CN109872211A - A kind of method and apparatus of object recommendation - Google Patents
A kind of method and apparatus of object recommendation Download PDFInfo
- Publication number
- CN109872211A CN109872211A CN201711259195.1A CN201711259195A CN109872211A CN 109872211 A CN109872211 A CN 109872211A CN 201711259195 A CN201711259195 A CN 201711259195A CN 109872211 A CN109872211 A CN 109872211A
- Authority
- CN
- China
- Prior art keywords
- recommendation
- user
- recommendation weight
- consumption cycle
- order
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of method and apparatus of object recommendation, are related to field of computer technology.One specific embodiment of this method includes: to obtain the consumption cycle for the object that user has bought；In the period end neighborhood of a point of consumption cycle, recommended is come with the recommendation weight of the object after increasing in chronological order.Which overcomes prior art centers to have the characteristics that periodically to reproduce because not accounting for object, and the technical issues of causing the buying experience of user to reduce, and then reach the technical effect of the in due course object for recommending user's needs, improve the purpose of user experience.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of method and apparatus of object recommendation.
Background technique
With the continuous development of internet, more and more users' selection is done shopping on the net.User passes through browser
Access internet, so that it may easily select object required for oneself.Internet can carry out pair to user in many cases,
The recommendation of elephant, for example, object similar or associated to the object can be recommended to it after user has purchased a certain object,
For another example, the object of new restocking, the object of discounting, fast-selling object etc. can also be recommended to user.By the recommendation of object, one
The sales volume of object can be improved in aspect, on the other hand, actively recommend can to avoid user because frequently search search and generate
Unnecessary searching request mitigates the burden of Website server.
In realizing process of the present invention, at least there are the following problems in the prior art for inventor's discovery:
For current object recommendation system, seldom in view of object has the characteristic periodically consumed, such as rice, food
There is the object periodically used with salt etc., when user is after an object service life, there is no next for system
Recommend the class object to user in a service life, reduces user experience.
Summary of the invention
In view of this, the embodiment of the present invention provides a kind of method and apparatus of object recommendation, it is able to solve the prior art
Recommender system does not account for the service life of object, and the problem of cause user experience to reduce.
To achieve the above object, according to an aspect of an embodiment of the present invention, a kind of method of object recommendation is provided.
A kind of method of object recommendation of the embodiment of the present invention includes: to obtain the consumption cycle for the object that user has bought；
In the period end neighborhood of a point of consumption cycle, recommended is come with the recommendation weight of the object after increasing in chronological order.
According to one preferred embodiment of the present invention, the step of increasing the recommendation weight of object includes: according to preset increasing
Function determines the recommendation weight of object, and wherein the independent variable of increasing function is the time, and dependent variable is the recommendation weight of object.
According to one preferred embodiment of the present invention, increasing function is
Wherein,Indicate the recommendation weight of object,For constant, t1At the time of expression starts to recommend, t2It indicates to terminate to recommend
At the time of.
According to one preferred embodiment of the present invention, before the step of obtaining the consumption cycle for the object that user has bought, also
Include: the placing an order the moment of placing an order of multiple history for obtaining object, determines in multiple moment that place an order between each group adjacent moment that places an order
Time interval, to obtain multiple time intervals；If the undulating value between multiple time intervals is less than preset fluctuation threshold,
Using the average value of multiple time intervals as the consumption cycle of object.
According to one preferred embodiment of the present invention, the step of recommendation weight of the object after increasing in chronological order further include:
Using Pearson correlation coefficient, browsing object associated with object is determined from the historical viewings object of user；Temporally
Sequence increases object and browses the recommendation weight of object.
To achieve the above object, according to another aspect of an embodiment of the present invention, a kind of device of object recommendation is provided.
A kind of device of object recommendation of the embodiment of the present invention includes: acquisition module, pair bought for obtaining user
The consumption cycle of elephant；Recommending module, in the period end neighborhood of a point of consumption cycle, with pair after increasing in chronological order
The recommendation weight of elephant carrys out recommended.
According to one preferred embodiment of the present invention, recommending module is used for: determining pushing away for object according to preset increasing function
Weight is recommended, wherein the independent variable of increasing function is the time, and dependent variable is the recommendation weight of object.
According to one preferred embodiment of the present invention, increasing function is
Wherein,Indicate the recommendation weight of object,For constant, t1At the time of expression starts to recommend, t2It indicates to terminate to push away
At the time of recommending.
According to one preferred embodiment of the present invention, further include processing module, be used for: the multiple history for obtaining object places an order down
Single moment determines the time interval in multiple moment that place an order between each group adjacent moment that places an order, to obtain multiple time intervals；If
Undulating value between multiple time intervals is less than preset fluctuation threshold, then using the average value of multiple time intervals as object
Consumption cycle.
According to one preferred embodiment of the present invention, recommending module is also used to: Pearson correlation coefficient is utilized, from the history of user
Browsing object associated with object is determined in browsing object；Increase object in chronological order and browses the advowson of object
Weight.
A kind of electronic equipment of object recommendation of the embodiment of the present invention includes: one or more processors；Storage device is used
In storing one or more programs, when one or more of programs are executed by one or more of processors, so that described
The method that one or more processors realize the object recommendation of the embodiment of the present invention.
To achieve the above object, another aspect according to an embodiment of the present invention, provides a kind of computer-readable medium.
A kind of computer-readable medium of the embodiment of the present invention, is stored thereon with computer program, and described program is processed
The method of the object recommendation of the embodiment of the present invention is realized when device executes.
One embodiment in foregoing invention has the following advantages that or the utility model has the advantages that because using the periodicity of object disappears
The characteristics of expense, is added to the technological means in recommended method, so overcome prior art center has because not accounting for object
The characteristics of periodically reproducing, and the technical issues of cause the buying experience of user to reduce, and then reach in due course and recommend user
The technical effect of the object needed, improves user experience.For example, in some period sex objects of user's purchase, in user
Into this class object Buying Cycle when, gradually enhance the recommendation of such period sex object, for a long time, be conducive to cultivate
The buying habit of user.
Further effect possessed by above-mentioned non-usual optional way adds hereinafter in conjunction with specific embodiment
With explanation.
Detailed description of the invention
Attached drawing for a better understanding of the present invention, does not constitute an undue limitation on the present invention.Wherein:
Fig. 1 is the schematic diagram of the main flow of the method for object recommendation according to an embodiment of the present invention；
Fig. 2 is the flow diagram of object recommendation according to an embodiment of the present invention；
Fig. 3 is the characteristic schematic diagram of increasing function according to an embodiment of the present invention；
Fig. 4 is the schematic diagram of the main modular of the device of object recommendation according to an embodiment of the present invention；
Fig. 5 is that the embodiment of the present invention can be applied to exemplary system architecture figure therein；
Fig. 6 is adapted for the structural representation of the computer system for the terminal device or server of realizing the embodiment of the present invention
Figure.
Specific embodiment
Below in conjunction with attached drawing, an exemplary embodiment of the present invention will be described, including the various of the embodiment of the present invention
Details should think them only exemplary to help understanding.Therefore, those of ordinary skill in the art should recognize
It arrives, it can be with various changes and modifications are made to the embodiments described herein, without departing from scope and spirit of the present invention.Together
Sample, for clarity and conciseness, descriptions of well-known functions and structures are omitted from the following description.
Fig. 1 is the schematic diagram of the main flow of the method for object recommendation according to an embodiment of the present invention, as shown in Figure 1, this
A kind of method of object recommendation of inventive embodiments mainly includes the following steps:
Step S101: the consumption cycle for the object that user has bought is obtained.Consumption cycle by the way that object is added, which is used as, to push away
The foundation and factor recommended, increase the dimension of recommendation, so that recommendation is more humanized, improve user experience.
In the embodiment of the present invention, before the step of obtaining the consumption cycle for the object that user has bought, further includes: obtain
It takes what the multiple history of object placed an order to place an order the moment, determines between the time in multiple moment that place an order between each group adjacent moment that places an order
Every (adjacent being placed an order the moment for one group constantly with adjacent place an order twice), to obtain multiple time intervals；If between multiple times
Undulating value between is less than preset fluctuation threshold and (is judged the fluctuation and stabilization of multiple time intervals with the undulating value
Property), then using the average value of multiple time intervals as the consumption cycle of object.For example, being directed to user A, analysis user A purchase is same
Single time under multiple history of one object or same class object is determined between multiple times according to the time single under multiple history
Every, analyze between multiple time intervals fluctuation (interval under i.e. each history between single time is stable, so that it is determined that with
Family A has the behavior periodically bought to the object or the class object), it is preset if the undulating value between multiple time intervals is less than
Fluctuation threshold, it is determined that multiple time interval average value (after the values of multiple time intervals is added divided by it is multiple when
Between the quantity that is spaced) be exactly Buying Cycle namely consumption cycle of the user A for the object or the class object.
Step S102: in the period end neighborhood of a point of consumption cycle, with the recommendation of the object after increasing in chronological order
Weight carrys out recommended.According to the consumption cycle of the object of acquisition, in the case where closing on consumption cycle, can reinforce to the object
Recommendation weight, namely recommend intensity.Specifically, being recommended since at the time of closing on consumption cycle, then gradually reinforce pushing away
Weight is recommended, is shown it preferentially or in the top, until user buys or reaches certain moment after consumption cycle, and
And the advowson at the moment weighs to maximum value, the recommendation weight for the object of then just decaying rapidly or is directly reduced to zero, tool
The implementation of body will in subsequent elaboration exhaustive presentation, repeated no more in this, certainly, the way of recommendation of the invention not only includes
Preferential displaying or in the top can also include that APP message pushes, SMS push etc. way of recommendation.
In embodiments of the present invention, the step of increasing the recommendation weight of object includes: according to preset increasing letter
Number determines the recommendation weight of object, and wherein the independent variable of increasing function is the time, and dependent variable is the recommendation weight of object.By default
Increasing function make recommend weight step up, in the present invention, increasing function is
Wherein,Indicate the recommendation weight of object,For constant, t1At the time of expression starts to recommend, t2It indicates to terminate to recommend
At the time of, [t1,t2] indicate object the recommendation phase.It should be pointed out that being only a preferred increasing letter shown by the present invention
Number, as long as the purpose of the present invention can be achieved in the increasing function for enabling to the recommendation weight of object to step up.
In embodiments of the present invention, the step of recommendation weight of the object after increasing in chronological order further include: benefit
With Pearson correlation coefficient, browsing object associated with object is determined from the historical viewings object of user；It is temporally suitable
Sequence increases object and browses the recommendation weight of object.It is true in the object that the historical viewings of user are crossed by Pearson correlation coefficient
Similar or associated browsing object is made, and is recommended simultaneously, at user option range is increased, further increases
The usage experience of user.
Fig. 2 is the flow diagram of object recommendation according to an embodiment of the present invention, as shown in Fig. 2, the solution of the present invention stream
Journey includes the following steps:
Step S201: for different users, whether the object for analyzing user's purchase has periodicity, and determines user
The consumption cycle of the object of purchase.Recommended due to the characteristics of the present invention be directed to object is periodically consumed, so being directed to
User group be all that some old users (if it is new user, need to obtain the user in advance in history elsewhere
Buy information), to be analyzed for acquiring enough data.
Specifically, being directed to some user A, first has to analysis user A and buy under the same object or same class object
Single time, by the interval of lower single time, to judge this user to the object or the class object with the presence or absence of period purchase
Behavior, if M times of the user time interval bought is not much different, (undulating value of i.e. each time interval is lower than preset fluctuation threshold
Value), it is determined that the average value of each time interval is exactly that this user (consumes the Buying Cycle of the object or the class object
Period).
Step S202: in the case where reaching the consumption cycle of period sex object A, recommender system steps up periodically right
As the recommendation weight of A, until user buys.After having determined user to the Buying Cycle of object, when user is in the next Buying Cycle
Front and back a period of time in when can carry out same object or related object recommendation (be carved into the Buying Cycle from some time before the Buying Cycle
Certain moment afterwards is the recommendation phase).If user does not buy in time within the recommendation phase, increase recommendation weight, for example, push
APP message sends SMS, adjusts the recommendation order of the class object in recommendation list etc. and is easier to obtain beneficial to user
The method of relevant recommendation information, until user buys.
It should be pointed out that some associated objects can be recommended while recommending object.In the present invention
Embodiment in, can use Pearson correlation coefficient to determine associated object, from the historical viewings object of user really
Make browsing object associated with object；Then increase object in chronological order and browse the recommendation weight of object.Specifically,
Pearson correlation coefficient is as follows:
Using the object properties of period sex object as vector X, using the object properties of browsing object as object vector Y,
In, Y is [Y1, Y2, Y3 ...], carries out correlation calculations using Pearson correlation coefficient, correlation is determined from object vector
Then browsing object corresponding to the object properties of connection is recommended correlation browsing object together with period sex object.Such as: one
The attribute vector of object can be expressed as [category, brand, price, color ...] etc., have tool certainly in specific operation
The quantized values of body, then the object properties of period sex object can be expressed as the vector of one group of data composition, target object
It can be expressed as the vector of one group of data composition of same dimension.
Determine that the principle of related browsing object can be with using Pearson correlation coefficient are as follows: seek two co sinus vector included angle values
Absolute value, value is bigger, and correlation is stronger.Related coefficient between two vectors is higher, from a vector go to predict another to
The accuracy of amount is higher, and equally, when related coefficient is higher, the co-variation part between vector is also more.Therefore, from wherein one
The variation of a vector just would know that the variation of another vector.Further, if the related coefficient between two vectors is 1
Or -1, then the value of object vector Y can be gone to know by vector X.When related coefficient is 0, X and two variable of Y are irrelevant.It is specific right
It should be related to as follows:
When the value of X increases, when Y also increases, positive correlation, related coefficient is between 0.00 and 1.00；
When the value of X reduces, when Y also reduces, positive correlation, related coefficient is between 0.00 and 1.00；
When the value of X increases, and Y reduces, negative correlativing relation, related coefficient is between -1.00 and 0.00；
When the value of X reduces, and Y increases, negative correlativing relation, related coefficient is between -1.00 and 0.00；
To sum up, the absolute value of related coefficient is bigger, and vector X and the correlation of object vector Y are stronger, and related coefficient is closer
In 0, vector X and the object vector Y degree of correlation are weaker.
Step S203: after user's purchase, the recommendation weight to period sex object A is reduced.If the user within the recommendation phase
This object is successfully bought, then the recommendation weight for the class object of decaying rapidly or is directly reduced to zero；If user after the recommendation phase
Again without purchase, it is determined that user may have purchased the object otherwise, then the recommendation for the class object of decaying rapidly
Weight is directly reduced to zero.Specific implementation is as shown in figure 3, the characteristic that Fig. 3 is increasing function according to an embodiment of the present invention is shown
It is intended to, at the time of expression starts to recommend, at the time of indicating to terminate to recommend, indicates the period endpoint of consumption cycle, indicate consumption week
The period end neighborhood of a point of phase, the neighborhood are the recommendation phase of object or related object.Using increasing function since constantly gradually
It improves and recommends weight, recommend weight until user decays rapidly after buying within the recommendation phase or be directly reduced to zero, or when reaching
After the recommendation weight maximum value at quarter, user still recommends weight without the same decaying rapidly of purchase or is directly reduced to zero.
It should be pointed out that, in the Buying Cycle next time of the object, repeating the above steps after above-mentioned steps.
The method of object recommendation according to an embodiment of the present invention can be seen that because using periodically consuming object
Feature is added to the technological means in recommended method, so overcoming prior art center because not accounting for object with the period
Property the characteristics of reproducing, and the technical issues of cause the buying experience of user to reduce, and then reach in due course and recommend user's needs
Object technical effect, improve user experience.For example, entering in some period sex objects of user's purchase in user
When the Buying Cycle of this class object, gradually enhance the recommendation of such period sex object, for a long time, is conducive to cultivate user
Buying habit.
Fig. 4 is the schematic diagram of the main modular of the device of object recommendation according to an embodiment of the present invention, as shown in figure 4, this
The device 400 of the object recommendation of inventive embodiments, which specifically includes that, obtains module 401 and recommending module 402.Wherein:
Module 401 is obtained, for obtaining the consumption cycle for the object that user has bought；Recommending module 402, for consuming
In the period end neighborhood of a point in period, recommended is come with the recommendation weight of the object after increasing in chronological order.Pass through increase
The consumption cycle of object improves user experience so that recommendation is more humanized as the dimension recommended.
Preferably, recommending module 402 of the invention is used for: the advowson of object is determined according to preset increasing function
Weight, wherein the independent variable of increasing function is the time, and dependent variable is the recommendation weight of object.
Increasing function is in the preferred embodiment of the present invention
Wherein,Indicate the recommendation weight of object,For constant, t1At the time of expression starts to recommend, t2It indicates to terminate to recommend
At the time of.
In addition, being used for the invention also includes processing module (not shown): the multiple history for obtaining object places an order down
Single moment determines the time interval in multiple moment that place an order between each group adjacent moment that places an order, to obtain multiple time intervals；If
Undulating value between multiple time intervals is less than preset fluctuation threshold, then using the average value of multiple time intervals as object
Consumption cycle.
Recommending module 402 is also used in the preferred embodiment of the present invention: Pearson correlation coefficient is utilized, from the history of user
Browsing object associated with object is determined in browsing object；Increase object in chronological order and browses the advowson of object
Weight.
From the above, it can be seen that because being added in recommended method using by periodical the characteristics of consuming of object
Technological means so overcome prior art center has the characteristics that periodically to reproduce because not accounting for object, and causes to use
The technical issues of buying experience at family reduces, and then reach the technical effect of the in due course object for recommending user's needs, it improves
User experience.For example, in some period sex objects of user's purchase, when user enters the Buying Cycle of this class object
It waits, gradually enhances the recommendation of such period sex object, for a long time, be conducive to the buying habit for cultivating user.
Fig. 5 is shown can be using the object recommendation method of the embodiment of the present invention or the exemplary system of object recommendation device
Framework 500.
As shown in figure 5, system architecture 500 may include terminal device 501,502,503, network 504 and server 505.
Network 504 between terminal device 501,502,503 and server 505 to provide the medium of communication link.Network 504 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 501,502,503 and be interacted by network 504 with server 505, to receive or send out
Send message etc..Various telecommunication customer end applications, such as the application of shopping class, net can be installed on terminal device 501,502,503
(merely illustrative) such as the application of page browsing device, searching class application, instant messaging tools, mailbox client, social platform softwares.
Terminal device 501,502,503 can be the various electronic equipments with display screen and supported web page browsing, packet
Include but be not limited to smart phone, tablet computer, pocket computer on knee and desktop computer etc..
Server 505 can be to provide the server of various services, such as utilize terminal device 501,502,503 to user
The shopping class website browsed provides the back-stage management server (merely illustrative) supported.Back-stage management server can be to reception
To the data such as object information inquiry request analyze etc. processing, and (such as target push information, object are believed by processing result
Breath -- merely illustrative) feed back to terminal device.
It should be noted that object recommendation method provided by the embodiment of the present invention is generally executed by server 505, accordingly
Ground, object recommendation device are generally positioned in server 505.
It should be understood that the number of terminal device, network and server in Fig. 5 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
Below with reference to Fig. 6, it illustrates the computer systems 600 for the terminal device for being suitable for being used to realize the embodiment of the present invention
Structural schematic diagram.Terminal device shown in Fig. 6 is only an example, function to the embodiment of the present invention and should not use model
Shroud carrys out any restrictions.
As shown in fig. 6, computer system 600 includes central processing unit (CPU) 601, it can be read-only according to being stored in
Program in memory (ROM) 602 or be loaded into the program in random access storage device (RAM) 603 from storage section 608 and
Execute various movements appropriate and processing.In RAM 603, also it is stored with system 600 and operates required various programs and data.
CPU 601, ROM 602 and RAM 603 are connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to always
Line 604.
I/O interface 605 is connected to lower component: the importation 606 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 607 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 608 including hard disk etc.；
And the communications portion 609 of the network interface card including LAN card, modem etc..Communications portion 609 via such as because
The network of spy's net executes communication process.Driver 610 is also connected to I/O interface 605 as needed.Detachable media 611, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 610, in order to read from thereon
Computer program be mounted into storage section 608 as needed.
Particularly, disclosed embodiment, the process described above with reference to flow chart may be implemented as counting according to the present invention
Calculation machine software program.For example, embodiment disclosed by the invention includes a kind of computer program object comprising be carried on computer
Computer program on readable medium, the computer program include the program code for method shown in execution flow chart.?
In such embodiment, which can be downloaded and installed from network by communications portion 609, and/or from can
Medium 611 is dismantled to be mounted.When the computer program is executed by central processing unit (CPU) 601, system of the invention is executed
The above-mentioned function of middle restriction.
It should be noted that computer-readable medium shown in the present invention can be computer-readable signal media or meter
Calculation machine readable storage medium storing program for executing either the two any combination.Computer readable storage medium for example can be --- but not
Be limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.Meter
The more specific example of calculation machine readable storage medium storing program for executing can include but is not limited to: have the electrical connection, just of one or more conducting wires
Taking formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only storage
Device (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device,
Or above-mentioned any appropriate combination.In the present invention, computer readable storage medium can be it is any include or storage journey
The tangible medium of sequence, the program can be commanded execution system, device or device use or in connection.And at this
In invention, computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to: wireless, electric wire, optical cable, RF etc. are above-mentioned
Any appropriate combination.
Flow chart and block diagram in attached drawing are illustrated according to the system of various embodiments of the invention, method and computer journey
The architecture, function and operation in the cards of ordered pair elephant.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of above-mentioned module, program segment or code include one or more
Executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in box
The function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practical
On can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it wants
It is noted that the combination of each box in block diagram or flow chart and the box in block diagram or flow chart, can use and execute rule
The dedicated hardware based systems of fixed functions or operations is realized, or can use the group of specialized hardware and computer instruction
It closes to realize.
Being described in module involved in the embodiment of the present invention can be realized by way of software, can also be by hard
The mode of part is realized.Described module also can be set in the processor, for example, can be described as: a kind of processor packet
It includes and obtains module and recommending module.Wherein, the title of these modules does not constitute the limit to the module itself under certain conditions
It is fixed.
As on the other hand, the present invention also provides a kind of computer-readable medium, which be can be
Included in equipment described in above-described embodiment；It is also possible to individualism, and without in the supplying equipment.Above-mentioned calculating
Machine readable medium carries one or more program, when said one or multiple programs are executed by the equipment, makes
Obtaining the equipment includes: to obtain the consumption cycle for the object that user has bought；In the period end neighborhood of a point of consumption cycle, to press
The recommendation weight of object after time sequencing increase carrys out recommended.
Technical solution according to an embodiment of the present invention, because being added to recommendation using by periodical the characteristics of consuming of object
Technological means in method, so overcome prior art center has the characteristics that periodically to reproduce because not accounting for object,
And the technical issues of causing the buying experience of user to reduce, and then reach the technology effect of the in due course object for recommending user's needs
Fruit improves user experience.For example, entering the purchase of this class object in user in some period sex objects of user's purchase
When period, gradually enhance the recommendation of such period sex object, for a long time, is conducive to the buying habit for cultivating user.
Above-mentioned specific embodiment, does not constitute a limitation on the scope of protection of the present invention.Those skilled in the art should be bright
It is white, design requirement and other factors are depended on, various modifications, combination, sub-portfolio and substitution can occur.It is any
Made modifications, equivalent substitutions and improvements etc. within the spirit and principles in the present invention, should be included in the scope of the present invention
Within.
Claims (12)
1. a kind of method of object recommendation characterized by comprising
Obtain the consumption cycle for the object that user has bought；
In the period end neighborhood of a point of the consumption cycle, come with the recommendation weight of the object after increasing in chronological order
Recommended.
2. the method according to claim 1, wherein the step of increasing the recommendation weight of the object includes:
The recommendation weight of the object is determined according to preset increasing function, wherein the independent variable of the increasing function is the time,
Dependent variable is the recommendation weight of the object.
3. according to the method described in claim 2, it is characterized in that, the increasing function is
Wherein,Indicate the recommendation weight of the object,For constant, t1At the time of expression starts to recommend, t2It indicates to terminate to recommend
At the time of.
4. the method according to claim 1, wherein the consumption cycle for the object bought in the acquisition user
The step of before, further includes:
Obtain that the multiple history of the object places an order places an order the moment, when determining that each group is adjacent lower single in multiple moment that place an order
Time interval between quarter, to obtain multiple time intervals；
If the undulating value between the multiple time interval is less than preset fluctuation threshold, with the flat of the multiple time interval
Consumption cycle of the mean value as the object.
5. the method according to claim 1, wherein the recommendation weight of the object after increasing in chronological order
The step of further include:
Using Pearson correlation coefficient, browsing pair associated with the object is determined from the historical viewings object of user
As；
Increase the recommendation weight of the object and the browsing object in chronological order.
6. a kind of device of object recommendation characterized by comprising
Module is obtained, for obtaining the consumption cycle for the object that user has bought；
Recommending module, in the period end neighborhood of a point of the consumption cycle, with described right after increasing in chronological order
The recommendation weight of elephant carrys out recommended.
7. device according to claim 6, which is characterized in that the recommending module is used for:
The recommendation weight of the object is determined according to preset increasing function, wherein the independent variable of the increasing function is the time,
Dependent variable is the recommendation weight of the object.
8. device according to claim 7, which is characterized in that the increasing function is
Wherein,Indicate the recommendation weight of the object,For constant, t1At the time of expression starts to recommend, t2It indicates to terminate to recommend
At the time of.
9. device according to claim 6, which is characterized in that further include processing module, be used for:
Obtain that the multiple history of the object places an order places an order the moment, when determining that each group is adjacent lower single in multiple moment that place an order
Time interval between quarter, to obtain multiple time intervals；
If the undulating value between the multiple time interval is less than preset fluctuation threshold, with the flat of the multiple time interval
Consumption cycle of the mean value as the object.
10. device according to claim 6, which is characterized in that the recommending module is also used to:
Using Pearson correlation coefficient, browsing pair associated with the object is determined from the historical viewings object of user
As；
Increase the recommendation weight of the object and the browsing object in chronological order.
11. a kind of electronic equipment of object recommendation characterized by comprising
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now such as method as claimed in any one of claims 1 to 5.
12. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that described program is held by processor
Such as method as claimed in any one of claims 1 to 5 is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711259195.1A CN109872211A (en) | 2017-12-04 | 2017-12-04 | A kind of method and apparatus of object recommendation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711259195.1A CN109872211A (en) | 2017-12-04 | 2017-12-04 | A kind of method and apparatus of object recommendation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109872211A true CN109872211A (en) | 2019-06-11 |
Family
ID=66915511
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711259195.1A Pending CN109872211A (en) | 2017-12-04 | 2017-12-04 | A kind of method and apparatus of object recommendation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109872211A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111586169A (en) * | 2020-05-07 | 2020-08-25 | 苏宁云计算有限公司 | Commodity marketing information pushing method and system |
| CN112819555A (en) * | 2019-11-15 | 2021-05-18 | 北京沃东天骏信息技术有限公司 | Article recommendation method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104599160A (en) * | 2015-02-06 | 2015-05-06 | 腾讯科技（深圳）有限公司 | Commodity recommendation method and commodity recommendation device |
| CN104657336A (en) * | 2015-03-10 | 2015-05-27 | 湖北大学 | Personal recommendation algorithm based on semi-cosine function |
| CN105761094A (en) * | 2015-01-05 | 2016-07-13 | Sk普兰尼特有限公司 | System And Method For Recommending Product Purchased Periodically, Apparatus Therefore |
| CN106294758A (en) * | 2016-09-23 | 2017-01-04 | 华南师范大学 | Collaborative recommendation method based on the change of user cognition degree |
| KR101726520B1 (en) * | 2014-12-08 | 2017-04-12 | 주식회사 엘지씨엔에스 | Personalized recommendation method, system and computer-readable record medium |
| CN107292645A (en) * | 2016-03-31 | 2017-10-24 | 壹贰叁叁购（厦门）信息技术有限公司 | A kind of Method of Commodity Recommendation of dynamic self-adapting |
-
2017
- 2017-12-04 CN CN201711259195.1A patent/CN109872211A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101726520B1 (en) * | 2014-12-08 | 2017-04-12 | 주식회사 엘지씨엔에스 | Personalized recommendation method, system and computer-readable record medium |
| CN105761094A (en) * | 2015-01-05 | 2016-07-13 | Sk普兰尼特有限公司 | System And Method For Recommending Product Purchased Periodically, Apparatus Therefore |
| CN104599160A (en) * | 2015-02-06 | 2015-05-06 | 腾讯科技（深圳）有限公司 | Commodity recommendation method and commodity recommendation device |
| CN104657336A (en) * | 2015-03-10 | 2015-05-27 | 湖北大学 | Personal recommendation algorithm based on semi-cosine function |
| CN107292645A (en) * | 2016-03-31 | 2017-10-24 | 壹贰叁叁购（厦门）信息技术有限公司 | A kind of Method of Commodity Recommendation of dynamic self-adapting |
| CN106294758A (en) * | 2016-09-23 | 2017-01-04 | 华南师范大学 | Collaborative recommendation method based on the change of user cognition degree |
Non-Patent Citations (2)
| Title |
|---|
| 殇离行: "基于行为心理学的网络购物推荐算法思考", 《HTTPS://MY.OSCHINA.NET/U/1395815/BLOG/909194》 * |
| 薛福亮: "《电子商务推荐相关技术分析及其改进机制》", 30 June 2014, 中国财富出版社 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112819555A (en) * | 2019-11-15 | 2021-05-18 | 北京沃东天骏信息技术有限公司 | Article recommendation method and device |
| CN111586169A (en) * | 2020-05-07 | 2020-08-25 | 苏宁云计算有限公司 | Commodity marketing information pushing method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108805594B (en) | Information pushing method and device | |
| CN109191261A (en) | A kind of Method of Commodity Recommendation and system | |
| CN108985809A (en) | Motivate method, apparatus, electronic equipment and the storage medium of push | |
| CN107465741A (en) | Information-pushing method and device | |
| CN110111167A (en) | A kind of method and apparatus of determining recommended | |
| CN109961299A (en) | The method and apparatus of data analysis | |
| CN107463675A (en) | Data processing method and its system | |
| CN107590678A (en) | Method of Commodity Recommendation and system | |
| CN110020162A (en) | User identification method and device | |
| CN110020143A (en) | A kind of landing page generation method and device | |
| CN108898496A (en) | Products Show method, apparatus, medium and electronic equipment | |
| CN109727047A (en) | A kind of method and apparatus, data recommendation method and the device of determining data correlation degree | |
| CN112528153A (en) | Content recommendation method, device, equipment, storage medium and program product | |
| CN110223093A (en) | A kind of method and apparatus of commodity promotion | |
| CN108595448A (en) | Information-pushing method and device | |
| CN109711917A (en) | Information-pushing method and device | |
| CN110135871B (en) | Method and device for calculating user repurchase period | |
| CN109961328A (en) | The method and apparatus for determining order cooling off period | |
| CN107562941A (en) | Data processing method and its system | |
| CN108933823A (en) | User's touching reaches method and apparatus | |
| CN109872211A (en) | A kind of method and apparatus of object recommendation | |
| CN110019425A (en) | A kind of method and apparatus that data are shown | |
| CN109474884B (en) | Data processing method and system | |
| CN110232581A (en) | It is a kind of to provide the method and apparatus of discount coupon for user | |
| CN109977982A (en) | User classification method, system, electronic equipment and computer-readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |