CN106447472A - Buying behavior-based recommendation method and device - Google Patents
Buying behavior-based recommendation method and device Download PDFInfo
- Publication number
- CN106447472A CN106447472A CN201611090075.9A CN201611090075A CN106447472A CN 106447472 A CN106447472 A CN 106447472A CN 201611090075 A CN201611090075 A CN 201611090075A CN 106447472 A CN106447472 A CN 106447472A
- Authority
- CN
- China
- Prior art keywords
- user
- order amount
- valid order
- behavior
- store
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0254—Targeted advertisements based on statistics
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- 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]
- G06Q30/0631—Item recommendations
Abstract
The invention relates to a buying behavior-based recommendation method and device. The method comprises the following steps of: counting the first effective order quantity generated by advertising within unit time; counting the second effective order quantity generated by malls within the unit time; and comparing the first effective order quantity with the second effective order quantity to obtain a buying interest sequence table of a user, wherein if the first effective order quantity is greater than the second effective order quantity, the advertising channel is superior to the malls in the buying interest sequence table of the user; if the first effective order quantity is less than the second effective order quantity, the malls are superior to the advertising channel in the buying interest sequence table of the user. The invention has the following beneficial effects: an interesting promotion way is delivered to the user according to the behavior situation of the user, then an advertising platform can select a more reasonable promotion way based on the buying behaviors of the user, and various promotion resources are utilized more reasonably.
Description
Technical field
The present embodiments relate to multimedia information field, more particularly, to a kind of recommendation based on purchasing behavior
Method and device.
Background technology
Generally, for same advertising platform, advertisement that different sponsors makes can indiscriminate when specific
Between spend and thrown in, no matter current user group's quantity, user group's personal characteristics and user group etc. are so that in advertisement
Cannot be effectively to user group's advertisement in release time, the effect of advertisement putting does not far reach patronage user is desired and pushes away
Wide purpose.
At present, some TV programme are while live, in order to be able to allow spectators user preferably to participate in into, typically permissible
The live of program is participated in by " shaking " function of such as certain letter on other communication platforms, the experience of spectators user obtains
It is substantially improved, during participation activity, sponsor can be utilized this function to throw in advertisement or throw in certain program of channel
Put advertisement.
For same user, user is generally only interested in a type of popularization resource, such as when user is formed
After custom only browse advertisements and select store is directly ignored, or only store is browsed on the contrary or is selected store
Carry out purchasing behavior and ignore advertisement, continue to throw in the very big wave that ignored popularization type can cause this popularization resource type
Take, be unfavorable for the abundant realization of the promotional value of advertising platform, there is presently no the method that can solve the problem that this problem or dress
Put appearance.
Content of the invention
The present invention provides a kind of recommendation method and device based on purchasing behavior, to realize according to user in a certain type
The behavior situation showing in the way of promotion determines this user way of promotion interested, makes the way of promotion more reasonable, improves
Promote the utilization rate of resource.
In a first aspect, embodiments providing a kind of recommendation method based on purchasing behavior, methods described includes:
Count in the unit interval by throwing in the first valid order amount that advertisement generates;
Statistics was passed through to throw in the second valid order amount that store generates within the described unit interval;
Relatively described first valid order amount and described second valid order amount, draw the purchase sequence of interest table of user;
When described first valid order amount is more than described second valid order amount, throw in the purchase sequence of interest table of user
Put advertising channel to be better than throwing in store;
When described first valid order amount is less than described second valid order amount, throw in the purchase sequence of interest table of user
Put store to be better than throwing in advertising channel.
In conjunction with the other hand, in a kind of possible embodiment on the other hand, methods described also includes:
The type of merchandise being related to after adline to user browse advertisements and user's entrance store counts, and obtains
To statistical result;
Determine the behavior situation of described user according to described statistical result;
Described user participate in program interaction when, the behavior situation according to described user to described user recommend comprise described in
The advertisement of behavior situation or store.
In conjunction with the other hand, in a kind of possible embodiment on the other hand, described true according to described statistical result
The behavior situation of fixed described user, including:
Obtain source data from the end that logs in of described user;
Obtain the user property of described user, historical behavior and browse feature from described source data;
In conjunction with the user property of described user, historical behavior and browse the behavior situation that feature determines described user.
In conjunction with the other hand, in a kind of possible embodiment on the other hand, when the purchase interest sequence drawing user
During list, methods described also includes:
When described first valid order amount is more than described second valid order amount, determine the current business throwing in store
Category type participates in the low frequency type of merchandise that frequency is less than certain predetermined frequency;
Renewal is replaced to each described low frequency type of merchandise;
When described first valid order amount is less than described second valid order amount, determine wide in current input advertisement
Accuse type and participate in the low frequency adline that frequency is less than certain predetermined frequency;
Renewal is replaced to each described low frequency adline.
In conjunction with the other hand, in a kind of possible embodiment on the other hand, methods described also includes:
Determine described user behavior situation maintain the time;
When described maintain the time more than a Preset Time when, fixing behavior situation, to recommend to described user every time
Adline that described behavior situation comprises and the type of merchandise that store is related to.
Second aspect, present invention also offers a kind of recommendation apparatus based on purchasing behavior, described device includes:
First statistical module, passes through in the unit interval to throw in the first valid order amount that advertisement generates for counting;
Second statistical module, passed through to throw in the second valid order that store generates for statistics within the described unit interval
Amount;
Comparison module, for relatively described first valid order amount and described second valid order amount, draws the purchase of user
Buy sequence of interest table;
First putting module, for when described first valid order amount be more than described second valid order amount when, user's
Buy and throw in advertising channel in sequence of interest table better than input store;
Second putting module, for when described first valid order amount be less than described second valid order amount when, user's
Buy and throw in store in sequence of interest table better than input advertising channel.
In conjunction with the other hand, in a kind of possible embodiment on the other hand, described device also includes:
Statistic submodule, for entering, to the adline of user browse advertisements and user, the commodity being related to behind store
Type is counted, and obtains statistical result;
Behavior situation determination sub-module, for determining the behavior situation of described user according to described statistical result;
Select a recommending module, for when described user participates in program interaction, the behavior situation according to described user is to institute
State advertisement or the store that user's recommendation comprises described behavior situation.
In conjunction with another aspect, in a kind of possible embodiment on the other hand, described behavior situation determination sub-module
Also it is used for:
Obtain source data from the end that logs in of described user;
Obtain the user property of described user, historical behavior and browse feature from described source data;
In conjunction with the user property of described user, historical behavior and browse the behavior situation that feature determines described user.
In conjunction with the other hand, in a kind of possible embodiment on the other hand, described device also includes:
Low frequency commodity determination sub-module, for when described first valid order amount be more than described second valid order amount when,
Determine that the current type of merchandise throwing in store participates in the low frequency type of merchandise that frequency is less than certain predetermined frequency;
First replacement update module, for being replaced renewal to each described low frequency type of merchandise;
Low frequency advertisement determination sub-module, for when described first valid order amount be less than described second valid order amount when,
Determine that the current adline throwing in advertisement participates in the low frequency adline that frequency is less than certain predetermined frequency;
Second replacement update module, for being replaced renewal to each described low frequency adline.
In conjunction with the other hand, in a kind of possible embodiment on the other hand, described device also includes:
Time determining module, for determine described user behavior situation maintain the time;
Stuck-module, for when described maintain the time more than a Preset Time when, fixing behavior situation, with every time to
Described user recommends adline that described behavior situation comprises and the type of merchandise that store is related to.
The present invention passes through to count in the unit interval by throwing in advertisement and throwing in the valid order amount that store generates
Contrast, show that the behavior situation of this user preferentially tends to any way of promotion, according further to the behavior situation of user
Throw in the way of promotion interested to this user so that advertising platform can the purchasing behavior based on user carry out more rational
The input of the way of promotion, solves and can only promote in one way to all users at present and cause poor total of promotion effect
Amount, makes all kinds of popularization resources be more reasonably utilized.
It should be appreciated that above general description and detailed description hereinafter are only exemplary and explanatory, not
The present invention can be limited.
Brief description
Accompanying drawing herein is merged in description and constitutes the part of this specification, shows the enforcement meeting the present invention
Example, and be used for explaining the principle of the present invention together with description.
Fig. 1 is a kind of flow chart of the recommendation method based on purchasing behavior according to an exemplary embodiment.
Fig. 2 is the flow chart according to particular type recommended advertisements or store according to an exemplary embodiment.
Fig. 3 is the flow chart that a kind of behavior situation according to an exemplary embodiment obtains.
Fig. 4 is a kind of entire block diagram of the recommendation apparatus based on purchasing behavior according to an exemplary embodiment.
Fig. 5 is the composition frame chart of the statistical module according to an exemplary embodiment.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that, in order to just
Part related to the present invention rather than entire infrastructure is illustrate only in description, accompanying drawing.
It should be mentioned that some exemplary embodiments are described as before exemplary embodiment is discussed in greater detail
The process described as flow chart or method.Although each step is described as in flow chart the process of order, therein permitted
Multi-step can be implemented concurrently, concomitantly or simultaneously.Additionally, the order of each step can be rearranged, when its operation
When completing, described process can be terminated, it is also possible to have the other steps being not included in accompanying drawing.Process can correspond to
In method, function, code, subroutine, subprogram etc..
The present invention relates to a kind of recommendation method and device based on purchasing behavior, it mainly applies to the field of advertisement putting
Scape, for example, carry out the popularization in advertisement or store in software, carry out the popularization in advertisement or store etc. in TV programme, it is thought substantially
Think be:Count the quantity generating valid order thrown in advertisement and thrown in store respectively, judge to show that this user's is effective
The behavior situation bought, the behavior situation measuring out the customer group in this region by its respective valid order is to be partial to
Advertisement or store, and determine that advertising platform throws in advertisement or preferential input business to this user priority according to this behavior situation
City.
The present embodiment is applicable to carry out in the display situation of advertisement in the advertising platform with Central Control Module, should
Method can be executed by Central Control Module, and wherein this central controller can be realized by software and/or hardware, typically
Ground can be integrated in advertising platform, and Fig. 1 is a kind of stream of recommendation method based on purchasing behavior of exemplary embodiment of the present
Journey schematic diagram, in conjunction with shown in Fig. 1, methods described may particularly include following steps:
In step 110, by throwing in the first valid order amount that advertisement generates in statistics one unit interval;
When needing the behavior situation of user is counted, a unit interval such as one can be extracted from historical record
In the time of the moon, this user passes through to click on the first valid order amount that the advertisement thrown in generates.
In the step 120, statistics was passed through to throw in the second valid order amount that store generates within the described unit interval;
In a kind of feasible embodiment, can extract from historical record in the time of a such as one month unit interval
This user passes through to click on the second valid order amount that the store thrown in generates.
In step 130, compare described first valid order amount and described second valid order amount, draw the purchase of user
Sequence of interest table;
Described first valid order amount is all represented with described second valid order amount in the way of numerical value, by comparing two numbers
Value size can draw the purchase sequence of interest table of user, buying in sequence of interest table according to the way of promotion not in user
With it can include but is not limited to above advertisement and two kinds of the store way of promotion.
In step 140, when described first valid order amount is more than described second valid order amount, the purchase of user is emerging
Throw in advertising channel in interesting sequence table to be better than throwing in store;
When the actual purchase behavior number of times that user is produced based on advertisement is more than the actual purchase producing based on store
During behavior number of times, that is, described first valid order amount is more than described second valid order amount then it represents that user is more likely to pass through
Browse advertisements and implement purchasing behavior, now will preferentially to this user throw in advertisement.
In step 150, when described first valid order amount is less than described second valid order amount, the purchase of user is emerging
Throw in store in interesting sequence table to be better than throwing in advertising channel.
When the actual purchase behavior number of times that user is produced based on store is more than the actual purchase producing based on advertisement
During behavior number of times, that is, described second valid order amount is more than described first valid order amount then it represents that user is more likely to pass through
Browse store and implement purchasing behavior, now preferentially will throw in store to this user.
By the method for the present invention, by counting the number generating valid order thrown in advertisement and thrown in store respectively
Amount, is judged to draw the behavior situation of effective purchase of this user, is measured out in this region by its respective valid order
The behavior situation of customer group is to be partial to advertisement or store, and determines that advertising platform is excellent to this user according to this behavior situation
First throw in advertisement or preferential store of throwing in so that advertising platform can be according to the behavior situation of each user to corresponding user
Select to be best suited for the way of promotion of this user, thus greatly improving the promotion effect of promotion media.
In another kind of implement scene of exemplary embodiment of the present, methods described also includes having been browsed according to user
Adline or the type of merchandise carry out the process of the recommendation of more hommization, as shown in Fig. 2 this process comprises the steps:
In step 210, the commodity class that the adline to user browse advertisements and user are related to after entering store
Type is counted, and obtains statistical result;
At least include the user classification of the particular content of advertisement and user in browse advertisements in described statistical result to exist
Browse the product type of the specific product in store during store, such as advertisement belongs to the popularization advertisement of furniture type, the type of merchandise belongs to
Commodity in electronic equipment type.
In a step 220, the behavior situation of described user is determined according to described statistical result;
In a kind of feasible embodiment, such as advertisement belongs to the popularization advertisement of furniture type, and the type of merchandise belongs to electricity
The commodity of sub- equipment type, then can determine that the behavior situation of described user is to be bought furniture or electronics device in the near future
Material.
In step 230, when described user participates in program interaction, the behavior situation according to described user is to described user
Recommend advertisement or the store comprising described behavior situation.
When user is detected again and logging in program interaction platform and participate in program interaction, then described behavior situation is to described
User recommends to comprise advertisement or the store of described behavior situation, and specifically recommends specific product type to this user, for example to
This user recommends furniture, electronic equipment.
By the method for the present invention, after the behavior situation drawing user, can be according to statistical result to corresponding use
Family recommends to include advertisement or the store of specific product type, so that the advertising resource in advertising platform or store resource
User's request can be met, to reach significantly more efficient promotion effect.
In another kind of implement scene of exemplary embodiment of the present, described described use is determined according to described statistical result
The behavior situation at family, as shown in figure 3, this process may include following steps:
In the step 310, obtain source data from the end that logs in of described user;
In step 320, obtain the user property of described user, historical behavior from described source data and browse spy
Levy;
Described source data is logging in the behavior record with regard to user of end record, browsing record, behavior in described user
Mode, userspersonal information, browse property parameters etc..
In a step 330, in conjunction with the user property of described user, historical behavior and browse feature and determine described user's
Behavior situation.
With regard to obtaining the data message for situation correlation of going on a journey in the personal data of user from source data, for example, at least wrap
Include the user property of described user, historical behavior and browse feature, it is drawn by the data message related to behavior situation
Behavior situation belongs to one kind of big data perception measuring and calculating.
By the method for the present invention, by obtaining the source data with regard to user from user side and then analyzing the behavior state of user
Gesture, can make behavior situation reflect the recent actual wishes of user to the full extent so that in the input medium to this user
When the way of promotion being best suited for this user can be selected to be promoted, reach good promotion effect.
In another kind of implement scene of exemplary embodiment of the present, when drawing the purchase sequence of interest table of user,
Methods described also includes:
When described first valid order amount is more than described second valid order amount, determine the current business throwing in store
Category type participates in the low frequency type of merchandise that frequency is less than certain predetermined frequency;
Renewal is replaced to each described low frequency type of merchandise;
When described first valid order amount is less than described second valid order amount, determine wide in current input advertisement
Accuse type and participate in the low frequency adline that frequency is less than certain predetermined frequency;
Renewal is replaced to each described low frequency adline.
By the method for the present invention, when the way of promotion of one of which cannot meet the demand of user, then this kind is pushed away
Low frequency type in wide mode is replaced renewal, again attracts user to replace the product type after renewal or COS
Attention, to make another kind of or several ways of promotion reach better pushing away on the popularization of user's request meeting further
Wide effect.
In another kind of implement scene of exemplary embodiment of the present, methods described also includes:
Determine described user behavior situation maintain the time;
When described maintain the time more than a Preset Time when, fixing behavior situation, to recommend to described user every time
Adline that described behavior situation comprises and the type of merchandise that store is related to.
Every a Preset Time, the behavior situation of described user is detected, judge that its behavior situation time becomes
Change, determine described user behavior situation maintain the time more than a Preset Time when, then behavior situation can be considered as use
The behavioural habits at family, and then make behavior situation be fixed as the behavioural habits of user, and be accustomed to every to user according to the behavior
Select more to meet the way of promotion of user behavior custom when secondary recommended advertisements, store or other service, reached better
Promotion effect.
Fig. 4 is that a kind of signaling process figure/structure of recommendation apparatus based on purchasing behavior provided in an embodiment of the present invention is shown
It is intended to, this device can be realized by software and/or hardware, is usually integrated in advertising platform, can be by based on purchasing behavior
Recommendation method is realizing.As illustrated, the present embodiment can be based on above-described embodiment, there is provided one kind is based on purchasing behavior
Recommendation apparatus, its mainly include the first statistical module 410, the second statistical module 420, comparison module 430, first throw in mould
Block 440 and the second putting module 450.
First statistical module 410 therein, effective by throwing in the first of advertisement generation in the unit interval for counting
Order volume;
Second statistical module 420 therein, passed through to throw in second that store generates for statistics within the described unit interval
Valid order amount;
Comparison module 430 therein, for relatively described first valid order amount and described second valid order amount, draws
The purchase sequence of interest table of user;
First putting module 440 therein, for being more than described second valid order amount when described first valid order amount
When, throw in advertising channel in the purchase sequence of interest table of user and be better than throwing in store;
Second putting module 450 therein, for being less than described second valid order amount when described first valid order amount
When, throw in store in the purchase sequence of interest table of user and be better than throwing in advertising channel.
In another kind of implement scene of exemplary embodiment of the present, as shown in figure 5, described device also includes:
Statistic submodule 510, is related to behind store for entering to the adline of user browse advertisements and user
The type of merchandise is counted, and obtains statistical result;
Behavior situation determination sub-module 520, for determining the behavior situation of described user according to described statistical result;
Select a recommending module 530, for described user participate in program interaction when, the behavior situation according to described user to
Described user recommends advertisement or the store comprising described behavior situation.
In another kind of implement scene of exemplary embodiment of the present, described behavior situation determination sub-module also by with
In:
Obtain source data from the end that logs in of described user;
Obtain the user property of described user, historical behavior and browse feature from described source data;
In conjunction with the user property of described user, historical behavior and browse the behavior situation that feature determines described user.
In another kind of implement scene of exemplary embodiment of the present, described device also includes:
Low frequency commodity determination sub-module, for when described first valid order amount be more than described second valid order amount when,
Determine that the current type of merchandise throwing in store participates in the low frequency type of merchandise that frequency is less than certain predetermined frequency;
First replacement update module, for being replaced renewal to each described low frequency type of merchandise;
Low frequency advertisement determination sub-module, for when described first valid order amount be less than described second valid order amount when,
Determine that the current adline throwing in advertisement participates in the low frequency adline that frequency is less than certain predetermined frequency;
Second replacement update module, for being replaced renewal to each described low frequency adline.
In another kind of implement scene of exemplary embodiment of the present, described device also includes:
Time determining module, for determine described user behavior situation maintain the time;
Stuck-module, for when described maintain the time more than a Preset Time when, fixing behavior situation, with every time to
Described user recommends adline that described behavior situation comprises and the type of merchandise that store is related to.
The recommendation apparatus based on purchasing behavior providing in above-described embodiment can perform institute in any embodiment in the present invention
The recommendation method based on purchasing behavior providing, possesses the execution corresponding functional module of the method and beneficial effect, not above-mentioned
The ins and outs describing in detail in embodiment, can be found in the recommendation based on purchasing behavior provided in any embodiment of the present invention
Method.
It will be appreciated that, the present invention also extends to the computer program being suitable for putting the invention into practice, particularly
Computer program on carrier or in carrier.Program can be compiled with source code, object code, code intermediate source and such as part
The form of the object code of the form translated, or it is suitable for shape used in the realization according to the method for the present invention with any other
Formula.Also it will be noted that, such program is likely to be of many different frame design.For example, realize the side according to the present invention
Functional program code of method or system may be subdivided into one or more subroutine.
For being obvious for technical personnel in these subroutine intermediate distribution functional many different modes.
Subroutine can be collectively stored in an executable file, thus forming self-contained program.Such executable file can
To include computer executable instructions, such as processor instruction and/or interpreter instruction (for example, Java interpreter instruction).Can
Alternatively, one or more or all subroutines of subroutine may be stored at least one external library file, and
And statically or dynamically (for example at runtime) links with mastery routine.Mastery routine contains at least one of subroutine
At least one call.Subroutine can also be included to function call each other.It is related to the embodiment bag of computer program
Include the computer executable instructions of each step of process step corresponding at least one of illustrated method method.These refer to
Order can be subdivided into subroutine and/or be stored in one or more possible static state or the file of dynamic link.
The embodiment that another is related to computer program include corresponding in illustrated system and/or product at least
The computer executable instructions of each device in the device of.These instructions can be subdivided into subroutine and/or be stored
In the file of one or more possible static state or dynamic link.
The carrier of computer program can be any entity or the device that can deliver program.For example, carrier can wrap
Containing storage medium, such as (ROM such as CDROM or quasiconductor ROM) or magnetic recording media (such as floppy disk or hard disk).Enter
One step ground, carrier can be the carrier that can transmit, such as electricity or optical signalling, its can via cable or optical cable, or
Person passes through radio or other means transmission.When program is embodied as such signal, carrier can be by such cable
Or device forms.Alternatively, carrier can be the integrated circuit being wherein embedded with program, and described integrated circuit is suitable for holding
Row correlation technique, or for used by the execution of correlation technique.
Should be noted that, embodiment mentioned above is to illustrate the present invention, rather than limits the present invention, and this
The technical staff in field is possible to design many alternate embodiments, without departing from scope of the following claims.In power
During profit requires, any reference markss being placed between round parentheses are not to be read as being limitations on claims.Verb " bag
Include " and its paradigmatic using being not excluded for depositing of element in addition to those recorded in the claims or step
?.Article " one " before element or " one " are not excluded for the presence of a plurality of such elements.The present invention can pass through
Including the hardware of several visibly different assemblies, and realized by properly programmed computer.Enumerating several devices
In device claim, several in these devices can be embodied by the same item of hardware.In mutually different appurtenance
Profit states in requiring that the fact merely of some measures is not intended that the combination of these measures can not be used to benefit.
If desired, difference in functionality discussed herein can execute with different order execution and/or simultaneously with one another.
In addition if desired, one or more functions described above can be optional or can be combined.
If desired, each step is not limited to the execution sequence in each embodiment, different step as discussed above
Can execute with different order execution and/or simultaneously with one another.Additionally, in other embodiments, one or many described above
Individual step can be optional or can be combined.
Although various aspects of the invention are given in the independent claim, the other side of the present invention includes being derived from
The feature of described embodiment and/or have independent claims the dependent claims of feature combination, and not only
It is the combination being clearly given in claim.
It should be noted herein that although the foregoing describing the example embodiment of the present invention, but these descriptions are not
Should be understood in a limiting sense.On the contrary, can carry out several changing and modifications will without departing from such as appended right
The scope of the present invention defined in asking.
Will be appreciated by those skilled in the art that each module in the device of the embodiment of the present invention can be with general meter
Calculate device to realize, each module can concentrate in single computing device or the group of networks of computing device composition, and the present invention is real
Apply the method that the device in example corresponds in previous embodiment, it can be realized by executable program code it is also possible to lead to
The mode crossing integrated circuit combination, to realize, therefore the invention is not limited in specific hardware or software and its combination.
Will be appreciated by those skilled in the art that each module in the device of the embodiment of the present invention can be with general shifting
Realizing, each module can concentrate in single mobile terminal or the device combination of mobile terminal composition dynamic terminal, the present invention
Device in embodiment corresponds to the method in previous embodiment, and it can be realized by editing executable program code,
Can be realized by way of integrated circuit combination, therefore the invention is not limited in specific hardware or software and its knot
Close.
Note, above are only exemplary embodiment and institute's application technology principle of the present invention.Those skilled in the art can manage
Solution, the invention is not restricted to specific embodiment described here, can carry out various obvious changes for a person skilled in the art
Change, readjust and substitute without departing from protection scope of the present invention.Therefore although being entered to the present invention by above example
Go and be described in further detail, but the present invention has been not limited only to above example, without departing from the inventive concept,
Other Equivalent embodiments more can also be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (10)
1. a kind of recommendation method based on purchasing behavior is it is characterised in that methods described includes:
Count in the unit interval by throwing in the first valid order amount that advertisement generates;
Statistics was passed through to throw in the second valid order amount that store generates within the described unit interval;
Relatively described first valid order amount and described second valid order amount, draw the purchase sequence of interest table of user;
When described first valid order amount is more than described second valid order amount, throw in wide in the purchase sequence of interest table of user
Accuse channel to be better than throwing in store;
When described first valid order amount is less than described second valid order amount, in the purchase sequence of interest table of user, throw in business
City is better than throwing in advertising channel.
2. method according to claim 1 is it is characterised in that methods described also includes:
The type of merchandise being related to after adline to user browse advertisements and user's entrance store counts, and is united
Meter result;
Determine the behavior situation of described user according to described statistical result;
When described user participates in program interaction, the behavior situation according to described user recommends to comprise described behavior to described user
The advertisement of situation or store.
3. method according to claim 2 is it is characterised in that the described row determining described user according to described statistical result
For situation, including:
Obtain source data from the end that logs in of described user;
Obtain the user property of described user, historical behavior and browse feature from described source data;
In conjunction with the user property of described user, historical behavior and browse the behavior situation that feature determines described user.
4. method according to claim 2 is it is characterised in that when drawing the purchase sequence of interest table of user, described side
Method also includes:
When described first valid order amount is more than described second valid order amount, determine the current commodity class thrown in store
Type participates in the low frequency type of merchandise that frequency is less than certain predetermined frequency;
Renewal is replaced to each described low frequency type of merchandise;
When described first valid order amount is less than described second valid order amount, determine the current commercial paper thrown in advertisement
Type participates in the low frequency adline that frequency is less than certain predetermined frequency;
Renewal is replaced to each described low frequency adline.
5. according to the arbitrary described method of Claims 2 or 3 it is characterised in that methods described also includes:
Determine described user behavior situation maintain the time;
When described maintain the time more than a Preset Time when, fixing behavior situation, with recommend to described user every time described
Adline that behavior situation comprises and the type of merchandise that store is related to.
6. a kind of recommendation apparatus based on purchasing behavior are it is characterised in that described device includes:
First statistical module, passes through in the unit interval to throw in the first valid order amount that advertisement generates for counting;
Second statistical module, passed through to throw in the second valid order amount that store generates for statistics within the described unit interval;
Comparison module, for relatively described first valid order amount and described second valid order amount, show that the purchase of user is emerging
Interesting sequence table;
First putting module, for when described first valid order amount be more than described second valid order amount when, the purchase of user
Throw in advertising channel in sequence of interest table to be better than throwing in store;
Second putting module, for when described first valid order amount be less than described second valid order amount when, the purchase of user
Throw in store in sequence of interest table to be better than throwing in advertising channel.
7. device according to claim 6 is it is characterised in that described device also includes:
Statistic submodule, for entering, to the adline of user browse advertisements and user, the type of merchandise being related to behind store
Counted, obtained statistical result;
Behavior situation determination sub-module, for determining the behavior situation of described user according to described statistical result;
Select a recommending module, for when described user participates in program interaction, the behavior situation according to described user is to described use
Advertisement or the store comprising described behavior situation is recommended at family.
8. device according to claim 7 is it is characterised in that described behavior situation determination sub-module is also used for:
Obtain source data from the end that logs in of described user;
Obtain the user property of described user, historical behavior and browse feature from described source data;
In conjunction with the user property of described user, historical behavior and browse the behavior situation that feature determines described user.
9. device according to claim 7 is it is characterised in that described device also includes:
Low frequency commodity determination sub-module, for when described first valid order amount is more than described second valid order amount, determining
The current type of merchandise thrown in store participates in the low frequency type of merchandise that frequency is less than certain predetermined frequency;
First replacement update module, for being replaced renewal to each described low frequency type of merchandise;
Low frequency advertisement determination sub-module, for when described first valid order amount is less than described second valid order amount, determining
The current adline thrown in advertisement participates in the low frequency adline that frequency is less than certain predetermined frequency;
Second replacement update module, for being replaced renewal to each described low frequency adline.
10. according to the arbitrary described device of claim 7 or 8 it is characterised in that described device also includes:
Time determining module, for determine described user behavior situation maintain the time;
Stuck-module, for when described maintain the time more than a Preset Time when, fixing behavior situation, with every time to described
User recommends the type of merchandise that the adline that comprises of described behavior situation and store are related to.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611090075.9A CN106447472A (en) | 2016-11-30 | 2016-11-30 | Buying behavior-based recommendation method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611090075.9A CN106447472A (en) | 2016-11-30 | 2016-11-30 | Buying behavior-based recommendation method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106447472A true CN106447472A (en) | 2017-02-22 |
Family
ID=58222591
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611090075.9A Withdrawn CN106447472A (en) | 2016-11-30 | 2016-11-30 | Buying behavior-based recommendation method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106447472A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109087178A (en) * | 2018-08-28 | 2018-12-25 | 清华大学 | Method of Commodity Recommendation and device |
CN109255682A (en) * | 2018-09-11 | 2019-01-22 | 广东布田电子商务有限公司 | A kind of mixed recommendation system towards electronic business system |
CN109559058A (en) * | 2018-12-12 | 2019-04-02 | 广州蓝深科技有限公司 | A kind of e-commerce user behavioral data analytical technology based on cloud computing |
CN110099363A (en) * | 2019-03-28 | 2019-08-06 | 苏州德沃雄氏信息科技有限公司 | A kind of marketing advertising platform data distributing method and system based on consumption big data |
CN111523033A (en) * | 2020-04-22 | 2020-08-11 | 北京京东振世信息技术有限公司 | Information pushing method and device based on browsing records and related equipment |
-
2016
- 2016-11-30 CN CN201611090075.9A patent/CN106447472A/en not_active Withdrawn
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109087178A (en) * | 2018-08-28 | 2018-12-25 | 清华大学 | Method of Commodity Recommendation and device |
CN109087178B (en) * | 2018-08-28 | 2021-05-18 | 清华大学 | Commodity recommendation method and device |
CN109255682A (en) * | 2018-09-11 | 2019-01-22 | 广东布田电子商务有限公司 | A kind of mixed recommendation system towards electronic business system |
CN109559058A (en) * | 2018-12-12 | 2019-04-02 | 广州蓝深科技有限公司 | A kind of e-commerce user behavioral data analytical technology based on cloud computing |
CN110099363A (en) * | 2019-03-28 | 2019-08-06 | 苏州德沃雄氏信息科技有限公司 | A kind of marketing advertising platform data distributing method and system based on consumption big data |
CN110099363B (en) * | 2019-03-28 | 2022-04-05 | 苏州德沃元驰信息科技有限公司 | Marketing advertisement platform data distribution method and system based on consumption big data |
CN111523033A (en) * | 2020-04-22 | 2020-08-11 | 北京京东振世信息技术有限公司 | Information pushing method and device based on browsing records and related equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10185971B2 (en) | Systems and methods for planning and executing an advertising campaign targeting TV viewers and digital media viewers across formats and screen types | |
Webster et al. | Ratings analysis: Theory and practice | |
CN106447472A (en) | Buying behavior-based recommendation method and device | |
Lin et al. | The integration of value-based adoption and expectation–confirmation models: An example of IPTV continuance intention | |
JP6125591B2 (en) | Method and apparatus for improved media content evaluation system | |
CN103390238B (en) | System and method for configuring advertisement | |
CN103295148B (en) | The method and apparatus generating and realizing data model | |
Mirbagheri et al. | Mobile marketing communication: Learning from 45 popular cases for campaign designing | |
CN107820105B (en) | Method and device for providing data object information | |
TM et al. | Just one more episode: Exploring consumer motivations for adoption of streaming services | |
CN102906779A (en) | Auctioning segmented avails | |
Tuunainen et al. | Mobile service platforms: Comparing nokia ovi and apple app store with the iisin model | |
CN106570731A (en) | Method and device for delivering advertisement | |
CN107749000A (en) | Platform returns the instant processing method and processing device of existing information | |
CN106358057A (en) | Advertisement putting method and device | |
Pandey et al. | Survey on revenue management in media and broadcasting | |
CN110060085A (en) | It is a kind of to parse method, system and the equipment being distributed under advertising objective crowd line | |
CN104765778A (en) | Method and device for providing information to be transmitted based on user behaviors | |
CN106507147A (en) | The processing method and processing device of advertisement | |
US20150363817A1 (en) | Method and System for Online Audience Development and Advertising | |
KR20130103237A (en) | Method for providing on-line advertisement and the advertisement server thereof | |
US20200111069A1 (en) | Method, apparatus, and system for providing a creative over a network | |
CN108027929A (en) | Determined according to Consumer Preferences and play the media management system and method for the commercial film of all marketable products | |
CN110796465B (en) | Resource display equipment determining method, advertisement display screen determining method and device | |
CN106779823A (en) | The display methods and device of advertisement |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20170222 |