CN108648049A - A kind of sequence of recommendation method based on user behavior difference modeling - Google Patents
A kind of sequence of recommendation method based on user behavior difference modeling Download PDFInfo
- Publication number
- CN108648049A CN108648049A CN201810414330.3A CN201810414330A CN108648049A CN 108648049 A CN108648049 A CN 108648049A CN 201810414330 A CN201810414330 A CN 201810414330A CN 108648049 A CN108648049 A CN 108648049A
- Authority
- CN
- China
- Prior art keywords
- user
- commodity
- behavior
- sequence
- vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Abstract
The invention discloses a kind of sequence of recommendation methods based on user behavior difference modeling, including:Obtain the historical behavior information of user;Product features vector is calculated according to the historical behavior information of acquisition;Series Modeling is carried out in conjunction with product features vector usage behavior difference modeling method, the current demand and history preference of user are obtained by two different neural network frameworks;According to the current purchasing demand of user and history preference, it is predicted by combination learning interested commodity next to user, and matched in commodity vector space, most similar multiple commodity in commodity vector space are found with prediction result, commercial product recommending sequence is generated.This method can provide accurately sequence of recommendation service to the user by the difference modeling to user's sequential behavior, the intelligent current demand understood in user's purchase decision and long-term preference.
Description
Technical field
The present invention relates to machine learning and technical field of electronic commerce, more particularly to a kind of distinguished based on user behavior to model
Sequence of recommendation method.
Background technology
With the continuous development of online shopping platform, commending system has become irreplaceable important in e-commerce
Component part.Commending system can learn the preference information hidden in user's history behavior, to user's Shopping Behaviors into
The further prediction of row promotes the income of e-commerce platform to be promoted while helping customer to select to be satisfied with commodity.Therefore, such as
What efficient, accurate commercial product recommending service for providing personalization to the user is all the weight of educational circles and industrial quarters research all the time
Want problem.
Currently, mainly there is following two major classes research about commending system:
1) commending system based on user's static preferences
Algorithm based on content, collaborative filtering or mixed type is all to belong to such, these methods are by by user's commodity
Information sees static feature as, and the commodity phase Sihe hidden in these features is excavated by the methods of cluster, matrix decomposition
The information such as user individual preference, to carry out Similar content or the recommendation of similar preference to user.Under this class model, Yong Huli
History behavioral data is counted as the static nature of user, and the preference of user is considered steady in a long-term and can be to user's future
Decision process has an impact, and on this basis, this kind of commending system only needs to learn user's history preference, and is pushed away for its preference
Recommend similar commodity.
2) the sequence of recommendation method based on short session
In partial line upper mounting plate, especially small-sized retail platform and multimedia contents service quotient lack enough use
Family historical behavior, but its backstage has added up the short session content of a large amount of user.In view of to lack user long-term for this scene
Preference profiles have scholar to propose user's sequence of recommendation method based on short session.Such methods are typically based on the short-term of user
Operation behavior builds deep neural network to model the dynamic change of user's behavior in a short time, to be used for predicting under user
The interested merchandise items of one step simultaneously recommend user.
It is above in line platform recommendation method, the commending system based on user's static preferences can be good at study and understand
The stabilization preference of user, and its favorite commodity of user or service can be accurately recommended, but this method is static
, only the preference of user to be regarded as and is remained unchanged for a long period of time, the preference for not accounting for user is also the process of a dynamic change,
Meanwhile this method does not account for the current demand of user, is strictly what user liked it is therefore possible to recommend user
But it is not that user is required.Sequence of recommendation method based on short session is to record the interactive process of user in a short time
Come, the sequence signature during analyzing user's current decision in these acts and efforts for expediency, to judge that user is next interested
Commodity or service.The sequence of recommendation method of this short session can model user behavior in a short time by deep neural network
Dynamic change, but this method has ignored user itself preference, this makes recommendation results often meet user demand but not
It is the favorite type of user.Meanwhile two methods fail to the dynamic change in the entire decision process by user and carry out deeply
Enter modeling, does not make a concrete analysis of the difference preference's degree gone out expressed by user's difference behavior.Therefore, using existing recommendation method
It is difficult to complete decision process when accurate modeling user selects commodity or service, user demand and preference cannot be combined,
Recommendation is caused to fail to reach user's expectation.
Invention content
The object of the present invention is to provide a kind of sequence of recommendation methods based on user behavior difference modeling, when by user
The difference of sequence behavior models, the intelligent current demand understood in user's purchase decision and long-term preference, and can be carried for user
For accurately sequence of recommendation service.
The purpose of the present invention is what is be achieved through the following technical solutions:
A kind of sequence of recommendation method based on user behavior difference modeling, including:
Obtain the historical behavior information of user;
Product features vector is calculated according to the historical behavior information of user;
Series Modeling is carried out in conjunction with product features vector usage behavior difference modeling method, passes through two different nerve nets
Network framework obtains the current demand and history preference of user;
According to the current purchasing demand of user and history preference, pass through combination learning interested commodity next to user
It is predicted, and is matched in commodity vector space, found most similar more in commodity vector space with prediction result
A commodity generate commercial product recommending sequence.
As seen from the above technical solution provided by the invention, for the deep enough spy of the difference modeling energy of user behavior
Suffered influence factor is begged in user's decision process, the different need of the user reflected for the different types of behavior of user
Ask with preference carried out it is more deep consider, and then the operation of user's next step is effectively predicted, to recommend use
The more satisfied commodity in family, and can sequence of recommendation dynamically be carried out by being interacted with user, it compensates for existing method and lacks
Weary dynamic and personalized certain drawback.
Description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, required use in being described below to embodiment
Attached drawing be briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this
For the those of ordinary skill in field, without creative efforts, other are can also be obtained according to these attached drawings
Attached drawing.
Fig. 1 is a kind of flow of sequence of recommendation method based on user behavior difference modeling provided in an embodiment of the present invention
Figure.
Specific implementation mode
With reference to the attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Based on this
The embodiment of invention, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, belongs to protection scope of the present invention.
The embodiment of the present invention provides a kind of sequence of recommendation method based on user behavior difference modeling, as shown in Figure 1, it is led
Include the following steps:
Step 1, the historical behavior information for obtaining user.
Each user can leave a series of log recording from the background when browsing is in line platform, these records have
The commodity relevant operations such as specific sequential relationship, including user's browsing, click, addition shopping cart, collection and purchase.These data
It can be collected directly from online shopping platform or online service provider.
In the embodiment of the present invention, the historical behavior information of acquired user is the data of interaction commodity sequence form, is used
The interaction commodity sequence of family u is expressed as:X therein indicates commodity, under be designated as commodity
Serial number, b indicate user's operation behavior, be one-hot vector, vectorial length is the quantity of type of interaction.
Step 2 calculates product features vector according to the historical behavior information of user.
In the embodiment of the present invention, by modeling the commodity sequence relation in user behavior, the Skip- based on negative sampling is built
Gram models generate the feature vector of commodity;Main process is as follows:
According to the interaction commodity sequence of user uProduct features vector is set up,
It is intended to maximize following target:
Wherein, N is interaction commodity sequenceLength, what p was indicated is softmax functional forms, definition be and xj、xi
Relevant probability, p (xj|xi) this form is referred to as softmax functions in professional domain, form is as follows:
Wherein, wiWith viIt is and commodity xiContext indicate corresponding latent variable and object vector;wjIt is and commodity
xjContext indicate corresponding latent variable;wk'It is and commodity xk'Context indicate corresponding latent variable;K''s
Value is 1 to N;
In order to mitigate the computation complexity of gradient, the following process of above formula is replaced:
Wherein, σ (r)=1/ (1+exp (- r)) is sigmoid functions, and E is the number of the negative sample to be drawn of each positive sample
Amount, here positive sample refer to and xiContext-sensitive commodity, the incoherent commodity that negative sample refers to just, the size of E can
To be set according to actual conditions or experience by user;
It is different to consider different commodity occurrence numbers, certain noise can be brought to above-mentioned negative sampling process, based on pair
The mode that commodity individual occurrence number is weighted, is again defined as above formula:
Wherein, Θ (xi) it is commodity xiThe frequency statistics occurred in interaction commodity sequence, the then target that commodity insertion characterizes
As maximize loss function:
Later, product features vector P is obtained by way of gradient declineu={ v1,v2,...,vN, wherein vjIndicate quotient
Product xjD dimensional feature vectors.
Step 3 carries out Series Modeling in conjunction with product features vector usage behavior difference modeling method, by two different
Neural network framework obtains the current demand and history preference of user.
After obtaining product features vector, difference behavior modeling can be using Continuous behavior as priori, to recommend
For the purpose of the project that target user most possibly accesses when accessing next time.The decision process of user is mainly by two factor shadows
It rings:Current motivation and history preference.More specifically, the current consumer motivation of user is dynamic in a short time, nearest
Fluctuation is also critically important for reflection Short-term characteristic.In view of all recent behaviors (such as clicking, collect, shopping cart, purchase)
It might mean that the current short-term motivation of user, it is dynamic that current consumption is presented using all types of recent behaviors in the present invention
Machine.On the other hand, for the history preference using user, not all types of behaviors can describe the preference of user.In order to
The long-term preference of user is modeled, the present invention only retains the potential preference that user is explicitly described from interactive history i.e. buying behavior
Behavior.In fact, the interactive process of user is a series of implicit feedbacks over time.Therefore, it is visited with from static mode
The conventional recommendation systems of rope user items interaction are different, and the next item down suggestion is handled by sequence modeling.Specifically, Wo Menshe
Two distinguishing behavior modeling processes are counted:It is current discriminatively to learn user for session behavior modeling and preference behavior modeling
Consumer motivation and preference steady in a long-term.In addition, on this basis, we have invented two kinds, and the deep-cycle based on LSTM is refreshing
Through network, to learn the arrangement of both motivations and preference behavior jointly.
First, conversate behavior modeling, product features vector Pu={ v1,v2,...,vNCorresponding interactive commodity sequence
ForIndicator function is defined as follows to determine commodity xiWhether current sessions behavior is met
Range:
DSBL(xi,xN)=Φ ((N-i)≤Ts);
Wherein, Φ (a) is a Boolean type function, when a is true, functional value 1, it is on the contrary then be 0;Ts indicates session
The control time of behavior walks, for controlling the length of session behavior;xNIt is current interaction commodity sequence Su bIn the last one commodity;
After definition initializes LSTM matrixes, in t-th of iteration step, the hiding layer state h of eachtUpdate,
With the hiding layer state h of a upper time stept-1And the product features vector v currently inputtedtWith behavior vector btIt is related;Wherein
Steps are as follows for update:
ht=ottanh(ct)
Wherein, it、ft、otInput gate, forgetting door, out gate in respectively t-th of iteration step;ctIt is network element
Memory module;btFor the user's operation behavior of t-th of the commodity of correspondence inputted in t-th of iteration step;Wvi、Whi、Wci、WbiIt is corresponding
For input gate itMiddle vt、ht-1、ct-1、btWeight;Wvf、Whf、Wcf、Wbf, correspond to forget door ftMiddle vt、ht-1、ct-1、btPower
Weight;Wvc、Whc、WbcCorrespond to v in memory modulet、ht-1、btWeight;Wvo、Who、Wco、WboCorrespond to out gate otMiddle vt、
ht-1、ct-1、btWeight;Input gate i is corresponded to respectivelyt, forget door ft, out gate ot, memory module ct
Deviation;htFor the output of current state;Tanh is hyperbolic tangent function.
Then the current purchasing demand of user is expressed as:
ΨSBL=hN;
During aforesaid operations, iterations are identical as commodity amount in interaction commodity sequence, i.e. t=1,2 ..., N, hN
The last one commodity of sequence xNOutput after input, i.e. n-th iteration step export.
Secondly, the history preference modeling for carrying out user, for each user's operation commodity-behavior to (vi,bi)∈Su b;
Its indicator function is expressed as:
DPBL(vi,bi)=Φ (bi∈P);
Wherein, P is the set of preference behavior, and main includes purchase, collection, addition shopping cart operation behavior;
The preference expression for learning user using two-way LSTM networks, in each time step of history preference modeling
There are two hidden layers to export, and for s-th of time step, wherein forward direction exportsIt is to be exported by its previous time stepWith work as
Preceding commodity-behavior is to (vs,bs) determined;Backward outputIt is to be exported by its latter time stepWith current quotient
Product-behavior is to (vs,bs) determined;Corresponding formula is as follows:
hs=ostanh(cs)
Wherein, is、fs、osThe input gate of respectively s-th time step forgets door, out gate;csIt is the note of network element
Recall module;bsFor the user's operation behavior of s-th of the commodity of correspondence inputted in s-th of iteration step;Wvi'、Whi'、Wci'、Wbi' right
It should be input gate isMiddle vs、hs-1、cs-1、bsWeight;Wvf'、Whf'、Wcf'、Wbf', correspond to forget door fsMiddle vs、hs-1、cs-1、
bsWeight;Wvc'、Whc'、Wbc' correspond to v in memory modules、hs-1、bsWeight;Wvo'、Who'、Wco'、Wbo' correspond to it is defeated
Go out osMiddle vs、hs-1、cs-1、bsWeight; Input gate i is corresponded to respectivelys, forget door fs, out gate
os, memory module csDeviation;hsFor the output of current state;If it is forward process, the output h of current statesAsIf it is backward process, the output h of current statesAs
By two-way LSTM networks, the preference that active user can be accessed to each time step characterizes vector:
Wherein,ForVector splicing, the average pond process that the history preference of user is expressed as:
Step 4, the current purchasing demand according to user and history preference, it is next to user interested by combination learning
Commodity predicted, and matched in commodity vector space, find with prediction result the most phase in commodity vector space
Close multiple commodity generate commercial product recommending sequence.
In the embodiment of the present invention, the current purchasing demand Ψ of user is combined by a full linking layerSBLWith history preference
ΨPBL, to which the predicted vector of the next interested commodity of user be calculated:
Wherein,WithCorresponding is the weight of current purchasing demand and history preference;Bias indicates model bias.
During model training, it is assumed that really the next interested commodity vector of user is:vT+1=(y1,
y2,...,yd);The loss function of model may be defined as:
Wherein, d is the dimension of vector.
Said program of the embodiment of the present invention records for the historical behavior of user, division difference is carried out according to time series
The sequence information of different user is embodied on the structure product features vector and user behavior difference modeling method of the present invention,
Product features vector is generated with commodity insertion characterizing method, and difference sequence is carried out to the different behaviors of commodity to user and is built
Mould, learns the current demand and history preference of user respectively, and interested commodity next to user are predicted.This method
The history preference of user is combined with current demand, the difference preference of commodity is built for expressed by user's difference behavior
Mould is dynamically learnt user's decision process by recurrent neural network, and then generates personalized sequence of recommendation to user, is made up
Existing method lacks dynamic and personalized certain drawback.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment can
By software realization, the mode of necessary general hardware platform can also be added to realize by software.Based on this understanding,
The technical solution of above-described embodiment can be expressed in the form of software products, the software product can be stored in one it is non-easily
In the property lost storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.), including some instructions are with so that a computer is set
Standby (can be personal computer, server or the network equipment etc.) executes the method described in each embodiment of the present invention.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
Any one skilled in the art is in the technical scope of present disclosure, the change or replacement that can be readily occurred in,
It should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with the protection model of claims
Subject to enclosing.
Claims (5)
1. a kind of sequence of recommendation method based on user behavior difference modeling, which is characterized in that including:
Obtain the historical behavior information of user;
Product features vector is calculated according to the historical behavior information of user;
Series Modeling is carried out in conjunction with product features vector usage behavior difference modeling method, passes through two different neural network framves
Structure obtains the current demand and history preference of user;
According to the current purchasing demand of user and history preference, carried out by combination learning interested commodity next to user
Prediction, and is matched in commodity vector space, finds with prediction result most similar multiple quotient in commodity vector space
Product generate commercial product recommending sequence.
2. a kind of sequence of recommendation method based on user behavior difference modeling according to claim 1, which is characterized in that institute
The historical behavior information of the user of acquisition is the data of interaction commodity sequence form, and the interaction commodity sequence of user u is expressed as:X therein indicates commodity, under be designated as the serial numbers of commodity, b indicates user's operation row
For.
3. a kind of sequence of recommendation method based on user behavior difference modeling according to claim 2, which is characterized in that root
According to user historical behavior information calculate product features vector step include:
According to the interaction commodity sequence of user uSet up product features vector, it is intended to
Maximize following target:
Wherein, N is interaction commodity sequence SuLength, and p (xj|xi) softmax functions are defined as, form is as follows:
Wherein, wiWith viIt is and commodity xiContext indicate corresponding latent variable and object vector;wjIt is and commodity xj's
Context indicates corresponding latent variable;wk'It is and commodity xk'Context indicate corresponding latent variable;The value of k'
N is arrived for 1;
The following process of above formula is replaced:
Wherein, σ (r)=1/ (1+exp (- r)) is sigmoid functions, and E is the quantity of the negative sample to be drawn of each positive sample;
Based on the mode being weighted to commodity individual occurrence number, above formula is defined as again:
Wherein, Θ (xi) it is commodity xiThe frequency statistics occurred in interaction commodity sequence, the then target that commodity insertion characterizes are
Maximize loss function:
Later, product features vector P is obtained by way of gradient declineu={ v1,v2,...,vN, wherein vjIndicate commodity xj
D dimensional feature vectors.
4. a kind of sequence of recommendation method based on user behavior difference modeling according to claim 3, which is characterized in that institute
It states and modeling method progress Series Modeling is distinguished according to the historical behavior information usage behavior of acquisition, calculating the current purchase of user needs
Summation history preference process include:
First, conversate behavior modeling, product features vector Pu={ v1,v2,...,vTCorresponding interactive commodity sequence isIndicator function is defined as follows to determine commodity xiWhether current sessions behavior is met
Range:
DSBL(xi,xT)=Φ ((T-i)≤Ts);
Wherein, Φ (a) is a Boolean type function, when a is true, functional value 1, it is on the contrary then be 0;Ts indicates session behavior
Control time step, for controlling the length of session behavior;xTIt is interactive commodity sequenceIn the last one commodity;
After definition initializes LSTM matrixes, in t-th of iteration step, the hiding layer state h of eachtUpdate and upper one
The hiding layer state h of a time stept-1And the product features vector v currently inputtedtAnd behavior vector btIt is related;Wherein update step
It is rapid as follows:
Wherein, it、ft、otInput gate, forgetting door, out gate in respectively t-th of iteration step;ctIt is the memory mould of network element
Block;btFor the user's operation behavior of t-th of the commodity of correspondence inputted in t-th of iteration step;Wvi、Whi、Wci、WbiIt corresponds to input
Door itMiddle vt、ht-1、ct-1、btWeight;Wvf、Whf、Wcf、Wbf, correspond to forget door ftMiddle vt、ht-1、ct-1、btWeight;Wvc、
Whc、WbcCorrespond to v in memory modulet、ht-1、btWeight;Wvo、Who、Wco、WboCorrespond to out gate otMiddle vt、ht-1、ct-1、bt
Weight;Input gate i is corresponded to respectivelyt, forget door ft, out gate ot, memory module ctDeviation;ht
For the output of current state;Tanh is hyperbolic tangent function;
Then the current purchasing demand of user is expressed as:
ΨSBL=hN;
Secondly, the history preference modeling for carrying out user, for each user's operation commodity-behavior pairIt is indicated
Function representation is:
DPBL(vi,bi)=Φ (bi∈P);
Wherein, P is the set of preference behavior;
The preference expression for learning user using two-way LSTM networks has two in each time step of history preference modeling
A hidden layer output, for s-th of time step, wherein forward direction exportsIt is to be exported by its previous time stepWith it is current
Commodity-behavior is to (vs,bs) determined;Backward outputIt is to be exported by its latter time stepWith current commodity-row
For to (vs,bs) determined;Corresponding formula is as follows:
Wherein, is、fs、osThe input gate of respectively s-th time step forgets door, out gate;csIt is the memory mould of network element
Block;bsFor the user's operation behavior of s-th of the commodity of correspondence inputted in s-th of iteration step;Wvi'、Whi'、Wci'、Wbi' correspond to
Input gate isMiddle vs、hs-1、cs-1、bsWeight;Wvf'、Whf'、Wcf'、Wbf', correspond to forget door fsMiddle vs、hs-1、cs-1、bs's
Weight;Wvc'、Whc'、Wbc' correspond to v in memory modules、hs-1、bsWeight;Wvo'、Who'、Wco'、Wbo' correspond to out gate
osMiddle vs、hs-1、cs-1、bsWeight; Input gate i is corresponded to respectivelys, forget door fs, out gate os, note
Recall module csDeviation;hsFor the output of current state;If it is forward process, the output h of current statesAsSuch as
Fruit be after to process, then the output h of current statesAs
By two-way LSTM networks, the preference that active user can be accessed to each time step characterizes vector:
Wherein,ForVector splicing, the average pond process that the history preference of user is expressed as:
5. a kind of sequence of recommendation method based on user behavior difference modeling according to claim 1 or 3 or 4, feature
It is, the current purchasing demand and history preference according to user, passes through combination learning interested quotient next to user
Product carry out prediction:
The current purchasing demand Ψ of user is combined by a full linking layerSBLWith history preference ΨPBL, to which use be calculated
The predicted vector of the next interested commodity in family:
Wherein,WithCorresponding is the weight of current purchasing demand and history preference;Bias indicates model bias;
During model training, it is assumed that really the next interested commodity vector of user is:vT+1=(y1,y2,...,
yd);The loss function of model is defined as:
Wherein, d is the dimension of vector.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810414330.3A CN108648049B (en) | 2018-05-03 | 2018-05-03 | Sequence recommendation method based on user behavior difference modeling |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810414330.3A CN108648049B (en) | 2018-05-03 | 2018-05-03 | Sequence recommendation method based on user behavior difference modeling |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108648049A true CN108648049A (en) | 2018-10-12 |
CN108648049B CN108648049B (en) | 2022-03-01 |
Family
ID=63748587
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810414330.3A Active CN108648049B (en) | 2018-05-03 | 2018-05-03 | Sequence recommendation method based on user behavior difference modeling |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108648049B (en) |
Cited By (29)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109408731A (en) * | 2018-12-27 | 2019-03-01 | 网易(杭州)网络有限公司 | A kind of multiple target recommended method, multiple target recommended models generation method and device |
CN109460816A (en) * | 2018-11-16 | 2019-03-12 | 焦点科技股份有限公司 | A kind of user's behavior prediction method based on deep learning |
CN109509056A (en) * | 2018-10-16 | 2019-03-22 | 平安科技(深圳)有限公司 | Method of Commodity Recommendation, electronic device and storage medium based on confrontation network |
CN109522474A (en) * | 2018-10-19 | 2019-03-26 | 上海交通大学 | Recommended method based on interaction sequence data mining depth user's similitude |
CN109543112A (en) * | 2018-11-30 | 2019-03-29 | 苏州大学 | A kind of sequence of recommendation method and device based on cyclic convolution neural network |
CN109543066A (en) * | 2018-10-31 | 2019-03-29 | 北京达佳互联信息技术有限公司 | Video recommendation method, device and computer readable storage medium |
CN109741105A (en) * | 2018-12-29 | 2019-05-10 | 星潮闪耀移动网络科技(中国)有限公司 | A kind of vector generation method and device |
CN109960761A (en) * | 2019-03-28 | 2019-07-02 | 腾讯科技(深圳)有限公司 | Information recommendation method, device, equipment and computer readable storage medium |
CN110008409A (en) * | 2019-04-12 | 2019-07-12 | 苏州市职业大学 | Based on the sequence of recommendation method, device and equipment from attention mechanism |
CN110060097A (en) * | 2019-04-01 | 2019-07-26 | 苏州市职业大学 | User behavior sequence of recommendation method based on attention mechanism and convolutional neural networks |
CN110097433A (en) * | 2019-05-14 | 2019-08-06 | 苏州大学 | Recommended method, device, equipment and storage medium based on attention mechanism |
CN110245299A (en) * | 2019-06-19 | 2019-09-17 | 中国人民解放军国防科技大学 | Sequence recommendation method and system based on dynamic interaction attention mechanism |
CN110458643A (en) * | 2019-05-15 | 2019-11-15 | 北京邮电大学 | Repeated commodity information recommendation method and electronic equipment based on Fusion Features |
CN110503531A (en) * | 2019-08-30 | 2019-11-26 | 中国科学技术大学 | The dynamic social activity scene recommended method of timing perception |
CN110569432A (en) * | 2019-08-14 | 2019-12-13 | 中国平安人寿保险股份有限公司 | commodity sequence calculation method and device, computer equipment and storage medium |
CN110889748A (en) * | 2019-12-02 | 2020-03-17 | 广州伊的家网络科技有限公司 | Store-merchant platform product recommendation method and device, computer equipment and storage medium |
CN111127152A (en) * | 2019-12-23 | 2020-05-08 | 深圳市赛维网络科技有限公司 | Commodity recommendation method, device and equipment based on user preference prediction and readable medium |
CN111259254A (en) * | 2020-02-07 | 2020-06-09 | 齐鲁工业大学 | Filtering recommendation method and system based on session noise |
CN111475720A (en) * | 2020-03-31 | 2020-07-31 | 北京三快在线科技有限公司 | Recommendation method, recommendation device, server and storage medium |
CN111563206A (en) * | 2020-07-03 | 2020-08-21 | 北京每日优鲜电子商务有限公司 | Article information sequence display method and device, electronic equipment and medium |
CN111797321A (en) * | 2020-07-07 | 2020-10-20 | 山东大学 | Personalized knowledge recommendation method and system for different scenes |
CN111815415A (en) * | 2020-07-14 | 2020-10-23 | 北京邮电大学 | Commodity recommendation method, system and equipment |
CN113301094A (en) * | 2020-09-10 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Information pushing method and device |
CN113313381A (en) * | 2021-05-28 | 2021-08-27 | 北京航空航天大学 | User interaction sensitive dynamic graph sequence recommendation system |
CN113362098A (en) * | 2020-03-06 | 2021-09-07 | 北京沃东天骏信息技术有限公司 | Data processing method, device and computer readable storage medium |
CN113393281A (en) * | 2020-03-11 | 2021-09-14 | 北京沃东天骏信息技术有限公司 | Method and device for processing request |
CN113536140A (en) * | 2021-09-16 | 2021-10-22 | 广东众聚人工智能科技有限公司 | Real-time recommendation method and system based on small sample data |
CN115828107A (en) * | 2023-01-09 | 2023-03-21 | 深圳市云积分科技有限公司 | Model training method and device based on offline environment |
CN116862625A (en) * | 2023-09-05 | 2023-10-10 | 武汉森全科技有限公司 | Online recommendation method for fresh fruits based on Internet big data |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2011005072A2 (en) * | 2009-07-09 | 2011-01-13 | Mimos Bhd. | Personalized shopping list recommendation based on shopping behavior |
CN103617540A (en) * | 2013-10-17 | 2014-03-05 | 浙江大学 | E-commerce recommendation method of tracking user interest changes |
CN105869024A (en) * | 2016-04-20 | 2016-08-17 | 北京小米移动软件有限公司 | Commodity recommending method and device |
CN107423442A (en) * | 2017-08-07 | 2017-12-01 | 火烈鸟网络(广州)股份有限公司 | Method and system, storage medium and computer equipment are recommended in application based on user's portrait behavioural analysis |
US20180075516A1 (en) * | 2016-09-14 | 2018-03-15 | Microsoft Technology Licensing, Llc | System for producing recommendations and predicting purchases of products based on usage patterns |
CN107832426A (en) * | 2017-11-13 | 2018-03-23 | 上海交通大学 | A kind of APP recommendation method and system based on using sequence context |
-
2018
- 2018-05-03 CN CN201810414330.3A patent/CN108648049B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2011005072A2 (en) * | 2009-07-09 | 2011-01-13 | Mimos Bhd. | Personalized shopping list recommendation based on shopping behavior |
CN103617540A (en) * | 2013-10-17 | 2014-03-05 | 浙江大学 | E-commerce recommendation method of tracking user interest changes |
CN105869024A (en) * | 2016-04-20 | 2016-08-17 | 北京小米移动软件有限公司 | Commodity recommending method and device |
US20180075516A1 (en) * | 2016-09-14 | 2018-03-15 | Microsoft Technology Licensing, Llc | System for producing recommendations and predicting purchases of products based on usage patterns |
CN107423442A (en) * | 2017-08-07 | 2017-12-01 | 火烈鸟网络(广州)股份有限公司 | Method and system, storage medium and computer equipment are recommended in application based on user's portrait behavioural analysis |
CN107832426A (en) * | 2017-11-13 | 2018-03-23 | 上海交通大学 | A kind of APP recommendation method and system based on using sequence context |
Non-Patent Citations (4)
Title |
---|
RENDLE S等: "Factorizing personalized Markov chains for next basket recommendation", 《PROCEEDINGS OF INTERNATIONAL CONFERENCE ON WORLD WIDE WEB》 * |
WANG P等: "Learning hierarchical representation model for nextbasket recommendation", 《PROCEEDINGS OF INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL》 * |
李裕礞等: "基于用户隐性反馈行为的下一个购物篮推荐", 《中文信息学报》 * |
王屯屯: "基于LSTM的在线商城商品推荐研究", 《现代计算机(专业版)》 * |
Cited By (47)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109509056A (en) * | 2018-10-16 | 2019-03-22 | 平安科技(深圳)有限公司 | Method of Commodity Recommendation, electronic device and storage medium based on confrontation network |
CN109509056B (en) * | 2018-10-16 | 2023-05-09 | 平安科技(深圳)有限公司 | Commodity recommendation method based on countermeasure network, electronic device and storage medium |
CN109522474A (en) * | 2018-10-19 | 2019-03-26 | 上海交通大学 | Recommended method based on interaction sequence data mining depth user's similitude |
CN109522474B (en) * | 2018-10-19 | 2021-05-18 | 上海交通大学 | Recommendation method for mining deep user similarity based on interactive sequence data |
CN109543066B (en) * | 2018-10-31 | 2021-04-23 | 北京达佳互联信息技术有限公司 | Video recommendation method and device and computer-readable storage medium |
US11244228B2 (en) | 2018-10-31 | 2022-02-08 | Beijing Dajia Internet Information Technology Co., Ltd. | Method and device for recommending video, and computer readable storage medium |
CN109543066A (en) * | 2018-10-31 | 2019-03-29 | 北京达佳互联信息技术有限公司 | Video recommendation method, device and computer readable storage medium |
CN109460816A (en) * | 2018-11-16 | 2019-03-12 | 焦点科技股份有限公司 | A kind of user's behavior prediction method based on deep learning |
CN109543112A (en) * | 2018-11-30 | 2019-03-29 | 苏州大学 | A kind of sequence of recommendation method and device based on cyclic convolution neural network |
CN109408731B (en) * | 2018-12-27 | 2021-03-16 | 网易(杭州)网络有限公司 | Multi-target recommendation method, multi-target recommendation model generation method and device |
CN109408731A (en) * | 2018-12-27 | 2019-03-01 | 网易(杭州)网络有限公司 | A kind of multiple target recommended method, multiple target recommended models generation method and device |
CN109741105A (en) * | 2018-12-29 | 2019-05-10 | 星潮闪耀移动网络科技(中国)有限公司 | A kind of vector generation method and device |
CN109960761A (en) * | 2019-03-28 | 2019-07-02 | 腾讯科技(深圳)有限公司 | Information recommendation method, device, equipment and computer readable storage medium |
CN109960761B (en) * | 2019-03-28 | 2023-03-31 | 深圳市雅阅科技有限公司 | Information recommendation method, device, equipment and computer readable storage medium |
CN110060097A (en) * | 2019-04-01 | 2019-07-26 | 苏州市职业大学 | User behavior sequence of recommendation method based on attention mechanism and convolutional neural networks |
CN110008409A (en) * | 2019-04-12 | 2019-07-12 | 苏州市职业大学 | Based on the sequence of recommendation method, device and equipment from attention mechanism |
CN110097433A (en) * | 2019-05-14 | 2019-08-06 | 苏州大学 | Recommended method, device, equipment and storage medium based on attention mechanism |
CN110097433B (en) * | 2019-05-14 | 2022-05-17 | 苏州大学 | Attention mechanism-based recommendation method, device, equipment and storage medium |
CN110458643B (en) * | 2019-05-15 | 2022-07-01 | 北京邮电大学 | Repetitive commodity information recommendation method based on feature fusion and electronic equipment |
CN110458643A (en) * | 2019-05-15 | 2019-11-15 | 北京邮电大学 | Repeated commodity information recommendation method and electronic equipment based on Fusion Features |
CN110245299A (en) * | 2019-06-19 | 2019-09-17 | 中国人民解放军国防科技大学 | Sequence recommendation method and system based on dynamic interaction attention mechanism |
CN110245299B (en) * | 2019-06-19 | 2022-02-08 | 中国人民解放军国防科技大学 | Sequence recommendation method and system based on dynamic interaction attention mechanism |
CN110569432B (en) * | 2019-08-14 | 2023-11-03 | 中国平安人寿保险股份有限公司 | Commodity sequence calculating method, commodity sequence calculating device, computer equipment and storage medium |
CN110569432A (en) * | 2019-08-14 | 2019-12-13 | 中国平安人寿保险股份有限公司 | commodity sequence calculation method and device, computer equipment and storage medium |
CN110503531A (en) * | 2019-08-30 | 2019-11-26 | 中国科学技术大学 | The dynamic social activity scene recommended method of timing perception |
CN110503531B (en) * | 2019-08-30 | 2022-04-19 | 中国科学技术大学 | Dynamic social scene recommendation method based on time sequence perception |
CN110889748B (en) * | 2019-12-02 | 2023-08-15 | 广州伊的家网络科技有限公司 | Store platform product recommendation method, store platform product recommendation device, computer equipment and storage medium |
CN110889748A (en) * | 2019-12-02 | 2020-03-17 | 广州伊的家网络科技有限公司 | Store-merchant platform product recommendation method and device, computer equipment and storage medium |
CN111127152A (en) * | 2019-12-23 | 2020-05-08 | 深圳市赛维网络科技有限公司 | Commodity recommendation method, device and equipment based on user preference prediction and readable medium |
CN111259254A (en) * | 2020-02-07 | 2020-06-09 | 齐鲁工业大学 | Filtering recommendation method and system based on session noise |
CN111259254B (en) * | 2020-02-07 | 2023-08-01 | 齐鲁工业大学 | Filtering recommendation method and system based on session noise |
CN113362098A (en) * | 2020-03-06 | 2021-09-07 | 北京沃东天骏信息技术有限公司 | Data processing method, device and computer readable storage medium |
CN113393281A (en) * | 2020-03-11 | 2021-09-14 | 北京沃东天骏信息技术有限公司 | Method and device for processing request |
CN111475720A (en) * | 2020-03-31 | 2020-07-31 | 北京三快在线科技有限公司 | Recommendation method, recommendation device, server and storage medium |
CN111563206A (en) * | 2020-07-03 | 2020-08-21 | 北京每日优鲜电子商务有限公司 | Article information sequence display method and device, electronic equipment and medium |
CN111563206B (en) * | 2020-07-03 | 2024-01-12 | 秦皇岛肆拾贰宇数字科技有限公司 | Method, device, electronic equipment and medium for displaying object information sequence |
CN111797321A (en) * | 2020-07-07 | 2020-10-20 | 山东大学 | Personalized knowledge recommendation method and system for different scenes |
CN111815415A (en) * | 2020-07-14 | 2020-10-23 | 北京邮电大学 | Commodity recommendation method, system and equipment |
CN111815415B (en) * | 2020-07-14 | 2023-10-27 | 北京邮电大学 | Commodity recommendation method, system and equipment |
CN113301094A (en) * | 2020-09-10 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Information pushing method and device |
CN113313381A (en) * | 2021-05-28 | 2021-08-27 | 北京航空航天大学 | User interaction sensitive dynamic graph sequence recommendation system |
CN113313381B (en) * | 2021-05-28 | 2022-04-08 | 北京航空航天大学 | User interaction sensitive dynamic graph sequence recommendation system |
CN113536140A (en) * | 2021-09-16 | 2021-10-22 | 广东众聚人工智能科技有限公司 | Real-time recommendation method and system based on small sample data |
CN115828107B (en) * | 2023-01-09 | 2023-05-05 | 深圳市云积分科技有限公司 | Model training method and device based on offline environment |
CN115828107A (en) * | 2023-01-09 | 2023-03-21 | 深圳市云积分科技有限公司 | Model training method and device based on offline environment |
CN116862625A (en) * | 2023-09-05 | 2023-10-10 | 武汉森全科技有限公司 | Online recommendation method for fresh fruits based on Internet big data |
CN116862625B (en) * | 2023-09-05 | 2023-11-21 | 武汉森全科技有限公司 | Online recommendation method for fresh fruits based on Internet big data |
Also Published As
Publication number | Publication date |
---|---|
CN108648049B (en) | 2022-03-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108648049A (en) | A kind of sequence of recommendation method based on user behavior difference modeling | |
Yu et al. | A cross-domain collaborative filtering algorithm with expanding user and item features via the latent factor space of auxiliary domains | |
CN110245299B (en) | Sequence recommendation method and system based on dynamic interaction attention mechanism | |
CN110717098B (en) | Meta-path-based context-aware user modeling method and sequence recommendation method | |
Pan et al. | Study on convolutional neural network and its application in data mining and sales forecasting for E-commerce | |
CN111797321B (en) | Personalized knowledge recommendation method and system for different scenes | |
Xu et al. | A multi-objective decision-making model with fuzzy rough coefficients and its application to the inventory problem | |
US20120030020A1 (en) | Collaborative filtering on spare datasets with matrix factorizations | |
CN111815415A (en) | Commodity recommendation method, system and equipment | |
CN111242729A (en) | Serialization recommendation method based on long-term and short-term interests | |
Wijaya et al. | Estimating city-level poverty rate based on e-commerce data with machine learning | |
CN110633421B (en) | Feature extraction, recommendation, and prediction methods, devices, media, and apparatuses | |
CN113918833B (en) | Product recommendation method realized through graph convolution collaborative filtering of social network relationship | |
Hu | Nonadditive similarity-based single-layer perceptron for multi-criteria collaborative filtering | |
CN113918834B (en) | Graph convolution collaborative filtering recommendation method fusing social relations | |
CN116010684A (en) | Article recommendation method, device and storage medium | |
CN113761359A (en) | Data packet recommendation method and device, electronic equipment and storage medium | |
Miao et al. | Joint prediction of rating and popularity for cold-start item by sentinel user selection | |
CN112819575B (en) | Session recommendation method considering repeated purchasing behavior | |
CN113850654A (en) | Training method of item recommendation model, item screening method, device and equipment | |
CN113688306A (en) | Recommendation strategy generation method and device based on reinforcement learning | |
Babeetha et al. | An enhanced kernel weighted collaborative recommended system to alleviate sparsity | |
CN110555719B (en) | Commodity click rate prediction method based on deep learning | |
CN110111184A (en) | A kind of negative sequence recommended method and system based on weighting Bayesian inference | |
CN110956528B (en) | Recommendation method and system for e-commerce platform |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |