CN107123011A - Trade company recommends method, sets up the method and relevant apparatus of trade company's evaluation model - Google Patents
Trade company recommends method, sets up the method and relevant apparatus of trade company's evaluation model Download PDFInfo
- Publication number
- CN107123011A CN107123011A CN201610743575.1A CN201610743575A CN107123011A CN 107123011 A CN107123011 A CN 107123011A CN 201610743575 A CN201610743575 A CN 201610743575A CN 107123011 A CN107123011 A CN 107123011A
- Authority
- CN
- China
- Prior art keywords
- trade company
- evaluation index
- data
- sample
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0609—Buyer or seller confidence or verification
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Recommend method the invention discloses a kind of trade company, set up the method and relevant apparatus of trade company's evaluation model, wherein, the trade company recommends method to include：Obtain first data related to targeted customer and second data related with trade company to be pushed；The value of the evaluation index of the trade company to be pushed is determined according to first data and the second data；Value and trade company's evaluation model based on the evaluation index are evaluated the trade company to be pushed；Trade company is recommended to the targeted customer according to the evaluation result to the trade company to be pushed.Using the present invention, it can recommend to be adapted to the trade company of user for user, improve Consumer's Experience；Trade company can be showed with the bigger possible user of consumption, improve order volume.Generally speaking, in terms of trade company's recommendation, the quality of recommendation and the experience of user are improved, also, the benefit produced by specific discharge is higher, greatlys save the flow cost of operation platform.
Description
Technical field
The present invention relates to the related data processing field in internet, more particularly, be related to a kind of trade company recommend method,
Set up the method and relevant apparatus of trade company's evaluation model.
Background technology
The development of internet increasingly changes the life style of people.In e-commerce system, how to recommend to close to user
Suitable product, commodity, service or businessman, is significant problem for each e-commerce system.
In existing e-commerce system, by taking take-away field as an example, trade company is being recommended (for example, whole city is dispensed to user
Trade company) when, it is many using fixed trade company's sorted lists.This mode causes the content recommendation for each user the same,
Can not targetedly it be recommended for the user of different characteristics.In addition, in such as online store, purchasing by group the other of service etc
Internet arena, when recommending trade company to user, specific aim recommendation can not be carried out for the user of different characteristics by equally existing
Defect.This does not only result in the expanded inefficient of poor user experience, businessman, and greatly wastes the flow money of operation platform
Source.
The content of the invention
In order to solve the defect present in existing trade company's recommended technology, embodiment of the present invention provides a kind of trade company and recommended
Method, the method and relevant apparatus for setting up trade company's evaluation model, can not only improve the quality and Consumer's Experience of trade company's recommendation, and
And, be conducive to improving the benefit produced by specific discharge, save the flow cost of operation platform.
On the one hand, embodiment of the present invention provides a kind of trade company recommendation method, including：
Obtain first data related to targeted customer and second data related with trade company to be pushed；
The value of the evaluation index of the trade company to be pushed is determined according to first data and the second data；
Value and trade company's evaluation model based on the evaluation index are evaluated the trade company to be pushed；
Trade company is recommended to the targeted customer according to the evaluation result to the trade company to be pushed.
In a kind of implementation of embodiment of the present invention, it is described obtain first data related to targeted customer and
Second data related to trade company to be pushed include：Drawn a portrait from user and obtain the hobby data of the targeted customer, or,
It is any one or more in the hobby data and data below for obtaining the targeted customer of being drawn a portrait from the user：OK
For attribute data, primary attribute data, user's ranked data；And, obtain the trade company to be pushed from trade company's operation platform
Characteristic.
Further, it is described according to the evaluation index of trade company to be pushed described in first data and the determination of the second data
Value, including：The hobby data and the characteristic are patterned into the first figure and second graph respectively；According to institute
The Duplication of the first figure and the second graph is stated, or, according to opposite end on first figure and the second graph
The sum of the distance between point, determines the value of the first evaluation index.
Or, further, the evaluation that the trade company to be pushed is determined according to first data and the second data
Refer to target value, including：Corresponding relation according to default data and evaluation index will remove the interest and like in first data
The value of data outside good data respectively as corresponding evaluation index.For example, by mesh described in the behavior property data
The number of times that mark user searches for each trade company to be pushed is used as the value of the second evaluation index；By mesh described in the behavior property data
The number of times that mark user clicks on each trade company to be pushed is used as the value of the 3rd evaluation index.
In another implementation of embodiment of the present invention, trade company's evaluation model is expressed as below equation：
Wherein, θ=[a0,a1,a2,……,ak]T,K+1 is equal to evaluation index
Number, k=0,1,2,3 ... ..., R represents evaluation of estimate, XkRepresent+1 evaluation index of kth, akRepresent+1 evaluation index of kth
Weight.
Further, the basis recommends trade company, bag to the evaluation result of the trade company to be pushed to the targeted customer
Include：The trade company to be pushed is ranked up according to the order of R values from big to small, and according to ranking results to the targeted customer
Recommend trade company.
On the other hand, embodiment of the present invention also provides a kind of method for setting up trade company's evaluation model, and methods described includes：
Choose sample of users and the sample trade company to be recommended to the sample of users；
Obtain characteristic value of each sample trade company relative to each sample of users after operation certain time；
Characteristic value and each predetermined sample trade company phase according to each sample trade company relative to each sample of users
Value for the evaluation index of each sample of users determines the weight of the evaluation index；
Trade company's evaluation model is set up based on the evaluation index and its weight.
It is described to obtain each sample business after operation certain time in a kind of implementation of embodiment of the present invention
Family relative to each sample of users characteristic value, including：Each sample of users measured by A/B is obtained in each sample
The monthly average amount of placing an order in trade company.
In another implementation of embodiment of the present invention, the evaluation index is included between reflection trade company and user
Matching degree evaluation index, or also include behavior property data, primary attribute data or user's ranked data with user
Corresponding evaluation index..
In another implementation of embodiment of the present invention, it is described according to each sample trade company relative to each sample
The characteristic value of user and each predetermined sample trade company determine described relative to the value of the evaluation index of each sample of users
The weight of evaluation index, including：
First, each sample trade company is substituted into respectively relative to the characteristic value of each sample of users and the value of evaluation index
Below equation obtains equation with many unknowns group：
Wherein, θ=[a0,a1,a2,……,ak]T,K+1 is equal to evaluation index
Number, Z represents the characteristic value, XkRepresent+1 evaluation index of kth, akRepresent the weight of+1 evaluation index of kth；
Then, weight a is calculated according to the equation with many unknowns groupkValue.
Further, it is described that trade company's evaluation model is set up based on the evaluation index and its weight, including：
Based on a calculatedkValue and the evaluation index set up equation below：
Wherein, θ=[a0,a1,a2,……,ak]T,K+1 is equal to evaluation index
Number, R represents evaluation of estimate, XkRepresent+1 evaluation index of kth, akRepresent the weight of+1 evaluation index of kth.
Correspondingly, embodiment of the present invention provides a kind of trade company's recommendation apparatus, and described device includes：
Obtain
Data module, first data related to targeted customer and second number related with trade company to be pushed for obtaining
According to；
Computing module, for according to the evaluation index of trade company to be pushed described in first data and the determination of the second data
Value；
Evaluation module, is commented the trade company to be pushed for the value based on the evaluation index and trade company's evaluation model
Valency；
Recommending module, for recommending trade company to the targeted customer according to the evaluation result to the trade company to be pushed.
In a kind of implementation of embodiment of the present invention, the data module includes：First data submodule, is used for
Perform following operation：Drawn a portrait from user and obtain the hobby data of the targeted customer, or, draw a portrait and obtain from the user
It is any one or more in the hobby data and data below of the targeted customer：Behavior property data, basis category
Property data, user's ranked data；Second data submodule, the feature for obtaining the trade company to be pushed from trade company's operation platform
Data.
Further, the computing module includes：First calculating sub module, for performing following operation：By the interest
Taste data and the characteristic are patterned into the first figure and second graph respectively, and according to first figure with it is described
The Duplication of second graph, or, according to the distance between opposite endpoint on first figure and the second graph and,
Determine the value of the first evaluation index.Or, further, the computing module includes：Second calculating sub module, for according to pre-
If data and evaluation index corresponding relation using in first data except the hobby data are commented as corresponding
Valency refers to target value.For example, the second calculating sub module is used for：Targeted customer described in the behavior property data is searched for into each to treat
The number of times for pushing trade company is used as the value of the second evaluation index；Targeted customer described in the behavior property data is clicked on into each to treat
The number of times for pushing trade company is used as the value of the 3rd evaluation index.
In another implementation of embodiment of the present invention, trade company's evaluation model is expressed as below equation：
Wherein, θ=[a0,a1,a2,……,ak]T,K+1 is equal to evaluation index
Number, R represents evaluation of estimate, XkRepresent+1 evaluation index of kth, akRepresent the weight of+1 evaluation index of kth.
Further, the recommending module is used to arrange the trade company to be pushed according to the order of R values from big to small
Sequence, and recommend trade company to the targeted customer according to ranking results.
Correspondingly, embodiment of the present invention also provides a kind of device for setting up trade company's evaluation model, and described device includes：
Module is chosen, for choosing sample of users and the sample trade company to be recommended to the sample of users；
Characteristic module, for obtaining spy of each sample trade company relative to each sample of users after operation certain time
Value indicative；
Computing module, for according to each sample trade company relative to the characteristic value of each sample of users and predetermined each
Individual sample trade company determines the weight of the evaluation index relative to the value of the evaluation index of each sample of users；
Model module, for setting up trade company's evaluation model based on the evaluation index and its weight.
In a kind of implementation of embodiment of the present invention, the characteristic module is used to obtain to be measured by A/B
Monthly average place an order amount of each sample of users in each sample trade company.
In another implementation of embodiment of the present invention, the evaluation index is included between reflection trade company and user
Matching degree evaluation index, or also include behavior property data, primary attribute data or user's ranked data with user
Corresponding evaluation index.
In another implementation of embodiment of the present invention, the computing module includes：
Submodule is substituted into, for the characteristic value and evaluation index by each sample trade company relative to each sample of users
Value substitutes into below equation and obtains equation with many unknowns group respectively：
Wherein, θ=[a0,a1,a2,……,ak]T,K+1 is equal to evaluation index
Number, Z represents the characteristic value, XkRepresent+1 evaluation index of kth, akRepresent the weight of+1 evaluation index of kth；
Calculating sub module, for calculating weight a according to the equation with many unknowns groupkValue.
Further, the model module is used for：The a calculated according to the computing modulekValue and the evaluation
Index Establishment equation below：
Wherein, θ=[a0,a1,a2,……,ak]T,K+1 is equal to evaluation index
Number, R represents evaluation of estimate, XkRepresent+1 evaluation index of kth, akRepresent the weight of+1 evaluation index of kth.
Had the advantages that using the various embodiments of the present invention：
By gathering user related data and trade company's related data and trade company being evaluated based on trade company's evaluation model, energy
It is enough：1. relatively objective and judgement " trade company is if appropriate for user " exactly；2. recommend to be adapted to the trade company of user for user, improve and use
Experience at family；3. trade company is showed with the bigger possible user of consumption, improves order volume；4. produced by raising specific discharge
Benefit, saves the flow cost of operation platform.
Determine each sample trade company relative to each sample of users based on the operation data to sample of users and sample trade company
Characteristic value, and then calculated relative to the value of the evaluation index of each sample of users with reference to each sample trade company, Neng Gouji
The weighted value of evaluation index is determined in real data, so as to set up accurate evaluation trade company based on evaluation index and its weight
For user if appropriate for trade company's evaluation model.
Brief description of the drawings
Fig. 1 is the schematic flow sheet that method is recommended by a kind of trade company according to embodiments of the present invention；
Fig. 2 is a kind of schematic flow sheet of method for setting up trade company's evaluation model according to embodiments of the present invention；
Fig. 3 is a kind of schematic flow sheet of implementation of the processing 204 in method shown in Fig. 2；
Fig. 4 A are a kind of block diagrams of trade company's recommendation apparatus according to embodiments of the present invention；
Fig. 4 B are a kind of block diagrams of the data module 42 of Fig. 4 A shown devices；
Fig. 4 C are a kind of block diagrams of the computing module 44 of Fig. 4 A shown devices；
Fig. 5 is a kind of block diagram of model equipment for setting up trade company's evaluation model according to embodiments of the present invention；
Fig. 6 is a kind of block diagram of the computing module 56 of model equipment shown in Fig. 5；
Fig. 7 is a kind of schematic diagram by graphical data according to embodiments of the present invention.
Embodiment
It is described in detail to various aspects of the present invention below in conjunction with the drawings and specific embodiments.Wherein, many institute's weeks
The module known, unit and its connection, link, communication or operation each other are not shown or not elaborated.Also, institute
Feature, framework or the function of description can in any way be combined in one or more embodiments.People in the art
Member is it should be appreciated that following various embodiments are served only for for example, not for limiting the scope of the invention.May be used also
To be readily appreciated that, module or unit or step in each embodiment described herein and shown in the drawings can be matched somebody with somebody by various differences
Put and be combined and design.
Fig. 1 is the schematic flow sheet that method is recommended by a kind of trade company according to embodiments of the present invention.Reference picture 1, methods described
Including：
100：Obtain first data related to targeted customer and second data related with trade company to be pushed.
It should be noted that " acquisition " that refers in the present invention be not limited to active obtaining, it is passive receive, directly obtain,
Mode is obtained etc. by transferring device." trade company " referred in the present invention refers to production is sold or provided on internet platform
The businessman of product/service, for example, taking out the trade company on platform." trade company's recommendation " refers to choose specific trade company from numerous trade companies
Or (for example, sequence) recommends user in a specific way." first ", " second " are only used for distinguishing, and represent with independence
Individual/content/is present.
Alternatively, in a kind of implementation of the present embodiment, exemplified by taking out platform, " trade company to be pushed " can be complete
City dispenses trade company.
102：The value of the evaluation index of the trade company to be pushed is determined according to first data and the second data.
" evaluation index " referred in the present invention can be understood as reflect/evaluate user to the expectation degree of trade company or
The index of the degree of recognition.In a kind of preferred implementation of the present embodiment, evaluation index can include reflection trade company and user
Between matching degree evaluation index and reflection user behavior tend to evaluation index.
104：Value and trade company's evaluation model based on the evaluation index are evaluated the trade company to be pushed.For example,
The evaluation of estimate of trade company to be pushed is calculated according to the value of evaluation index and trade company's evaluation model, institute's evaluation values can reflect for phase
For family, degree or possibility that trade company is expected to/approved.
In the present invention, trade company's evaluation model is pre-established, it is for instance possible to use method mentioned below of the invention
Set up.
106：Trade company is recommended to the targeted customer according to the evaluation result to the trade company to be pushed.
The method provided using the present embodiment, by gathering user related data and trade company's related data and being commented based on trade company
Valency model is evaluated trade company, on the one hand, being capable of relatively objective and judgement " trade company is if appropriate for user " exactly；The opposing party
Face, can recommend to be adapted to the trade company of user for user, improve Consumer's Experience；Another further aspect, can show trade company with more
Possible user is consumed greatly, improves order volume.Generally speaking, the benefit produced by specific discharge can be effectively improved, is greatlyd save
The flow cost of operation platform.
Alternatively, in a kind of implementation of the present embodiment, processing 100 can be accomplished by the following way：From user
Portrait obtains the hobby data of the targeted customer, or, drawn a portrait from the user and obtain the interest of the targeted customer
It is any one or more in taste data and data below：Behavior property data, primary attribute data, user's classification number
According to；And, the characteristic of the trade company to be pushed is obtained from trade company's operation platform.
In the implementation, various data can be excavated, organized and stored by special data team, and be realized
Mode only needs to obtain data.Certainly, in other implementations of the present invention, related data carry out group can also be obtained
Knit to obtain the first data and the second data.
Alternatively, in a kind of implementation of the present embodiment, processing 102 can include following processing procedure：By interest
Taste data and characteristic are patterned into the first figure and second graph respectively；It is overlapping with second graph according to the first figure
Rate, or, according to the distance between opposite endpoint on the first figure and second graph and, determine the value of the first evaluation index.
In the implementation, " figure " can be line segment, triangle, quadrangle, other polygons；" end points " includes line
End points, polygonal summit of section etc.." opposite endpoint " refers to the end points in same direction/dimension, for example, referring to Fig. 7 institutes
A kind of more specifically example (being described in detail below) shown, wherein, P1 and p1 are opposite endpoint, P2 and p2 opposite endpoints,
P3 and p3 is opposite endpoint.If other polygons, then the rest may be inferred.
In the implementation, what the first evaluation index reflected is the matching degree between user and trade company.
Alternatively, in a kind of implementation of the present embodiment, processing 102 can include following processing procedure：By first
Data in data in addition to hobby data, according to value of the default correspondence order respectively as corresponding evaluation index.Change
Yan Zhi, those skilled in the art can flexibly, reasonably set evaluation index, and set the source of the value of evaluation index, evaluate
The source of index and its value can be corresponded.
Furthermore, the number of times that targeted customer in behavior property data can be searched for each trade company to be pushed is used as
The value of two evaluation indexes, the number of times that targeted customer in behavior property data is clicked on into each trade company to be pushed refers to as the 3rd evaluation
Target value.Wherein, second evaluation index and the 3rd evaluation index are the evaluations for being preferably used for reflecting that user behavior tends to
Index.
Alternatively, in a kind of implementation of the present embodiment, in processing 104 trade company's evaluation model for referring to be expressed as with
Lower judgement schematics：
Wherein, θ=[a0,a1,a2,……,ak]T,K+1 is equal to evaluation index
Number, R represents evaluation of estimate, XkRepresent+1 evaluation index of kth, akRepresent the weight of+1 evaluation index of kth.In addition, at this
In other implementations of invention, XkAnd akCan be configurable, i.e. allow to calculating XkAnd akIt is adjusted and changes.
By the way that the value for handling the evaluation index obtained in 102 is substituted into above formula, you can obtain evaluation of estimate R.It is exemplary
Ground, processing 106 in, can be treated according to the order of R values from big to small push trade company be ranked up, and according to ranking results to
Targeted customer recommends trade company.
Fig. 2 is a kind of schematic flow sheet of method for setting up trade company's evaluation model according to embodiments of the present invention, the business
Family evaluation model can be used in embodiment illustrated in fig. 1 carrying out trade company's evaluation.Reference picture 2, methods described includes：
200：Choose sample of users and the sample trade company to be recommended to the sample of users.
Alternatively, in a kind of implementation of the present embodiment, the business specified number is randomly selected from trade company to be pushed
Family randomly selects the user specified number as sample of users as sample trade company from user.
202：Obtain characteristic value of each sample trade company relative to each sample of users after operation certain time.
Wherein, with sample trade company A for sample of users a characteristic value, this feature value reflected sample user a is to sample
This trade company A degree of recognition/level of interest/expected degree etc., for example, this feature value can be in certain period of time, sample
Order volume, the favorable comment amounts of user a in sample trade company A etc..In other words, this feature value can be represented for same user
Speech, sequence of the trade company in numerous trade companies.
It should be noted that " certain time " that refers in the present invention and a certain time is not specific to, for example, can be with small
When, day, week, represent the moon.It will be appreciated by those skilled in the art that generally, " certain time " of operation is longer, then feature
Value more can more accurately reflect user to the degree of recognition/level of interest/expected degree of trade company etc., and simultaneously, " certain time "
It is longer, the realization of the method for embodiment illustrated in fig. 2 can be extended again.It is therefore preferred that those skilled in the art can be with summary
Two aspects determine to meet the time of demand.And the present invention is not defined to the specific duration of " certain time ".
204：Calculate weight.Specifically, according to each sample trade company relative to the characteristic value of each sample of users and pre-
Each sample trade company first determined determines the weight of the evaluation index relative to the value of the evaluation index of each sample of users.
Alternatively, in a kind of implementation of the present embodiment, it may be predetermined that evaluation index and evaluation index
Acquisition approach or calculation.Exemplarily, evaluation index can include commenting for the matching degree between reflection user and trade company
Valency index, or, in addition to it is corresponding with the behavior property data, primary attribute data, user's ranked data of user evaluation refer to
Mark.
206：Trade company's evaluation model is set up based on evaluation index and its weight.
The method provided using the present embodiment, each sample is determined based on the operation data to sample of users and sample trade company
Trade company and then refers to reference to each evaluation of sample trade company relative to each sample of users relative to the characteristic value of each sample of users
Target value is calculated, and the weighted value of evaluation index can be determined based on real data, so as to evaluation index and its weight
Based on set up accurate evaluation trade company for user if appropriate for trade company's evaluation model.
Alternatively, in a kind of implementation of the present embodiment, above-mentioned processing 202 can be realized in the following ways：Obtain
Take monthly average place an order amount of each sample of users measured by A/B in each sample trade company.In other words, on
On the take-away platform of line, recommend the sample trade company of selection to the sample of users of selection and continue operation, and then obtain characteristic value.
It should be noted that in the processing 200 of the present embodiment, sample trade company and sample of users can be only chosen, and by
Other devices recommend sample trade company to sample of users.But, in other embodiments of the invention, it can also handle in 200,
After sample trade company and sample of users is chosen, sample trade company is recommended to sample of users.In addition, in processing 202, can carry out
A/B is tested and then is obtained characteristic value, can also be triggered other devices and be carried out A/B tests and only obtain characteristic value from the device.
Alternatively, in a kind of implementation of the present embodiment, reference picture 3, processing 204 can be real in the following ways
It is existing：
300:Data substitution preset formula is obtained into equation with many unknowns group.Specifically, by each sample trade company relative to each
The characteristic value of individual sample of users and the value of evaluation index substitute into below equation and obtain equation with many unknowns group respectively：
Wherein, θ=[a0,a1,a2,……,ak]T,K+1 is equal to evaluation index
Number, Z represents the characteristic value, XkRepresent+1 evaluation index of kth, akRepresent the weight of+1 evaluation index of kth.
302：Weight a is calculated according to the equation with many unknowns groupkValue.Specifically, it is assumed that have m sample trade company, n sample
This user, then can obtain m*n equation group, solve this m*n equation group and can obtain evaluation index XkWeight akValue.
Alternatively, can be using least square method, linear regression (Linear Regression), many in processing 302
Item formula returns the parameter that (Polynomial Regression), ElasticNet recurrence etc. solve equation with many unknowns group.
In the implementation, it is possible to further a calculated according to 302kValue and at least two evaluations refer to
Mark sets up equation below：
Wherein, θ=[a0,a1,a2,……,ak]T,K+1 is equal to evaluation index
Number, R represents evaluation of estimate, XkRepresent+1 evaluation index of kth, akRepresent the weight of+1 evaluation index of kth.
Above formulaIt is exactly a kind of trade company's evaluation model according to embodiments of the present invention, wherein, R values are higher, table
Show certain more suitable user of corresponding trade company.
According to the explanation of Fig. 2-embodiment illustrated in fig. 3, it will be appreciated by those skilled in the art that the trade company that the present invention is provided is commented
Valency model, data that can constantly based on renewal either in terms of the weight of standard diagrams or evaluation index or survey
Examination data are optimized, so as to for more accurately evaluating over time trade company.
In addition, in a kind of implementation of the embodiment of the present invention, weight akWith evaluation index xkCan be it is configurable,
So, it is easy to related personnel to be neatly adjusted and change for weight and/or evaluation index as needed.For example, operation
Personnel can be adjusted and change to weight and/or evaluation index for different activities, date, realize preferably marketing effect
Really.
The embodiment of the method for the present invention is illustrated above in association with accompanying drawing, the device embodiment to the present invention is entered below
Row explanation.
Fig. 4 A are a kind of block diagrams of trade company's recommendation apparatus according to embodiments of the present invention.Reference picture 4A, trade company's recommendation apparatus
Including data module 42, computing module 44, evaluation module 46 and recommending module 48.It is specifically described below.
In the present embodiment, data module 42 be used to obtaining first data related to targeted customer and with business to be pushed
The second related data of family.Alternatively, in a kind of implementation of the present embodiment, as shown in Figure 4 B, data module 42 includes
First data submodule 422 and the second data submodule 424.
Specifically, the first data submodule 422 is used to perform following operation：The targeted customer is obtained from user's portrait
Hobby data, or, drawn a portrait from the user and obtain the hobby data and data below of the targeted customer
In it is any one or more：Behavior property data, primary attribute data, user's ranked data.Second data submodule 424 is used
In the characteristic that the trade company to be pushed is obtained from trade company's operation platform.
In the present embodiment, computing module 44 is used to determine the business to be pushed according to first data and the second data
The value of the evaluation index at family.
Alternatively, in a kind of implementation of the present embodiment, as shown in Figure 4 C, computing module 44 includes first and calculates son
Module 442, for performing following operation：The hobby data and the characteristic are patterned into the first figure respectively
And second graph, and according to the Duplication of first figure and the second graph, or, according to first figure and institute
The sum of the distance between opposite endpoint on second graph is stated, it is determined that the value of the first evaluation index of reflection matching degree.
Alternatively, in a kind of implementation of the present embodiment, as shown in Figure 4 C, computing module 44 includes second and calculates son
Module 444, the hobby will be removed for the corresponding relation according to default data and evaluation index in first data
Data as corresponding evaluation index value.Exemplarily, the second calculating sub module 444 can be used for the behavior property
Targeted customer described in data searches for the second evaluation index that the number of times of each trade company to be pushed tends to as reflection user behavior
Value；The number of times that targeted customer described in the behavior property data is clicked on to each trade company to be pushed is used as reflection user behavior
The value of the 3rd evaluation index tended to.
In the present embodiment, evaluation module 46 is treated for value and trade company's evaluation model based on the evaluation index to described
Trade company is pushed to be evaluated.Alternatively, in a kind of implementation of the present embodiment, trade company's evaluation model is expressed as following public affairs
Formula：
Wherein, θ=[a0,a1,a2,……,ak]T,K+1 is equal to evaluation index
Number, R represents evaluation of estimate, XkRepresent+1 evaluation index of kth, akRepresent the weight of+1 evaluation index of kth.
The value of evaluation index is substituted into above-mentioned formula and both can obtain evaluation of estimate by evaluation module 46.
In the present embodiment, recommending module 48 is used to be used to the target according to the evaluation result to the trade company to be pushed
Recommend trade company in family.For example, the trade company to be pushed can be ranked up according to the order of R values from big to small, and according to sequence
As a result trade company is recommended to the targeted customer.
Using trade company's recommendation apparatus provided in an embodiment of the present invention, on the one hand, can it is relatively objective and exactly judge " business
Family is if appropriate for user "；On the other hand, it can recommend to be adapted to the trade company of user for user, improve Consumer's Experience；Another further aspect,
Trade company can be showed with the bigger possible user of consumption, improve order volume.Generally speaking, specific discharge can be effectively improved
Produced benefit, greatlys save the flow cost of operation platform.
Fig. 5 is a kind of block diagram of model equipment for setting up trade company's evaluation model according to embodiments of the present invention, can be set up
The trade company's evaluation model referred in Fig. 1-4 illustrated embodiments.As shown in figure 5, the device includes choosing module 52, characteristic module
54th, computing module 56 and model module 58.It is specifically described below.
In the present embodiment, choosing module 52 is used to choose sample of users and the sample business to be recommended to the sample of users
Family.Alternatively, in a kind of implementation of the present embodiment, sample module 52 randomly selects sample of users and sample trade company.
In the present embodiment, characteristic module 54 be used for obtain operation certain time after each sample trade company relative to each
The characteristic value of individual sample of users.Exemplarily, the characteristic value can be the moon of each sample of users in each sample trade company
The averagely amount of placing an order, the per day amount of placing an order, the Zhou Pingjun amounts of placing an order etc..And it is possible to the characteristic value is measured by A/B, or
Person obtains the characteristic value from the device for performing A/B tests.
In the present embodiment, computing module 56 is used for the characteristic value according to each sample trade company relative to each sample of users
The power of the evaluation index is determined relative to the value of the evaluation index of each sample of users with each predetermined sample trade company
Weight.
In the present embodiment, model module 58 is used to set up trade company's evaluation model based on the evaluation index and its weight.
For example, setting up the judgement schematics based on evaluation index and its weight calculation evaluation of estimate.Alternatively, the evaluation index includes reflection
The evaluation index of matching degree, or, in addition to behavior property data, primary attribute data, user's ranked data pair with user
The evaluation index answered.
The device provided using the present embodiment, each sample is determined based on the operation data to sample of users and sample trade company
Trade company and then refers to reference to each evaluation of sample trade company relative to each sample of users relative to the characteristic value of each sample of users
Target value is calculated, and the weighted value of evaluation index can be determined based on real data, so as to evaluation index and its weight
Based on set up accurate evaluation trade company for user if appropriate for trade company's evaluation model.
Alternatively, in a kind of implementation of the present embodiment, as shown in fig. 6, computing module 56 can include substituting into son
Module 562 and calculating sub module 564.Wherein, substituting into submodule 562 is used for each sample trade company relative to each sample of users
Characteristic value and the value of evaluation index substitute into below equation respectively and obtain equation with many unknowns group：
Wherein, θ=[a0,a1,a2,……,ak]T,K+1 is equal to evaluation index
Number, Z represents the characteristic value, XkRepresent+1 evaluation index of kth, akRepresent the weight of+1 evaluation index of kth.
In this implementation, calculating sub module 564 is used to calculate weight a according to the equation with many unknowns groupkValue.
Alternatively, in a kind of implementation of the present embodiment, model module 58 is particularly used in the following processing of progress：
The a calculated according to the computing modulekValue and the evaluation index set up equation below：
Wherein, θ=[a0,a1,a2,……,ak]T,K+1 is equal to evaluation index
Number, R represents evaluation of estimate, XkRepresent+1 evaluation index of kth, akRepresent the weight of+1 evaluation index of kth.
In the implementation, least square method, linear regression (Linear Regression), multinomial can be used
Return the parameter that (Polynomial Regression), ElasticNet recurrence etc. solve equation with many unknowns group.
It will be appreciated by those skilled in the art that the embodiment of the method that provides of the present invention can as device embodiment processing
Logic, the device embodiment that the present invention is provided can be used for the embodiment of the method for realizing the present invention again.Therefore, in device embodiment
In, on handled performed by modules, submodule and executable processing explanation, on related names, term, scope solution
Release, and the description on the particular problem solved, the beneficial effect reached, refer to the corresponding theory in embodiment of the method
Bright, here is omitted.
The Part Methods embodiment and device embodiment according to the present invention are illustrated above in association with accompanying drawing.Under
Face, from initial designs to the angle of the final process for determining target trade company, illustrative explanation is carried out to the present invention.
Exemplified by recommending full name to dispense trade company to the user taken out on platform, in order to realize preferable recommendation effect, recommend
The design of method substantially follows following steps：The first step, determines evaluation index (influence factor)；Second step, statistics；3rd
Step, for the property of each factor, draws different calculation formula；4th step, whole city distributors are issued by A/B tests
Family, so as to obtain test data, carries out parameter fitting；5th step, is carried out public according to the feedback of subsequent user and substantial amounts of data
Formula optimizes.
Step one：Determine influence factor
Among user's portrait, the different dimensions such as primary attribute, user's classification, hobby, behavior property are there is,
This patent only takes hobby and behavior property to make a concrete analysis of, but the content that is covered of this patent not only comprising this two
Individual aspect, but can class release conclusion for all dimensions of user's portrait.
In hobby, suit one's taste emphatically herein, the factor such as price sensitivity, brand is analyzed；In behavior property
In, user is searched for the type dining room frequency herein, the dining room number of times etc. is clicked on as main considerations.
In operation platform, be stored with the related data of whole city dispatching trade company.
Step 2：Statistics
So that Baidu takes out as an example, it has a set of complete user's portrait system, can therefrom take out related to user
Data.In addition, the data related to whole city dispatching trade company can be obtained by operation platform.
Step 3：Draw judgement schematics
On whole city dispense trade company sequencing problem, can essentially be converted into rely on user portrait be ranked up ask
Topic.
In this step kind, the hobby part of user's portrait, can be converted into solution whole city dispatching businessman and user is pre-
Phase consumes the matching degree problem of trade company.Logically, from the point of view of simply, if according to hobby, trade company expected from user and certain
The matching degree of trade company is high, then during recommendation, it should by the in the top of the trade company.Can with figure shown in Fig. 7 come
The expression of image.Wherein, the triangle for being desired for centre of user, and the evaluation and test of trade company is irregular triangle, three tops
Point represents taste, price sensitivity, brand factor respectively.In a kind of exemplary process, if triangle more overlaps explanation
Trade company more meets the taste of user.In another exemplary process, the sum of the distance between respective vertices is calculated, value is smaller,
Then trade company more meets the taste of user.
Three dimensions are only considered herein, so it is a triangle graphically to come out, with the increase of dimension, four
Individual dimension corresponds to quadrangle, and five dimensions correspond to pentagon etc..The method of this use graph-based matching degree can be with
Analogized according to dimension and extended.
In addition, the method for the matching degree that user dispenses trade company with whole city is calculated according to graphically also to be had very in other scenes
Big level of application, such as recommend Reiseziel etc. in travel site to user's Recommendations in shopping website to user,
The problem of polygon is to calculate matching degree can be drawn according to the dimension of influence.
In this step kind, the distance between 2 points of solution will be converted to the problem of solving the matching degree between trade company and user
Problem.If apart from more short so it is considered that trade company all the more matches with user.
Herein the interest matching degree of user and trade company, xi and yi denotation coordinations are represented with dist (X, Y).From the point of view of simple,
Dist (X, Y) is bigger, illustrates the expection for not meeting user more.That is, the expection of user and dist (X, Y) are a kind of negatively correlated passes
System, the inverse with dist (X, Y) is positive correlation.
Furthermore, it is contemplated that the interest of synthetic user and behavior can be evaluated more accurately.Therefore, by dist above
(X, Y), user search for the number of times of whole city dispatching trade company, click on the number of times of whole city dispatching trade company as evaluation criterion.Order is searched
Rope number of times is S, and number of clicks is V, then judgement schematics are：
R=a*S+b*V+c/dist (X, Y)
Step 4：A/B tests are carried out, test data is obtained, formula fitting is carried out.
Taking out on platform, randomly selecting n user and the trade company of m.Most final review of each trade company for each user
The monthly average amount of placing an order in the trade company is represented with the user by point R, can so obtain m*n equation.
Afterwards, for tri- unknown scale parameters of a, b, c, least square method can be used to carry out parameter fitting.Ability
Field technique personnel should be appreciated that for 3 unknown numbers a, b, c, it is only necessary to which 3 equations can be to solve, but this when is very
Easily there is deviation, in order to eliminate the influence of some equation, it is possible to use least square method is unknown to carry out solving optimal 3
Number a, b, c.As follows, C represents dist (X, Y).
According to test data, m*n group test datas can be obtained：
R1=a*S1+b*V1+c/C1
……
Rm*n=a*Sm*n+b*Vm*n+c/Cm*n
For convenience of writing, data are done and once unified, above-mentioned formula can be described as：
Linear model：R=a0*X0+a1*X1+a2*X2Formula (1)
Introduce parameter vector：θ=[a0,a1,a2,]T
Order：Wherein K=1~m*n
Equation can be arranged and be：
According to the theory of least square method, if by YKAs being point inside three-dimensional system of coordinate, it is necessary to the a0 solved,
A1, a2 can be minimum by the distance of point-to-point.Ensure that J is minimum in following formula：
According to mathematical knowledge, if necessary to ensure that J is minimum, derivation just is carried out to above equation, allowing derivative to be 0 just can be with
Minimum value is determined, so that the value of 3 parameters of calculating formula.
For the actual value calculated above, it can generally be solved using spss softwares, spss is to solving polynary first power
The linear regression of journey has good solution, it is only necessary to according to our thinking, corresponding data is ready to excel, led
Entering software can just calculate, and can finally be utilized the parameter that least square method has been returned.It should be noted that this patent is not
Can only be solved with least square method, Optimal Parameters.Also using Linear Regression linear regressions,
Polynomial Regression polynomial regressions, ElasticNet recurrence etc. solve the side that multi head linear equation group seeks parameter
Method.
Step 5：Carry out formula optimization
It is big with the change of data volume, and the evaluation with user to Generalization bounds, more data can be collected and come
The optimization of paired recommended formula.And also mentioned before us, in addition to the hobby of user and behavior, user's portrait
Also more dimensions, all dimensions are added by we, can together Optimal Parameters.
Through the above description of the embodiments, those skilled in the art can be understood that the present invention can be by
The mode of software combination hardware platform is realized.Understood based on such, technical scheme makes tribute to background technology
That offers can be embodied in the form of software product in whole or in part, and the computer software product can be stored in storage and be situated between
In matter, such as ROM/RAM, magnetic disc, CD, including some instructions are to cause a computer equipment (can be individual calculus
Machine, server, smart mobile phone or network equipment etc.) perform described in some parts of each embodiment of the invention or embodiment
Method.
The term and wording used in description of the invention is just to for example, be not intended to constitute restriction.Ability
Field technique personnel should be appreciated that on the premise of the general principle of disclosed embodiment is not departed from, to above-mentioned embodiment
In each details can carry out various change.Therefore, the scope of the present invention is only determined by claim, in the claims, unless
It is otherwise noted, all terms should be understood by the broadest rational meaning.
Claims (24)
1. method is recommended by a kind of trade company, it is characterised in that methods described includes：
Obtain first data related to targeted customer and second data related with trade company to be pushed；
The value of the evaluation index of the trade company to be pushed is determined according to first data and the second data；
Value and trade company's evaluation model based on the evaluation index are evaluated the trade company to be pushed；
Trade company is recommended to the targeted customer according to the evaluation result to the trade company to be pushed.
2. the method as described in claim 1, it is characterised in that the acquisition first data related to targeted customer and with
The second related data of trade company to be pushed include：
Drawn a portrait from user and obtain the hobby data of the targeted customer, or, obtain the target from user portrait
It is any one or more in the hobby data and data below of user：Behavior property data, primary attribute data, use
Family ranked data；And,
The characteristic of the trade company to be pushed is obtained from trade company's operation platform.
3. method as claimed in claim 2, it is characterised in that described described according to first data and the determination of the second data
The value of the evaluation index of trade company to be pushed, including：
The hobby data and the characteristic are patterned into the first figure and second graph respectively；
According to the Duplication of first figure and the second graph, or, according to first figure and second figure
The sum of the distance between opposite endpoint in shape, determines the value of the first evaluation index.
4. method as claimed in claim 2, it is characterised in that described described according to first data and the determination of the second data
The value of the evaluation index of trade company to be pushed, including：
According to default data and evaluation index corresponding relation by first data in addition to the hobby data
Data respectively as corresponding evaluation index value.
5. method as claimed in claim 4, it is characterised in that described described according to first data and the determination of the second data
The value of the evaluation index of trade company to be pushed, including：
The number of times that targeted customer described in the behavior property data is searched for into each trade company to be pushed is used as the second evaluation index
Value；
The number of times that targeted customer described in the behavior property data is clicked on into each trade company to be pushed is used as the 3rd evaluation index
Value.
6. the method as any one of claim 1-5, it is characterised in that trade company's evaluation model is expressed as following public affairs
Formula：
Wherein, θ=[a0,a1,a2,……,ak]T,K+1 is equal to the number of evaluation index
Mesh, R represents evaluation of estimate, XkRepresent+1 evaluation index of kth, akRepresent the weight of+1 evaluation index of kth.
7. method as claimed in claim 6, it is characterised in that the basis is to the evaluation result of the trade company to be pushed to institute
State targeted customer and recommend trade company, including：
The trade company to be pushed is ranked up according to the order of R values from big to small, and used according to ranking results to the target
Recommend trade company in family.
8. a kind of method for setting up trade company's evaluation model, it is characterised in that methods described includes：
Choose sample of users and the sample trade company to be recommended to the sample of users；
Obtain characteristic value of each sample trade company relative to each sample of users after operation certain time；
According to each sample trade company relative to each sample of users characteristic value and each predetermined sample trade company relative to
The value of the evaluation index of each sample of users determines the weight of the evaluation index；
Trade company's evaluation model is set up based on the evaluation index and its weight.
9. method as claimed in claim 8, it is characterised in that the acquisition each sample trade company after operation certain time
Relative to the characteristic value of each sample of users, including：
Obtain monthly average place an order amount of each sample of users measured by A/B in each sample trade company.
10. method as claimed in claim 8, it is characterised in that
The evaluation index includes the evaluation index of the matching degree between reflection trade company and user, or also includes the row with user
For attribute data, primary attribute data or the corresponding evaluation index of user's ranked data.
11. the method as any one of claim 8-10, described to be used according to each sample trade company relative to each sample
The characteristic value at family and each predetermined sample trade company determine institute's commentary relative to the value of the evaluation index of each sample of users
The weight of valency index, including：
Each sample trade company is substituted into below equation respectively relative to the characteristic value of each sample of users and the value of evaluation index
Obtain equation with many unknowns group：
Wherein, θ=[a0,a1,a2,……,ak]T,K+1 is equal to the number of evaluation index
Mesh, Z represents the characteristic value, XkRepresent+1 evaluation index of kth, akRepresent the weight of+1 evaluation index of kth；
Weight a is calculated according to the equation with many unknowns groupkValue.
12. method as claimed in claim 11, it is characterised in that described that trade company is set up based on the evaluation index and its weight
Evaluation model, including：
Based on a calculatedkValue and the evaluation index set up equation below：
Wherein, θ=[a0,a1,a2,……,ak]T,K+1 is equal to the number of evaluation index
Mesh, R represents evaluation of estimate, XkRepresent+1 evaluation index of kth, akRepresent the weight of+1 evaluation index of kth.
13. a kind of trade company's recommendation apparatus, it is characterised in that described device includes：
Data module, for obtaining first data related to targeted customer and second data related with trade company to be pushed；
Computing module, the value of the evaluation index for determining the trade company to be pushed according to first data and the second data；
Evaluation module, is evaluated the trade company to be pushed for the value based on the evaluation index and trade company's evaluation model；
Recommending module, for recommending trade company to the targeted customer according to the evaluation result to the trade company to be pushed.
14. device as claimed in claim 13, it is characterised in that the data module includes：
First data submodule, for performing following operation：Drawn a portrait from user and obtain the hobby data of the targeted customer,
Or, any one or many in the hobby data and data below for obtaining the targeted customer of being drawn a portrait from the user
：Behavior property data, primary attribute data, user's ranked data；
Second data submodule, the characteristic for obtaining the trade company to be pushed from trade company's operation platform.
15. device as claimed in claim 14, it is characterised in that the computing module includes：
First calculating sub module, for performing following operation：By the hobby data and characteristic difference figure
The first figure and second graph are turned to, and according to the Duplication of first figure and the second graph, or, according to described
On first figure and the second graph the distance between opposite endpoint and, determine the value of the first evaluation index.
16. device as claimed in claim 14, it is characterised in that the computing module includes：
Second calculating sub module, institute will be removed for the corresponding relation according to default data and evaluation index in first data
Hobby data are stated as the value of corresponding evaluation index.
17. device as claimed in claim 16, it is characterised in that second calculating sub module is used for：
The number of times that targeted customer described in the behavior property data is searched for into each trade company to be pushed is used as the second evaluation index
Value；
The number of times that targeted customer described in the behavior property data is clicked on into each trade company to be pushed is used as the 3rd evaluation index
Value.
18. the device as any one of claim 13-17, it is characterised in that trade company's evaluation model be expressed as with
Lower formula：
Wherein, θ=[a0,a1,a2,……,ak]T,K+1 is equal to the number of evaluation index
Mesh, R represents evaluation of estimate, XkRepresent+1 evaluation index of kth, akRepresent the weight of+1 evaluation index of kth.
19. device as claimed in claim 18, it is characterised in that
The recommending module is used to be ranked up the trade company to be pushed according to the order of R values from big to small, and according to sequence
As a result trade company is recommended to the targeted customer.
20. a kind of device for setting up trade company's evaluation model, it is characterised in that described device includes：
Module is chosen, for choosing sample of users and the sample trade company to be recommended to the sample of users；
Characteristic module, for obtaining feature of each sample trade company relative to each sample of users after operation certain time
Value；
Computing module, for the characteristic value and each predetermined sample according to each sample trade company relative to each sample of users
This trade company determines the weight of the evaluation index relative to the value of the evaluation index of each sample of users；
Model module, for setting up trade company's evaluation model based on the evaluation index and its weight.
21. device as claimed in claim 20, it is characterised in that the characteristic module is used to obtain to be measured by A/B
Monthly average place an order amount of each sample of users in each sample trade company.
22. device as claimed in claim 20, it is characterised in that
The evaluation index includes the evaluation index of the matching degree between reflection trade company and user, or also includes the row with user
For attribute data, primary attribute data or the corresponding evaluation index of user's ranked data.
23. the device as any one of claim 20-22, it is characterised in that the computing module includes：
Submodule is substituted into, for each sample trade company to be divided relative to the characteristic value of each sample of users and the value of evaluation index
Not Dai Ru below equation obtain equation with many unknowns group：
Wherein, θ=[a0,a1,a2,……,ak]T,K+1 is equal to the number of evaluation index
Mesh, Z represents the characteristic value, XkRepresent+1 evaluation index of kth, akRepresent the weight of+1 evaluation index of kth；
Calculating sub module, for calculating weight a according to the equation with many unknowns groupkValue.
24. device as claimed in claim 23, it is characterised in that the model module is used for：
The a calculated according to the computing modulekValue and the evaluation index set up equation below：
Wherein, θ=[a0,a1,a2,……,ak]T,K+1 is equal to the number of evaluation index
Mesh, R represents evaluation of estimate, XkRepresent+1 evaluation index of kth, akRepresent the weight of+1 evaluation index of kth.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610743575.1A CN107123011A (en) | 2016-08-26 | 2016-08-26 | Trade company recommends method, sets up the method and relevant apparatus of trade company's evaluation model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610743575.1A CN107123011A (en) | 2016-08-26 | 2016-08-26 | Trade company recommends method, sets up the method and relevant apparatus of trade company's evaluation model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107123011A true CN107123011A (en) | 2017-09-01 |
Family
ID=59717819
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610743575.1A Pending CN107123011A (en) | 2016-08-26 | 2016-08-26 | Trade company recommends method, sets up the method and relevant apparatus of trade company's evaluation model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107123011A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108053262A (en) * | 2017-12-28 | 2018-05-18 | 北京小度信息科技有限公司 | Data push method and device |
| CN109325806A (en) * | 2018-09-20 | 2019-02-12 | 北京小度信息科技有限公司 | A kind of processing method and processing device of user information |
| CN109697636A (en) * | 2018-12-27 | 2019-04-30 | 拉扎斯网络科技（上海）有限公司 | A kind of trade company's recommended method, trade company's recommendation apparatus, electronic equipment and medium |
| CN110110222A (en) * | 2019-04-12 | 2019-08-09 | 保定市大为计算机软件开发有限公司 | A kind of target object determines method, apparatus and computer storage medium |
| CN112184258A (en) * | 2020-09-21 | 2021-01-05 | 杭州干脆面君网络科技有限公司 | Take-out food monitoring system |
| CN112381349A (en) * | 2020-10-14 | 2021-02-19 | 浪潮软件股份有限公司 | Configuration method for terminal code scanning quality evaluation |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102542490A (en) * | 2011-12-27 | 2012-07-04 | 纽海信息技术（上海）有限公司 | Commodity recommendation method based on model matching |
| CN102902691A (en) * | 2011-07-28 | 2013-01-30 | 上海拉手信息技术有限公司 | Recommending method and recommending system |
| CN105574216A (en) * | 2016-03-07 | 2016-05-11 | 达而观信息科技（上海）有限公司 | Personalized recommendation method and system based on probability model and user behavior analysis |
| CN105677831A (en) * | 2016-01-04 | 2016-06-15 | 拉扎斯网络科技（上海）有限公司 | Method and device for determining recommended commercial tenants |
-
2016
- 2016-08-26 CN CN201610743575.1A patent/CN107123011A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102902691A (en) * | 2011-07-28 | 2013-01-30 | 上海拉手信息技术有限公司 | Recommending method and recommending system |
| CN102542490A (en) * | 2011-12-27 | 2012-07-04 | 纽海信息技术（上海）有限公司 | Commodity recommendation method based on model matching |
| CN105677831A (en) * | 2016-01-04 | 2016-06-15 | 拉扎斯网络科技（上海）有限公司 | Method and device for determining recommended commercial tenants |
| CN105574216A (en) * | 2016-03-07 | 2016-05-11 | 达而观信息科技（上海）有限公司 | Personalized recommendation method and system based on probability model and user behavior analysis |
Non-Patent Citations (1)
| Title |
|---|
| 陈晨等: "基于本地插件的个性化搜索研究", 《计算机应用与软件》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108053262A (en) * | 2017-12-28 | 2018-05-18 | 北京小度信息科技有限公司 | Data push method and device |
| CN109325806A (en) * | 2018-09-20 | 2019-02-12 | 北京小度信息科技有限公司 | A kind of processing method and processing device of user information |
| CN109697636A (en) * | 2018-12-27 | 2019-04-30 | 拉扎斯网络科技（上海）有限公司 | A kind of trade company's recommended method, trade company's recommendation apparatus, electronic equipment and medium |
| CN110110222A (en) * | 2019-04-12 | 2019-08-09 | 保定市大为计算机软件开发有限公司 | A kind of target object determines method, apparatus and computer storage medium |
| CN110110222B (en) * | 2019-04-12 | 2021-03-16 | 保定市大为计算机软件开发有限公司 | Target object determination method and device and computer storage medium |
| CN112184258A (en) * | 2020-09-21 | 2021-01-05 | 杭州干脆面君网络科技有限公司 | Take-out food monitoring system |
| CN112381349A (en) * | 2020-10-14 | 2021-02-19 | 浪潮软件股份有限公司 | Configuration method for terminal code scanning quality evaluation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107123011A (en) | Trade company recommends method, sets up the method and relevant apparatus of trade company's evaluation model | |
| Fung et al. | An intelligent hybrid system for customer requirements analysis and product attribute targets determination | |
| CN107562818A (en) | Information recommendation system and method | |
| Jannach et al. | Recommending hotels based on multi-dimensional customer ratings | |
| CN108550052A (en) | Brush list detection method and system based on user behavior data feature | |
| CN103440283B (en) | The deficiency system of a kind of measuring point data and method of filling a vacancy | |
| CN106203773A (en) | A kind of method and device of automatic management employee | |
| CN105931068A (en) | Cardholder consumption figure generation method and device | |
| CN107862566A (en) | A kind of Method of Commodity Recommendation and system | |
| CN102081774A (en) | Card-raising identification method and system | |
| CN106651418A (en) | Method of recommending add-on item for special offer when spending enough by e-business | |
| CN106469392A (en) | Select and recommend to show the method and device of object | |
| CN107679945A (en) | Method for establishing consumer objects recommended models and associated method and device | |
| CN107067282B (en) | Consumer product rebate sale marketing management system and use method thereof | |
| Saura et al. | Retail innovativeness: Importance of ICT and impact on consumer behaviour | |
| Mesforoush et al. | Customer profitability segmentation for SMEs case study: network equipment company | |
| CN104867037A (en) | Data processing method and device of figure characteristics | |
| CN110163683A (en) | Value user's key index determines method, advertisement placement method and device | |
| CN110349678A (en) | A kind of Chinese medicine marketing system and its working method based on the positive and negative sequence rule digging of effective | |
| Kaur et al. | A pythagorean fuzzy approach for sustainable supplier selection using TODIM | |
| CN109919728A (en) | A kind of Method of Commodity Recommendation in difference quotient city | |
| CN112597398A (en) | Medicine recommendation model application method and system | |
| CN109615460A (en) | Gather the selection method and selection system of single commodity | |
| Halibas et al. | Developing trends in showrooming, webrooming, and omnichannel shopping behaviors: Performance analysis, conceptual mapping, and future directions | |
| Liu et al. | The Value of Multi-Dimensional Rating System: An Information Transfer View |
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 | ||
| CB02 | Change of applicant information |
Address after: Building N3, building 12, No. 27, Jiancai Chengzhong Road, Haidian District, Beijing 100096 Applicant after: Beijing Xingxuan Technology Co.,Ltd. Address before: 100085 Beijing, Haidian District on the road to the information on the ground floor of the 1 to the 3 floor of the 2 floor, room 11, 202 Applicant before: Beijing Xiaodu Information Technology Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170901 |
|
| RJ01 | Rejection of invention patent application after publication |