight of dimension more meet current practice so that product portrait is more accurate.
As it was previously stated, the value of each characteristic for giving a mark to consumption user (is also the power of characteristic below
Again), can be rule of thumb or test determines.The weight of characteristic can also be according to the characteristic of user itself come really
It is fixed.In an embodiment of the disclosure, according to the weight of characteristic each dimension with determined by of consumption user, it is determined that often
The step of scoring of individual consumption user (step S13), can include step S131 and step S132.
In step S131, the weight of each characteristic is determined according to the characteristic of the consumption user.
The step can be implemented according to the design of word frequency-reverse document-frequency algorithm, specifically, can be according to following step
It is rapid to implement.
(1) calculate its characteristic include fisrt feature data consumption user number and consumption user total number
Ratio, obtain the data frequency of fisrt feature data.
Wherein, fisrt feature data can be any feature data of consumption user.A certain characteristic is in consumption user
In occur more, show that this feature data are more important for the description of feature user, the weights of this feature data are higher.
For example, the total number of consumption user is 100, and characteristic includes that the number of the consumption user of the male sex is 80, then
The data frequency of masculinity data is 0.8 (80/100).
(2) total number of the overall user of calculating includes the number of the overall user of fisrt feature data with characteristic
The logarithm of ratio, obtains the reverse frequency of fisrt feature data.Wherein, overall user includes consumption user and non-consumption user.
It is understood that characteristic includes that the number of the overall user of fisrt feature data is more, then this feature
The difference degree of data is lower, and corresponding weights are lower.
For example, the total number of overall user is 10,000,000, and characteristic includes the number of the overall user of the male sex
For 10,000, then reverse frequency is
(3) data frequency of fisrt feature data is multiplied by the reverse frequency of fisrt feature data, fisrt feature number is obtained
According to weight.
As described above, according to the design of word frequency-reverse document-frequency algorithm, the weight of each characteristic is this feature number
According to data frequency be multiplied by reverse frequency.On the basis of above-mentioned example, the weight of masculinity data can be 0.8 × 3=
2.4。
Herein, value of the weight of characteristic equivalent to the characteristic described in the embodiment shown in Fig. 1, with Fig. 1's
Embodiment is compared, and in the embodiment, determines characteristic according to characteristic itself and word frequency-reverse document-frequency algorithm
Weight (i.e. the value of characteristic), embodies the feature of feature user exactly, and simple, availability is good.
In step S132, according to the weight of weight each dimension with determined by of each characteristic, each is determined
The scoring of consumption user.
Specifically, the weight of characteristic that can be by a consumption user in each dimension is weighted the (power of dimension
Weight) summation, obtain the scoring of the consumption user.The scoring embodies the feature of consumption user and the correlation degree of target product.
With the embodiment in above-mentioned Fig. 3 similarly, for the weight of characteristic, it is also possible to periodically determine feature
The interval weight of data, it is considered to the historical development of weight, determines the weight of characteristic so that determined in the way of increment
The weight of characteristic more meet current practice so that product portrait is more accurate.The embodiment will not be described in great detail.
In the middle of actual, each product is from the beginning of new listing.In view of when initial, target product does not also have
There is the data volume of consumption user or consumption user less, can now find the like product similar to which, imitate new product
Consumption user, further obtain new product product portrait.
Fig. 4 is the flow chart for building the method for product portrait that another exemplary embodiment is provided.As shown in figure 4,
On the basis of Fig. 1, (the step the step of characteristic of the consumption user of target product is classified according to multiple dimensions
11), before, methods described can also be comprised the following steps.
In step s 110, it is determined that the like product similar to target product.
Like product can be rule of thumb found, or like product can be determined using some algorithms.It is real one
Apply in example, step S110 may comprise steps of：
According to any one in Jie Kade Coefficient Algorithms and Pearson's similarity algorithm or many persons, determine target product and
The similarity of other products；According to determined by, similarity determines the like product similar to target product.
For example, in the embodiment according to Pearson's similarity algorithm, similarity can be calculated using below equation：
Wherein, r represents that the similarity of target product and another product, X and Y represent target product and another product respectively
The weight of i-th dimension degree, n represent dimension number.Wherein, the weight of the dimension of target product for example can be obtained by experience.
And for example, in the embodiment according to Jie Kade Coefficient Algorithms and Pearson's similarity algorithm, can first according to Jie Kade
Coefficient Algorithm is screened, and in the multiple products for obtaining, recycles Pearson's similarity algorithm to obtain similarity after screening.
Next, determined after the like product similar to target product according to similarity, can be by similarity more than predetermined
The product of similarity threshold be defined as like product.
In step S111, the consumption user of like product is defined as into the consumption user of target product.
In this embodiment, in the case of the data volume of consumption user deficiency can be estimated by like product and obtained
The product portrait of target product, so as to solve the problems, such as product " cold start-up " data deficiencies.
Fig. 5 is the block diagram for building the device of product portrait that an exemplary embodiment is provided.As shown in figure 5, described
Device 10 for building product portrait can include sort module 11, weight determination module 12, scoring determining module 13, feature
User's determining module 14, product portrait determining module 15.
Sort module 11 is for the characteristic of the consumption user of target product is classified according to multiple dimensions.
Weight determination module 12 for determining the weight of each dimension according to the characteristic of the consumption user.
Scoring determining module 13 for according to the characteristic of the consumption user and determined by each dimension weight,
Determine the scoring of each consumption user.
Feature user determining module 14 is for according to the feature user in the scoring determination consumption user.
Product draws a portrait determining module 15 for the characteristic according to the feature user, determines the product of the target product
Product are drawn a portrait.
Alternatively, the weight determination module 12 can include the first data frequency calculating sub module, the first reverse frequency
Calculating sub module and the first weight determination sub-module.
First data frequency calculating sub module, includes spy corresponding with each dimension for calculating its characteristic respectively
The number and the ratio of the total number of the consumption user of the consumption user of data are levied, the data frequency of correspondence dimension is obtained.
First reverse frequency calculating sub module, the total number for calculating overall user respectively are included with its characteristic
The logarithm of the ratio of the number of the overall user of characteristic corresponding with each dimension, obtains the reverse frequency of correspondence dimension,
Wherein, the overall user includes the consumption user and non-consumption user.
First weight determination sub-module, for the data frequency of each dimension is multiplied by reverse frequency respectively, obtains correspondence
The weight of dimension.
Alternatively, the weight determination module 12 can include that interval weight determination sub-module and the second weight determine submodule
Block.
Interval weight determination sub-module is used to periodically determine each dimension according to the characteristic of the consumption user
Interval weight in current period.
Second weight determination sub-module for the history interval weight and current interval weight according to each dimension, it is determined that often
The weight of individual dimension.
Alternatively, the scoring determining module 13 can include data weighting determination sub-module and scoring determination sub-module.
Data weighting determination sub-module for determining the power of each characteristic according to the characteristic of the consumption user
Weight.
Scoring determination sub-module for according to the weight of each characteristic and determined by each dimension weight, it is determined that
The scoring of each consumption user.
Alternatively, the data weighting determination sub-module includes the second data frequency calculating sub module, the second reverse frequency
Calculating sub module and the 3rd weight determination sub-module.
Second data frequency calculating sub module includes the consumption user of fisrt feature data for calculating its characteristic
Number and the ratio of the total number of the consumption user, obtain the data frequency of the fisrt feature data.
Second reverse frequency calculating sub module be used for calculate overall user total number include with its characteristic it is described
The logarithm of the ratio of the number of the overall user of fisrt feature data, obtains the reverse frequency of the fisrt feature data, wherein,
The overall user includes the consumption user and non-consumption user.
3rd weight determination sub-module is for being multiplied by the fisrt feature number by the data frequency of the fisrt feature data
According to reverse frequency, obtain the weight of the fisrt feature data.
Alternatively, described device 10 can also include like product determining module and consumption user determining module.
Like product determining module is used to determine the like product similar to the target product.
Consumption user determining module is for the consumption user of the like product to be defined as the consumption of the target product
User.
With regard to the device in above-described embodiment, wherein modules perform the concrete mode of operation in relevant the method
Embodiment in be described in detail, explanation will be not set forth in detail herein.
By above-mentioned technical proposal, the weight of each dimension is determined based on the characteristic of consumption user itself so that
The weight of dimension more accurately embodies the feature of consumption user.Therefore, the disclosure is considering each of user characteristic data
On the basis of the weight of individual dimension, more accurate product portrait is constructed, is conducive to being accurately positioned and producing to consumption user
The improvement of product, increases product benefit.
The preferred embodiment of the disclosure is described in detail above in association with accompanying drawing, but, the disclosure is not limited to above-mentioned reality
The detail in mode is applied, in the range of the technology design of the disclosure, various letters can be carried out with technical scheme of this disclosure
Monotropic type, these simple variants belong to the protection domain of the disclosure.
It is further to note that each particular technique feature described in above-mentioned specific embodiment, in not lance
In the case of shield, can be combined by any suitable means.In order to avoid unnecessary repetition, the disclosure to it is various can
The combination of energy is no longer separately illustrated.
Additionally, can also be combined between a variety of embodiments of the disclosure, as long as which is without prejudice to this
Disclosed thought, which should equally be considered as disclosure disclosure of that.
Claims (10)
1. it is a kind of for build product portrait method, it is characterised in that methods described includes：
The characteristic of the consumption user of target product is classified according to multiple dimensions；
The weight of each dimension is determined according to the characteristic of the consumption user；
According to the weight of characteristic each dimension with determined by of the consumption user, commenting for each consumption user is determined
Point；
The feature user in the consumption user is determined according to the scoring；
According to the characteristic of the feature user, the product portrait of the target product is determined.
2. method according to claim 1, it is characterised in that it is described determined according to the characteristic of the consumption user it is every
The step of weight of individual dimension, includes：
Calculating its characteristic respectively includes that the number of the consumption user of characteristic corresponding with each dimension is disappeared with described
The ratio of the total number at expense family, obtains the data frequency of correspondence dimension；
The total number and its characteristic that calculate overall user respectively include the entirety of characteristic corresponding with each dimension
The logarithm of the ratio of the number of user, obtains the reverse frequency of correspondence dimension, wherein, the overall user includes that the consumption is used
Family and non-consumption user；
The data frequency of each dimension is multiplied by into reverse frequency respectively, the weight of correspondence dimension is obtained.
3. method according to claim 1, it is characterised in that it is described determined according to the characteristic of the consumption user it is every
The step of weight of individual dimension, includes：
Interval weight of each dimension in current period is determined according to the characteristic of the consumption user periodically；
According to the history interval weight and current interval weight of each dimension, the weight of each dimension is determined.
4. method according to claim 1, it is characterised in that the characteristic according to the consumption user and institute are really
The step of weight of each fixed dimension, scoring for determining each consumption user, includes：
The weight of each characteristic is determined according to the characteristic of the consumption user；
According to the weight of weight each dimension with determined by of each characteristic, the scoring of each consumption user is determined.
5. method according to claim 4, it is characterised in that it is described determined according to the characteristic of the consumption user it is every
The step of weight of individual characteristic, includes：
Calculate its characteristic include fisrt feature data consumption user number and the total number of the consumption user
Ratio, obtains the data frequency of the fisrt feature data；
The total number and its characteristic that calculate entirety user include the number of the overall user of the fisrt feature data
The logarithm of ratio, obtains the reverse frequency of the fisrt feature data, wherein, the overall user include the consumption user and
Non-consumption user；
The data frequency of the fisrt feature data is multiplied by into the reverse frequency of the fisrt feature data, described first is obtained special
Levy the weight of data.
6. method according to claim 1, it is characterised in that in the characteristic of the consumption user by target product
Before the step of being classified according to multiple dimensions, methods described also includes：
It is determined that the like product similar to the target product；
The consumption user of the like product is defined as into the consumption user of the target product.
7. it is a kind of for build product portrait device, it is characterised in that described device includes：
Sort module, for the characteristic of the consumption user of target product is classified according to multiple dimensions；
Weight determination module, for the weight of each dimension is determined according to the characteristic of the consumption user；
Scoring determining module, for according to the characteristic of the consumption user and determined by each dimension weight, it is determined that
The scoring of each consumption user；
Feature user's determining module, for the feature user in the consumption user is determined according to the scoring；
Product portrait determining module, for the characteristic according to the feature user, determines that the product of the target product is drawn
Picture.
8. device according to claim 7, it is characterised in that the weight determination module includes：
First data frequency calculating sub module, includes characteristic corresponding with each dimension for calculating its characteristic respectively
According to consumption user number and the total number of the consumption user ratio, obtain correspondence dimension data frequency；
First reverse frequency calculating sub module, total number and its characteristic for calculating overall user respectively include with often
The logarithm of the ratio of the number of the overall user of the corresponding characteristic of individual dimension, obtains the reverse frequency of correspondence dimension, wherein,
The overall user includes the consumption user and non-consumption user；
First weight determination sub-module, for the data frequency of each dimension is multiplied by reverse frequency respectively, obtains correspondence dimension
Weight.
9. device according to claim 7, it is characterised in that the weight determination module includes：
Interval weight determination sub-module, for periodically determining that each dimension is being worked as according to the characteristic of the consumption user
Interval weight in the front cycle；
Second weight determination sub-module, for history interval weight and current interval weight according to each dimension, determines each
The weight of dimension.
10. device according to claim 7, it is characterised in that the scoring determining module includes：
Data weighting determination sub-module, for the weight of each characteristic is determined according to the characteristic of the consumption user；
Scoring determination sub-module, for according to the weight of each characteristic and determined by each dimension weight, it is determined that often
The scoring of individual consumption user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610964911.5A CN106548375B (en) | 2016-11-04 | 2016-11-04 | Method and apparatus for constructing product portrait |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610964911.5A CN106548375B (en) | 2016-11-04 | 2016-11-04 | Method and apparatus for constructing product portrait |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106548375A true CN106548375A (en) | 2017-03-29 |
| CN106548375B CN106548375B (en) | 2019-10-08 |
Family
ID=58395295
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610964911.5A Active CN106548375B (en) | 2016-11-04 | 2016-11-04 | Method and apparatus for constructing product portrait |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106548375B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107392656A (en) * | 2017-07-07 | 2017-11-24 | 芜湖恒天易开软件科技股份有限公司 | The formulation of the industry user that hires a car portrait and marketing effectiveness tracking |
| CN107516237A (en) * | 2017-07-22 | 2017-12-26 | 长沙兔子代跑网络科技有限公司 | A kind of drawn a portrait according to user excavates the method and device of generation race client |
| CN107944481A (en) * | 2017-11-16 | 2018-04-20 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating information |
| CN108564262A (en) * | 2018-03-31 | 2018-09-21 | 甘肃万维信息技术有限责任公司 | Enterprise's portrait big data model system based on big data analysis |
| CN108805383A (en) * | 2018-03-20 | 2018-11-13 | 东华大学 | A kind of user's portrait platform and application for washing shield big data based on clothes |
| CN109325796A (en) * | 2018-08-13 | 2019-02-12 | 中国平安人寿保险股份有限公司 | Potential user's screening technique, device, computer equipment and storage medium |
| CN109409936A (en) * | 2018-09-28 | 2019-03-01 | 深圳壹账通智能科技有限公司 | Customer consumption portrait generation method, device, equipment and readable storage medium storing program for executing |
| CN109753994A (en) * | 2018-12-11 | 2019-05-14 | 东软集团股份有限公司 | User's portrait method, apparatus, computer readable storage medium and electronic equipment |
| CN109919219A (en) * | 2019-03-01 | 2019-06-21 | 北京邮电大学 | A kind of Xgboost multi-angle of view portrait construction method based on Granule Computing ML-kNN |
| CN110009438A (en) * | 2018-11-07 | 2019-07-12 | 爱保科技（横琴）有限公司 | Information processing method and device based on car owner's community |
| CN111352962A (en) * | 2018-12-24 | 2020-06-30 | 网智天元科技集团股份有限公司 | Client portrait construction method and device |
| CN111581296A (en) * | 2020-04-02 | 2020-08-25 | 深圳壹账通智能科技有限公司 | Data correlation analysis method and device, computer system and readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103309960A (en) * | 2013-05-29 | 2013-09-18 | 亿赞普(北京)科技有限公司 | Method and device for extracting multidimensional information of network public sentiment event |
| CN105761106A (en) * | 2016-02-07 | 2016-07-13 | 徐璇炫 | Object ordering method based on user setting and device thereof |
| CN105869001A (en) * | 2015-01-19 | 2016-08-17 | 苏宁云商集团股份有限公司 | Customized product recommendation guiding method and system |
-
2016
- 2016-11-04 CN CN201610964911.5A patent/CN106548375B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103309960A (en) * | 2013-05-29 | 2013-09-18 | 亿赞普(北京)科技有限公司 | Method and device for extracting multidimensional information of network public sentiment event |
| CN105869001A (en) * | 2015-01-19 | 2016-08-17 | 苏宁云商集团股份有限公司 | Customized product recommendation guiding method and system |
| CN105761106A (en) * | 2016-02-07 | 2016-07-13 | 徐璇炫 | Object ordering method based on user setting and device thereof |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107392656A (en) * | 2017-07-07 | 2017-11-24 | 芜湖恒天易开软件科技股份有限公司 | The formulation of the industry user that hires a car portrait and marketing effectiveness tracking |
| CN107516237A (en) * | 2017-07-22 | 2017-12-26 | 长沙兔子代跑网络科技有限公司 | A kind of drawn a portrait according to user excavates the method and device of generation race client |
| CN107944481A (en) * | 2017-11-16 | 2018-04-20 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating information |
| CN107944481B (en) * | 2017-11-16 | 2022-02-18 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating information |
| CN108805383A (en) * | 2018-03-20 | 2018-11-13 | 东华大学 | A kind of user's portrait platform and application for washing shield big data based on clothes |
| CN108564262A (en) * | 2018-03-31 | 2018-09-21 | 甘肃万维信息技术有限责任公司 | Enterprise's portrait big data model system based on big data analysis |
| CN109325796A (en) * | 2018-08-13 | 2019-02-12 | 中国平安人寿保险股份有限公司 | Potential user's screening technique, device, computer equipment and storage medium |
| CN109325796B (en) * | 2018-08-13 | 2023-09-26 | 中国平安人寿保险股份有限公司 | Potential user screening method, device, computer equipment and storage medium |
| CN109409936A (en) * | 2018-09-28 | 2019-03-01 | 深圳壹账通智能科技有限公司 | Customer consumption portrait generation method, device, equipment and readable storage medium storing program for executing |
| CN110009438A (en) * | 2018-11-07 | 2019-07-12 | 爱保科技（横琴）有限公司 | Information processing method and device based on car owner's community |
| CN109753994B (en) * | 2018-12-11 | 2024-05-14 | 东软集团股份有限公司 | User image drawing method, device, computer readable storage medium and electronic equipment |
| CN109753994A (en) * | 2018-12-11 | 2019-05-14 | 东软集团股份有限公司 | User's portrait method, apparatus, computer readable storage medium and electronic equipment |
| CN111352962A (en) * | 2018-12-24 | 2020-06-30 | 网智天元科技集团股份有限公司 | Client portrait construction method and device |
| CN111352962B (en) * | 2018-12-24 | 2024-03-29 | 网智天元科技集团股份有限公司 | Customer portrait construction method and device |
| CN109919219A (en) * | 2019-03-01 | 2019-06-21 | 北京邮电大学 | A kind of Xgboost multi-angle of view portrait construction method based on Granule Computing ML-kNN |
| CN109919219B (en) * | 2019-03-01 | 2021-02-26 | 北京邮电大学 | Xgboost multi-view portrait construction method based on kernel computing ML-kNN |
| CN111581296B (en) * | 2020-04-02 | 2022-08-16 | 深圳壹账通智能科技有限公司 | Data correlation analysis method and device, computer system and readable storage medium |
| WO2021196457A1 (en) * | 2020-04-02 | 2021-10-07 | 深圳壹账通智能科技有限公司 | Data correlation analysis method and apparatus, computer system, and readable storage medium |
| CN111581296A (en) * | 2020-04-02 | 2020-08-25 | 深圳壹账通智能科技有限公司 | Data correlation analysis method and device, computer system and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106548375B (en) | 2019-10-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106548375A (en) | Method and apparatus for building product portrait | |
| Hartman et al. | The relevant internal rate of return | |
| CN106372249B (en) | A kind of clicking rate predictor method, device and electronic equipment | |
| US10147037B1 (en) | Method and system for determining a level of popularity of submission content, prior to publicizing the submission content with a question and answer support system | |
| US9026594B2 (en) | Method and system for determining user impact on their content pools within an online social network | |
| An et al. | Fragmented social media: a look into selective exposure to political news | |
| US20130297694A1 (en) | Systems and methods for interactive presentation and analysis of social media content collection over social networks | |
| CN110222975A (en) | A kind of loss customer analysis method, apparatus, electronic equipment and storage medium | |
| KR102340463B1 (en) | Sample weight setting method and device, electronic device | |
| TWI793412B (en) | Consumption prediction system and consumption prediction method | |
| TW201939400A (en) | Method and device for determining group of target users | |
| CN103699521A (en) | Text analysis method and device | |
| CN103729424A (en) | Method and system for assessing answers in Q&A (questions and answers) community | |
| US20170124468A1 (en) | Bias correction in content score | |
| CN106886559A (en) | The collaborative filtering method of good friend's feature and similar users feature is incorporated simultaneously | |
| CN108509499A (en) | A kind of searching method and device, electronic equipment | |
| US20140058793A1 (en) | Forecasting a number of impressions of a prospective advertisement listing | |
| CN108446944A (en) | A kind of the determination method, apparatus and electronic equipment in resident city | |
| Dajcman | Time-varying long-range dependence in stock market returns and financial market disruptions–a case of eight European countries | |
| CN104572915B (en) | One kind is based on the enhanced customer incident relatedness computation method of content environment | |
| Gjestvang et al. | Forced quantitative randomized response model: a new device | |
| Nakajima et al. | Capturing changes in asymmetric price transmission: a rolling window tar estimation using bluefin tuna case study | |
| CN103020141A (en) | Method and equipment for providing searching results | |
| CN105740276B (en) | Method and device for estimating click feedback model suitable for commercial search | |
| CN106055566A (en) | Mobile phone game recommendation method aiming at mobile advertisement users |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |