CN116645174A - Personalized recommendation method based on decoupling multi-behavior characterization learning - Google Patents
Personalized recommendation method based on decoupling multi-behavior characterization learning Download PDFInfo
- Publication number
- CN116645174A CN116645174A CN202310926715.9A CN202310926715A CN116645174A CN 116645174 A CN116645174 A CN 116645174A CN 202310926715 A CN202310926715 A CN 202310926715A CN 116645174 A CN116645174 A CN 116645174A
- Authority
- CN
- China
- Prior art keywords
- user
- embedding
- behavior
- formula
- representing
- 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
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000012512 characterization method Methods 0.000 title claims abstract description 13
- 230000006399 behavior Effects 0.000 claims abstract description 162
- 238000006243 chemical reaction Methods 0.000 claims abstract description 10
- 239000013598 vector Substances 0.000 claims description 66
- 230000003993 interaction Effects 0.000 claims description 29
- 230000006870 function Effects 0.000 claims description 21
- 239000011159 matrix material Substances 0.000 claims description 19
- 230000009471 action Effects 0.000 claims description 18
- 238000013528 artificial neural network Methods 0.000 claims description 13
- 230000003542 behavioural effect Effects 0.000 claims description 13
- 230000004913 activation Effects 0.000 claims description 12
- 230000002452 interceptive effect Effects 0.000 claims description 11
- 230000009466 transformation Effects 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 9
- 230000002776 aggregation Effects 0.000 claims description 6
- 238000004220 aggregation Methods 0.000 claims description 6
- 238000005192 partition Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000017105 transposition Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims 1
- 230000004931 aggregating effect Effects 0.000 abstract description 3
- 238000013135 deep learning Methods 0.000 abstract description 2
- 239000000284 extract Substances 0.000 abstract description 2
- 241000894007 species Species 0.000 description 20
- 230000000694 effects Effects 0.000 description 3
- 241000282326 Felis catus Species 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000011423 initialization method Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention relates to the technical field of recommendation systems and deep learning, in particular to a personalized recommendation method based on decoupling multi-behavior characterization learning. And learning user embedding and article embedding in each behavior by using the cascade behavior relation, wherein the characteristic information of the user and the article in each behavior is used as the meta-knowledge, and the meta-network model extracts the meta-knowledge to be the personalized characteristic conversion between the modeling behaviors of the user and the article. On this basis, the user embedding and the article embedding in each behavior are decoupled by using decoupling characterization learning. For decoupled user and item embedding, feature preference attention network modeling users have been designed to have different preferences for different features in different behaviors. And finally, aggregating the predictive scores of the users on the articles in all behaviors. Therefore, the recommendation system models more finely-grained user embedding and article embedding on the one hand, and more individuates the recommendation model on the other hand, so that the performance of the recommendation system is improved.
Description
Technical Field
The invention relates to the technical field of recommendation systems and deep learning, in particular to a personalized recommendation method based on decoupling multi-behavior characterization learning.
Background
The recommendation has made tremendous progress in the last decade as an effective tool for dealing with information overload problems in the information age. Model-based collaborative filtering learns representations of users and items to recommend based on their interactions, which has become a mainstream recommendation technique since it was successful in Netflix recommendation algorithm contests. Collaborative filtering models tend to build on a single behavior that is directly related to platform profit, such as purchasing behavior of an e-commerce platform or downloading behavior of an App platform. Because this behavior brings real economic or time costs to the user, the single behavior recommendation model can encounter serious data sparseness problems in practical applications. Fortunately, users typically take other types of actions (i.e., clicking and shopping carts) to obtain more information about the item to assist them in making the final decision. Other types of behavior have richer interactions than purchasing behavior. These types of behavior or auxiliary behavior may be used to help capture user preferences, alleviating data sparseness problems in recommendations.
In recent years, many behavioral recommendation models have made tremendous progress in utilizing cascading relationships of behaviors, such as the multi-behavioral recommendation model cascading graph convolutional network (MB-CGCN), which employs cascading graph convolutional neural network (GCN) modules to explicitly model cascading relationships between behaviors. In this model, the behavior features learned on the previous behavior by the structural model in GCN (LightGCN) are passed on to the next behavior in the chain after the feature transformation operation, and the embeddings learned from all behaviors are clustered together for final prediction.
Despite the tremendous advances made by cascading multi-behavior recommendation model techniques, two major limitations remain. On the one hand, user embedding and item embedding all features of each behavior are entangled together, creating sub-optimal problems. The user's preferences are different for different features in different behaviors, all of which are entangled together and cannot model the user's preferences. On the other hand, feature transitions between behaviors are shared. The feature transformation between each behavior should model the personalized feature transformation based on the user or item information, resulting in a more personalized recommendation model.
Disclosure of Invention
Aiming at the defects of the prior art, the personalized recommendation method based on decoupling multi-behavior characterization learning is developed, the preference degree of a user on an article in each behavior can be displayed, and personalized feature conversion by utilizing meta-learning network modeling is provided.
The technical scheme for solving the technical problems is as follows:
a personalized recommendation method based on decoupling multi-behavior characterization learning comprises the following steps:
(a) Preprocessing in an electronic commerce data set to obtain a training set and a testing set;
(b) The data set comprises M users, N articles and B interaction behaviors;
(c) Constructing a personalized cascade GCN module to obtain user embedding and article embedding of B interactive behaviors, wherein the module consists of B GCNs, and personalized information is transmitted between the GCNs by a meta-learning network;
(d) Decoupling the user embedding and the article embedding of the B interaction behaviors, and modeling the user with different feature preferences in different behaviors by using a feature preference attention network;
(e) Calculating the overall preference of the user for the article under the B behaviors;
(f) Model parameters are optimized by an Adam optimizer using model loss.
The step (a) comprises the following steps of: for an e-commerce data set, the articles interacted by the users in the B behaviors are respectively divided according to a leave-one-out method, the last interaction of each user in the B behaviors is reserved as a test set, the rest data are used as a training set, and the sequence of the B interaction behaviors follows the sequence of the data set or the real behaviors.
The step (b) comprises the following steps:
(B-1) the dataset comprising M user-formed user sets U, N items-formed item sets I, B interaction behaviors-formed B interaction matrices；
(b-2) mapping the user ID and the item ID into one-hot vector matrices, respectivelyAnd->Embedding matrix for user by using Xavier method>And an article embedding matrix->Parameter initialization is performed, wherein->Is the embedded vector dimension;
(b-3) passing through the formulaAnd formula->Calculating initial embedding vector of user ID and article ID respectively>And->Wherein->For matrix->Is the u-th user's one-hot vector,/->For matrix->One-hot vector of the i-th item,/->，/>，/>Is the embedded vector dimension.
The step (c) comprises the following steps:
(c-1) passing through the formulaCalculating to obtain->User of the seed behavior embeds +.>Graph convolution results of layers->In the formula->L is a drawing rollThe number of layers deposited->The representation represents +.>Item embedding of the species behaviour->Graph convolution result of layers, < >>Representation and user->Interactive item set->Representing a set of users interacting with item i, +.>Representing the size of the collection;
(c-2) passing through the formulaUser embedding +.>In the followingThe number of layers for the graph convolution, +.>Indicate->User of the seed behavior embeds +.>A graph convolution result of the layers;
(c-3) passing through the formulaCalculating to obtain->User-embedded meta-knowledge of the kind of behavior +.>In the formula->For the splicing function->User-embedded +.>Item insert representing action b, +.>Item insert representing aggregation interacting with user u, +.>；
(c-4) passing through the formulaCalculating to obtain->User-embedded personalized feature transformation parameter of seed behavior +.>In the formula->，And->Respectively represent +.>First-layer and second-layer neural network weight matrix of user in seed behavior, +.>And->Respectively represent +.>First-layer and second-layer neural network bias vectors of users in seed behavior, +.>Representing an activation function;
(c-5) passing through the formulaCalculating to obtain->Species behavior to->Personalized feature conversion embedded by behavioral user +.>Wherein->Is->User-initiated embedding of seed behavior;
(c-6) passing through the formulaCalculating to obtain->Item embedding of the species behaviour->Graph convolution results of layers->In the formula->，/>The number of layers for the graph convolution, +.>Indicate->User of the seed behavior embeds +.>Graph convolution result of layers, < >>Representation and article->Interactive user set, < > on->Representation and user->Interactive item set->Representing the size of the collection;
(c-7) passing through the formulaItem embedding for calculating b-th behavior>In the followingThe number of layers for the graph convolution, +.>Indicate->Item embedding of the species behaviour->A graph convolution result of the layers;
(c-8) passing through the formulaCalculating to obtain->Item-embedded meta-knowledge of the species behaviour +.>In the formula->For the splicing function->Item insert representing action b, +.>Representing aggregation and article->User-embedded, meta-data of interactions>；
(c-9) passing through the formulaCalculating to obtain->Item-embedded personalized feature transformation parameter of species behavior +.>In the formula->And->Respectively represent +.>First and second layer neural network weight matrices of items in a seed behavior,and->Respectively represent +.>First and second layer neural network bias vectors for items in a seed behavior, +.>Representing an activation function;
(c-10) passing through the formulaCalculating to obtain->Species behavior to->Personalized feature conversion for embedding of behavioral items +.>Wherein->Is->The article of action is initially embedded.
The step (d) comprises the following steps of:
(d-1) passing through the formulaDivision->Get->User embedding of seed behavior>Is->A continuous block, in which->Representing the number of feature vector partitions, +.>Indicate->User embedding of seed behavior>Corresponding->Individual feature vectors->Representing feature vector dimensions;
(d-2) passing through the formulaDivision->Get->Article embedding of species behavior->Is->A continuous block, in which->Representing the number of feature vector partitions, +.>Indicate->Article embedding of species behavior->Corresponding->Individual feature vectors->Representing feature vector dimensions;
(d-3) passing through the formulaCalculating preference weight of user embedded kth block feature vector to article embedded kth block feature vector of the b-th action>，，/>Indicate->Attention weight matrix of user in seed behavior, < ->The offset vector is represented as such,/>representing a splicing operation->Representing an activation function;
(d-4) passing through the formulaSplicing to obtain preference weight of user embedded K block feature vector of b-th behavior to object embedded corresponding block feature vector>In the followingRepresenting a splicing function;
(d-5) passing through the formulaCalculating the attention score of the characteristic preference of the user embedded K block characteristic vector of the b-th action on the article embedded corresponding block characteristic vector>In the formula->Representing a normalization function;
(d-6) passing through the formulaUser embedding of the b-th behavior calculated +.>New user embedding after feature preference attention score fusionIn the formula->Representation->And->Is multiplied by each dimension of (a).
The step (e) comprises the following steps:
(e-1) passing through the formulaCalculating user embedding +.>Embedding +.>Preference score of (2), wherein->、/>And->Respectively representing the user-embedded +.>Block feature vector feature preference attention score for embedding item into corresponding block feature vector, user-embedded +.>Block feature vector and item-embedded +.b in behavior>Block feature vector->Is a transposition operation;
(e-2) passing through the formulaCalculating the total score of the user to the item in the B behaviors, wherein +.>Representing user embedding +.>Embedding +.>Is a preference score of (c).
The step (f) comprises the following steps:
(f-1) according to the formulaCalculating BPR loss, wherein ∈R is calculated>For training set, ->，/>To observe the user->And articles->Interaction set existing between->For user->Sampling unobserved items in an interaction set，/>Representing a Sigmoid activation function;
(f-2) according to the formulaUser embedding +.>Is>In the following，/>Representing the distance covariance between the two matrices, < +.>Representing a distance variance of the matrix;
(f-3) according to the formulaCalculating to obtain the user embedded decoupling total loss in B behaviors；
(f-4) according to the formulaItem embedding for calculating b-th behavior>Is>In the following,/>Representing the distance covariance between the two matrices, < +.>Representing a distance variance of the matrix;
(f-5) according to the formulaCalculating to obtain the total loss of the embedded decoupling of the article in the B behaviors；
(f-6) according to the formulaCalculating to obtain a model total loss function>In the formula->、/>The super parameter control module comprises user embedding and article embedding decoupling total loss +.>And model parameters->L2 regularization->，/>Representing model parameters +.>Is regularized by L2.
The effects provided in the summary of the invention are merely effects of embodiments, not all effects of the invention, and the above technical solution has the following advantages or beneficial effects:
the invention provides a personalized recommendation method based on decoupling multi-behavior characterization learning, which consists of a decoupling characterization learning module and a meta learning module. Firstly, learning user embedding and article embedding in each behavior by utilizing a cascade behavior relation, taking characteristic information of the user and the article in each behavior as meta-knowledge, and extracting the meta-knowledge through a meta-network to model personalized characteristic conversion between the behaviors of the user and the article. On this basis, the user embedding and the article embedding in each behavior are decoupled by using decoupling characterization learning. For decoupled user and item embedding, feature preference attention network modeling users have been designed to have different preferences for different features in different behaviors. And finally, aggregating the predictive scores of the users on the articles in all behaviors. Therefore, the recommendation system models more finely-grained user embedding and article embedding on the one hand, and more individuates the recommendation model on the other hand, so that the performance of the recommendation system is improved.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention.
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a diagram of a decoupled multi-behavioral representation study of the present invention.
Detailed Description
In order to clearly illustrate the technical features of the present solution, the present invention will be described in detail below with reference to fig. 1 and 2 of the accompanying drawings.
As shown in fig. 1 to 2, a personalized recommendation method based on decoupling behavior characterization learning is characterized by comprising the following steps:
(a) Preprocessing in an electronic commerce data set to obtain a training set and a testing set;
(b) The data set comprises M users, N articles and B interaction behaviors;
(c) Constructing a personalized cascade GCN module to obtain user embedding and article embedding of B interactive behaviors, wherein the module consists of B GCNs, and personalized information is transmitted between the GCNs by a meta-learning network;
(d) Decoupling the user embedding and the article embedding of the B interaction behaviors, and modeling the user with different feature preferences in different behaviors by using a feature preference attention network;
(e) Calculating the overall preference of the user for the article under the B behaviors;
(f) Model parameters are optimized by an Adam optimizer using model loss.
And learning user embedding and article embedding in each behavior by using the cascade behavior relation, wherein the characteristic information of the user and the article in each behavior is used as the meta-knowledge, and the meta-network model extracts the meta-knowledge to be the personalized characteristic conversion between the modeling behaviors of the user and the article. On this basis, the user embedding and the article embedding in each behavior are decoupled by using decoupling characterization learning. For decoupled user and item embedding, feature preference attention network modeling users have been designed to have different preferences for different features in different behaviors. And finally, aggregating the predictive scores of the users on the articles in all behaviors. Therefore, the recommendation system models more finely-grained user embedding and article embedding on the one hand, and more individuates the recommendation model on the other hand, so that the performance of the recommendation system is improved.
In this embodiment, the step (a) includes the steps of: for an e-commerce data set, the articles interacted by the users in the B behaviors are respectively divided according to a leave-one-out method, the last interaction of each user in the B behaviors is reserved as a test set, the rest data are used as a training set, and the sequence of the B interaction behaviors follows the sequence of the data set or the real behaviors.
In this embodiment, the step (b) includes the steps of:
(B-1) the dataset comprising M user-formed user sets U, N items-formed item sets I, B interaction behaviors-formed B interaction matrices；
(b-2) mapping the user ID and the item ID into one-hot vector matrices, respectivelyAnd->Embedding matrix for user by Xavier method>And an article embedding matrix->Parameter initialization is performed, wherein->The method is an embedded vector dimension, one-hot is the simplest and more common text feature representation method, on word feature representation, the essence of the method directly takes the subscript of a word in a word set as the representation of a word change, and the Xavier method is a neural network initialization method;
(b-3) passing through the formulaAnd formula->Calculating initial embedding vector of user ID and article ID respectively>And->Wherein->For matrix->Is the u-th user's one-hot vector,/->For matrix->One-hot vector of the i-th item,/->，/>，/>Is the embedding vector dimension, P is the user embedding matrix, and Q is the object embedding matrix.
In this embodiment, the step (c) includes the steps of:
(c-1) passing through the formulaCalculating to obtain->User of the seed behavior embeds +.>Graph convolution results of layers->In the formula->L is the number of layers of the graph convolution, +.>The representation represents +.>Item embedding of the species behaviour->Graph convolution result of layers, < >>Representation and user->Interactive item set->Representing a set of users interacting with item i, +.>Representing the size of the collection;
(c-2) passing through the formulaUser embedding +.>In the followingThe number of layers for the graph convolution, +.>Indicate->User of the seed behavior embeds +.>A graph convolution result of the layers;
(c-3) passing through the formulaCalculating to obtain->User-embedded meta-knowledge of the kind of behavior +.>In the formula->For the splicing function->User-embedded +.>Item insert representing action b, +.>Item insert representing aggregation interacting with user u, +.>；
(c-4) passing through the formulaCalculating to obtain->User-embedded personalized feature transformation parameter of seed behavior +.>In the formula->，And->Respectively represent +.>First-layer and second-layer neural network weight matrix of user in seed behavior, +.>And->Respectively represent +.>First of users in a behaviorLayer and layer two neural network bias vectors, < ->Representing an activation function;
(c-5) passing through the formulaCalculating to obtain->Species behavior to->Personalized feature conversion embedded by behavioral user +.>Wherein->Is->User-initiated embedding of seed behavior;
(c-6) passing through the formulaCalculating to obtain->Item embedding of the species behaviour->Graph convolution results of layers->In the formula->，/>The number of layers for the graph convolution, +.>Indicate->User of the seed behavior embeds +.>Graph convolution result of layers, < >>Representation and article->Interactive user set, < > on->Representation and user->Interactive item set->Representing the size of the collection;
(c-7) passing through the formulaItem embedding for calculating b-th behavior>In the followingThe number of layers for the graph convolution, +.>Indicate->Item embedding of the species behaviour->A graph convolution result of the layers;
(c-8) passing through the formulaCalculating to obtain->Item-embedded meta-knowledge of the species behaviour +.>In the formula->For the splicing function->Item insert representing action b, +.>Representing aggregation and article->User-embedded, meta-data of interactions>；
(c-9) passing through the formulaCalculating to obtain->Item-embedded personalized feature transformation parameter of species behavior +.>In the formula->And->The representation represents +.>First and second layer neural network weight matrices of items in a seed behavior,and->Respectively represent +.>First and second layer neural network bias vectors for items in a seed behavior, +.>Representing an activation function;
(c-10) passing through the formulaCalculating to obtain->Species behavior to->Personalized feature conversion for embedding of behavioral items +.>Wherein->Is->Article initialization embedding of species behavior, +.>First->Item-embedded personalized feature transformation parameters of species behavior, < ->The item representing the b-th action is embedded.
In this embodiment, the step (d) includes the steps of:
(d-1) passing throughFormula (VI)Division->Get->User embedding of seed behavior>Is->A continuous block, in which->Representing the number of feature vector partitions, +.>Indicate->User embedding of seed behavior>Corresponding->Individual feature vectors->Representing feature vector dimensions;
(d-2) passing through the formulaDivision->Get->Article embedding of species behavior->Is->A continuous block, in which->Representing the number of feature vector partitions, +.>Indicate->Article embedding of species behavior->Corresponding->Individual feature vectors->Representing feature vector dimensions;
(d-3) passing through the formulaCalculating preference weight of user embedded kth block feature vector to article embedded kth block feature vector of the b-th action>In the formula->Indicate->Attention weight matrix of user in seed behavior, < ->Indicate->Attention offset vector of user in behavior，/>Indicate->Output weight matrix of user in seed behavior, +.>Representing a splicing operation->Representing an activation function;
(d-4) passing through the formulaSplicing to obtain preference weight of user embedded K block feature vector of b-th behavior to object embedded corresponding block feature vector>In the followingRepresenting a splicing function;
(d-5) passing through the formulaCalculating the attention score of the characteristic preference of the user embedded K block characteristic vector of the b-th action on the article embedded corresponding block characteristic vector>In the formula->Representing a normalization function;
(d-6) passing through the formulaUser embedding of the b-th behavior calculated +.>Fusion feature preference attentionNew user embedding after scoringIn the formula->Representation->And->Is multiplied by each dimension of (a). />
In this embodiment, the step (e) includes the steps of:
(e-1) passing through the formulaCalculating user embedding +.>Embedding +.>Preference score of (2), wherein->、/>And->Respectively representing the user-embedded +.>Block feature vector feature preference attention score for embedding item into corresponding block feature vector, user-embedded +.>Block feature vector and item-embedded +.b in behavior>Block feature vector->Is a transposition operation;
(e-2) passing through the formulaCalculating the total score of the user to the item in the B behaviors, wherein +.>Representing user embedding +.>Embedding +.>Is a preference score of (c).
In this embodiment, the step (f) includes the following steps:
(f-1) according to the formulaCalculating BPR loss, wherein ∈R is calculated>For training set, ->，/>To observe the user->And articles->Interaction set existing between->For user->Sampling unobserved items in an interaction set，/>Representing a Sigmoid activation function;
(f-2) according to the formulaUser embedding +.>Is>In the following，/>Representing the distance covariance between the two matrices, < +.>Representing a distance variance of the matrix;
(f-3) according to the formulaCalculating to obtain the user embedded decoupling total loss in B behaviors；
(f-4) according to the formulaItem embedding for calculating b-th behavior>Is>，/>
In the middle of，/>Representing the distance covariance between the two matrices, < +.>Representing a distance variance of the matrix;
(f-5) according to the formulaCalculating to obtain the total loss of the embedded decoupling of the article in the B behaviors；
(f-6) according to the formulaCalculating to obtain a model total loss function>In the formula->、/>The super parameter control module comprises user embedding and article embedding decoupling total loss +.>And model parameters->L2 regularization->，/>Representing model parameters +.>Is regularized by L2.
In order to more intuitively explain how the method is applied to practical problems, the scheme is more thoroughly and specifically described below in combination with practical application of the user to the use behavior of the article in a certain field.
The following is a further description of a heaven cat store, which is one of the largest electronic commerce platforms in China:
data set description: the kitten data set includes 15449 users and 11953 items, and the behavior information includes 873954 browsing behaviors, 195476 shopping cart adding behaviors, and 104329 purchasing behaviors. The cascading order of behaviors is browse- > join shopping cart- > purchase.
And (3) constructing a personalized cascade GCN module according to the step (c) to obtain user embedding and article embedding of the data set browsing behavior, the shopping cart adding behavior and the purchasing behavior of the skyhook mall. Decoupling user embedding and article embedding of the heaven and cat mall data set browsing behaviors, the shopping cart adding behaviors and the purchasing behaviors according to the step (d), and modeling that the user has different characteristic preferences in different behaviors by utilizing a characteristic preference attention network; calculating the overall preference of the user for the item under the actions of browsing, joining in shopping cart and purchasing according to step (e); finally, calculating the total loss of the model according to the step (f) and optimizing the model parameters through an Adam optimizer.
While the foregoing description of the embodiments of the present invention has been presented with reference to the drawings, it is not intended to limit the scope of the invention, but rather, it is apparent that various modifications or variations can be made by those skilled in the art without the need for inventive work on the basis of the technical solutions of the present invention.
Claims (7)
1. A personalized recommendation method based on decoupling multi-behavior characterization learning is characterized by comprising the following steps:
(a) Preprocessing in an electronic commerce data set to obtain a training set and a testing set;
(b) The data set comprises M users, N articles and B interaction behaviors;
(c) Constructing a personalized cascade GCN module to obtain user embedding and article embedding of B interactive behaviors, wherein the module consists of B GCNs, and personalized information is transmitted between the GCNs by a meta-learning network;
(d) Decoupling the user embedding and the article embedding of the B interaction behaviors, and modeling the user with different feature preferences in different behaviors by using a feature preference attention network;
(e) Calculating the overall preference of the user for the article under the B behaviors;
(f) Model parameters are optimized by an Adam optimizer using model loss.
2. The personalized recommendation method based on decoupled behavioral characteristics learning of claim 1, wherein step (a) comprises the steps of: for an e-commerce data set, the articles interacted by the users in the B behaviors are respectively divided according to a leave-one-out method, the last interaction of each user in the B behaviors is reserved as a test set, the rest data are used as a training set, and the sequence of the B interaction behaviors follows the sequence of the data set or the real behaviors.
3. The personalized recommendation method based on decoupled behavioral characteristics learning of claim 1, wherein step (b) comprises the steps of:
(B-1) the dataset comprising M user-formed user sets U, N items-formed item sets I, B interaction behaviors-formed B interaction matrices；
(b-2) mapping the user ID and the item ID into one-hot vector matrices, respectivelyAnd->Embedding matrix for user by Xavier method>And an article embedding matrix->Parameter initialization is performed, wherein->Is the embedded vector dimension;
(b-3) passing through the formulaAnd formula->Calculating initial embedding vector of user ID and article ID respectively>And->Wherein->For matrix->Is the u-th user's one-hot vector,/->Is a matrixOne-hot vector of the i-th item,/->，/>，/>Is the embedded vector dimension.
4. The personalized recommendation method based on decoupled behavioral characteristics learning of claim 1, wherein step (c) comprises the steps of:
(c-1) passing through the formulaCalculating to obtain->User of the seed behavior embeds +.>Graph convolution results of layers->In the formula->L is the number of layers of the graph convolution,indicate->Item embedding of the species behaviour->Graph convolution result of layers, < >>Representation and user->A collection of items that are to be interacted with,representing a set of users interacting with item i, +.>Representing the size of the collection;
(c-2) passing through the formulaUser embedding +.>In the formula->The number of layers for the graph convolution, +.>Indicate->User of the seed behavior embeds +.>A graph convolution result of the layers;
(c-3) passing through the formulaCalculating to obtain->User-embedded meta-knowledge of the kind of behavior +.>In the formula->For the splicing function->User embedding showing behavior b, +.>Item insert representing action b, +.>Representing the aggregation of the item embeddings interacting with user u,；
(c-4) passing through the formulaCalculating to obtain->User-embedded personalized feature transformation parameter of seed behavior +.>In the formula->And->Respectively represent +.>First and second layer neural network weight matrices of users in a seed behavior,and->Respectively represent +.>First-layer and second-layer neural network bias vectors of users in seed behavior, +.>Representing an activation function;
(c-5) passing through the formulaCalculating to obtain->Species behavior to->Personalized feature conversion embedded by behavioral user +.>Wherein->Is->User-initiated embedding of seed behavior;
(c-6) passing through the formulaCalculating to obtain->Item embedding of the species behaviour->Graph convolution results of layers->In the formula->，/>The number of layers to be convolved for the graph,indicate->User of the seed behavior embeds +.>Graph convolution result of layers, < >>Representation and article->Interactive user set, < > on->Representation and user->Interactive item set->Representing the size of the collection;
(c-7) passing through the formulaItem embedding for calculating b-th behavior>In the formula->The number of layers for the graph convolution, +.>Indicate->Item embedding of the species behaviour->A graph convolution result of the layers;
(c-8) passing through the formulaCalculating to obtain->Item-embedded meta-knowledge of the species behaviour +.>In the formula->For the splicing function->The article representing the b-th action is embedded,representing aggregation and article->User-embedded, meta-data of interactions>；
(c-9) passing through the formulaCalculating to obtain->Item-embedded personalized feature transformation parameter of species behavior +.>In the formula->And->Respectively represent +.>First and second layer neural network weight matrices of items in a seed behavior,and->Respectively represent +.>First and second layer neural network bias vectors for items in a seed behavior, +.>Representing an activation function;
(c-10) passing through the formulaCalculating to obtain->Species behavior to->Personalized feature conversion for embedding of behavioral items +.>Wherein->Is->The article of action is initially embedded.
5. The personalized recommendation method based on decoupled behavioral characteristics learning of claim 1, wherein step (d) comprises the steps of:
(d-1) passing through the formulaDivision->Get->User embedding of seed behavior>Is->A continuous block, in which->Representing the number of feature vector partitions, +.>Represent the firstUser embedding of seed behavior>Corresponding->Individual feature vectors->Representing feature vector dimensions;
(d-2) passing through the formulaDivision->Get->Article embedding of species behavior->Is->A continuous block, in which->Representing the number of feature vector partitions, +.>Indicate->Article embedding of species behavior->Corresponding->Individual feature vectors->Representing feature vector dimensions;
(d-3) passing through the formulaCalculating the preference weight of the user embedded kth block feature vector of the b-th action to the article embedded kth block feature vectorIn the formula->Indicate->The attention weight matrix of the user in the behavior,indicate->Attention bias vector of user in seed behavior, +.>Indicate->Output weight matrix of user in seed behavior, +.>Representing a splicing operation->Representing an activation function;
(d-4) passing through the formulaSplicing to obtain preference weight of user embedded K block feature vector of b-th behavior to object embedded corresponding block feature vector>In the followingRepresenting a splicing function;
(d-5) passing through the formulaCalculating the attention score of the characteristic preference of the user embedded K block characteristic vector of the b-th action on the article embedded corresponding block characteristic vector>In the formula->Representing a normalized exponential function;
(d-6) passing through the formulaUser embedding of the b-th behavior calculated +.>New user embedding after feature preference attention score fusionIn the formula->Representation->And->Is multiplied by each dimension of (a).
6. The personalized recommendation method based on decoupled behavioral characteristics learning of claim 1, wherein step (e) comprises the steps of:
(e-1) passing through the formulaCalculating user embedding +.>Embedding +.>Preference score of (2), wherein->、/>And->Respectively representing the user-embedded +.>Block feature vector feature preference attention score for embedding item into corresponding block feature vector, user-embedded +.>Block feature vector and item-embedded +.b in behavior>Block feature vector->Is a transposition operation;
(e-2) passing through the formulaCalculating the total score of the user to the article in the B behaviors, whereinRepresenting user in action bEmbedded->Embedding +.>Is a preference score of (c).
7. The personalized recommendation method based on decoupled behavioral characteristics learning of claim 1, wherein step (f) comprises the steps of:
(f-1) according to the formulaCalculating BPR loss, wherein ∈R is calculated>For training set, ->，/>To observe the user->And articles->Interaction set existing between->For user->Sampling unobserved items in interaction set +.>，/>Representing a Sigmoid activation function;
(f-2) according to the formulaUser embedding +.>Is>In the following，/>Representing the distance covariance between the two matrices, < +.>Representing a distance variance of the matrix;
(f-3) according to the formulaCalculation of user-embedded decoupling total loss +.>；
(f-4) according to the formulaItem embedding for calculating b-th behavior>Is>In the following，/>Representing the distance covariance between the two matrices, < +.>Representing a distance variance of the matrix;
(f-5) according to the formulaCalculating to obtain the total loss of the embedded decoupling of the article in the B behaviors>；
(f-6) according to the formulaCalculating to obtain a model total loss function>In the formula->、/>The super parameter control module comprises user embedding and article embedding decoupling total loss +.>And model parameters->L2 regularization->，/>Representing model parameters +.>Is regularized by L2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310926715.9A CN116645174B (en) | 2023-07-27 | 2023-07-27 | Personalized recommendation method based on decoupling multi-behavior characterization learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310926715.9A CN116645174B (en) | 2023-07-27 | 2023-07-27 | Personalized recommendation method based on decoupling multi-behavior characterization learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116645174A true CN116645174A (en) | 2023-08-25 |
| CN116645174B CN116645174B (en) | 2023-10-17 |
Family
ID=87643757
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310926715.9A Active CN116645174B (en) | 2023-07-27 | 2023-07-27 | Personalized recommendation method based on decoupling multi-behavior characterization learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116645174B (en) |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20220042598A (en) * | 2020-09-28 | 2022-04-05 | (주)브레인콜라 | Personalized recommendation method and system based on future interaction prediction |
| CN114385804A (en) * | 2021-11-12 | 2022-04-22 | 中山大学 | Comment recommendation method of heterogeneous graph attention neural network based on meta-learning |
| CN114519147A (en) * | 2022-02-17 | 2022-05-20 | 云南大学 | Social recommendation method based on GCN enhanced influence diffusion |
| CN114693397A (en) * | 2022-03-16 | 2022-07-01 | 电子科技大学 | Multi-view multi-modal commodity recommendation method based on attention neural network |
| CN114861065A (en) * | 2022-05-31 | 2022-08-05 | 山东省人工智能研究院 | Multi-behavior based personalized recommendation method for cascaded residual error graph convolution network |
| CN115114526A (en) * | 2022-06-30 | 2022-09-27 | 南京邮电大学 | Weighted graph convolution network score prediction recommendation method for multi-behavior enhancement information |
| CN115187343A (en) * | 2022-07-20 | 2022-10-14 | 山东省人工智能研究院 | Multi-behavior recommendation method based on attention map convolution neural network |
| WO2022222037A1 (en) * | 2021-04-20 | 2022-10-27 | 中国科学院深圳先进技术研究院 | Interpretable recommendation method based on graph neural network inference |
| CN115357804A (en) * | 2022-07-19 | 2022-11-18 | 大连民族大学 | Two-stage collaborative filtering multi-behavior recommendation method based on graph convolution network |
| CN115687772A (en) * | 2022-11-09 | 2023-02-03 | 安徽大学 | Sequence recommendation method based on sequence dependence enhanced self-attention network |
| US20230055699A1 (en) * | 2021-08-06 | 2023-02-23 | Rakuten Group, Inc. | Recommender system and method using shared neural item representations for cold-start recommendations |
| CN115878904A (en) * | 2023-02-22 | 2023-03-31 | 深圳昊通技术有限公司 | Intellectual property personalized recommendation method, system and medium based on deep learning |
| CN115905687A (en) * | 2022-11-01 | 2023-04-04 | 山东建筑大学 | Cold start-oriented recommendation system and method based on meta-learning graph neural network |
| CN116010718A (en) * | 2023-01-10 | 2023-04-25 | 合肥工业大学 | Fair personalized recommendation method, equipment and storage medium based on mutual information decoupling |
| CN116167812A (en) * | 2022-12-02 | 2023-05-26 | 重庆邮电大学 | Heterogeneous collaborative filtering method for multi-behavior recommendation |
| CN116340648A (en) * | 2023-03-27 | 2023-06-27 | 广东工业大学 | Knowledge graph attention network recommendation method based on graph collaborative filtering |
| CN116401542A (en) * | 2023-03-20 | 2023-07-07 | 华南理工大学 | Multi-intention multi-behavior decoupling recommendation method and device |
-
2023
- 2023-07-27 CN CN202310926715.9A patent/CN116645174B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20220042598A (en) * | 2020-09-28 | 2022-04-05 | (주)브레인콜라 | Personalized recommendation method and system based on future interaction prediction |
| WO2022222037A1 (en) * | 2021-04-20 | 2022-10-27 | 中国科学院深圳先进技术研究院 | Interpretable recommendation method based on graph neural network inference |
| US20230055699A1 (en) * | 2021-08-06 | 2023-02-23 | Rakuten Group, Inc. | Recommender system and method using shared neural item representations for cold-start recommendations |
| CN114385804A (en) * | 2021-11-12 | 2022-04-22 | 中山大学 | Comment recommendation method of heterogeneous graph attention neural network based on meta-learning |
| CN114519147A (en) * | 2022-02-17 | 2022-05-20 | 云南大学 | Social recommendation method based on GCN enhanced influence diffusion |
| CN114693397A (en) * | 2022-03-16 | 2022-07-01 | 电子科技大学 | Multi-view multi-modal commodity recommendation method based on attention neural network |
| CN114861065A (en) * | 2022-05-31 | 2022-08-05 | 山东省人工智能研究院 | Multi-behavior based personalized recommendation method for cascaded residual error graph convolution network |
| CN115114526A (en) * | 2022-06-30 | 2022-09-27 | 南京邮电大学 | Weighted graph convolution network score prediction recommendation method for multi-behavior enhancement information |
| CN115357804A (en) * | 2022-07-19 | 2022-11-18 | 大连民族大学 | Two-stage collaborative filtering multi-behavior recommendation method based on graph convolution network |
| CN115187343A (en) * | 2022-07-20 | 2022-10-14 | 山东省人工智能研究院 | Multi-behavior recommendation method based on attention map convolution neural network |
| CN115905687A (en) * | 2022-11-01 | 2023-04-04 | 山东建筑大学 | Cold start-oriented recommendation system and method based on meta-learning graph neural network |
| CN115687772A (en) * | 2022-11-09 | 2023-02-03 | 安徽大学 | Sequence recommendation method based on sequence dependence enhanced self-attention network |
| CN116167812A (en) * | 2022-12-02 | 2023-05-26 | 重庆邮电大学 | Heterogeneous collaborative filtering method for multi-behavior recommendation |
| CN116010718A (en) * | 2023-01-10 | 2023-04-25 | 合肥工业大学 | Fair personalized recommendation method, equipment and storage medium based on mutual information decoupling |
| CN115878904A (en) * | 2023-02-22 | 2023-03-31 | 深圳昊通技术有限公司 | Intellectual property personalized recommendation method, system and medium based on deep learning |
| CN116401542A (en) * | 2023-03-20 | 2023-07-07 | 华南理工大学 | Multi-intention multi-behavior decoupling recommendation method and device |
| CN116340648A (en) * | 2023-03-27 | 2023-06-27 | 广东工业大学 | Knowledge graph attention network recommendation method based on graph collaborative filtering |
Non-Patent Citations (3)
| Title |
|---|
| 刘志;林振涛;鄢致雯;陈波;: "基于属性偏好自学习的推荐方法", 浙江工业大学学报, no. 02 * |
| 李琳;唐守廉;: "基于多层注意力表示的音乐推荐模型", 电子学报, no. 09 * |
| 高钰澜等: ""基于轻量图卷积和注意力增强的多行为推荐模型"", 《计算机应用研究》, vol. 39, no. 6, pages 1753 - 1759 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116645174B (en) | 2023-10-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110717098B (en) | Meta-path-based context-aware user modeling method and sequence recommendation method | |
| CN106663124B (en) | Generating and using knowledge-enhanced models | |
| CN112380435B (en) | Document recommendation method and system based on heterogeneous graph neural network | |
| CN112328900A (en) | Deep learning recommendation method integrating scoring matrix and comment text | |
| CN113918834B (en) | Graph convolution collaborative filtering recommendation method fusing social relations | |
| Wang et al. | SDDRS: stacked discriminative denoising auto-encoder based recommender system | |
| Seitlinger et al. | Attention please! a hybrid resource recommender mimicking attention-interpretation dynamics | |
| CN113918832A (en) | Graph convolution collaborative filtering recommendation system based on social relationship | |
| CN112765482A (en) | Product delivery method, device, equipment and computer readable medium | |
| Bouzidi et al. | Deep learning-based automated learning environment using smart data to improve corporate marketing, business strategies, fraud detection in financial services, and financial time series forecasting | |
| CN116401542A (en) | Multi-intention multi-behavior decoupling recommendation method and device | |
| CN115858919A (en) | Learning resource recommendation method and system based on project field knowledge and user comments | |
| CN115687760A (en) | User learning interest label prediction method based on graph neural network | |
| Zhou et al. | Knowledge-based recommendation with hierarchical collaborative embedding | |
| Fang | Making recommendations using transfer learning | |
| Liu et al. | Hands-On Deep Learning Architectures with Python: Create deep neural networks to solve computational problems using TensorFlow and Keras | |
| Talha et al. | Deep learning in news recommender systems: A comprehensive survey, challenges and future trends | |
| CN116955591A (en) | Recommendation language generation method, related device and medium for content recommendation | |
| CN116645174B (en) | Personalized recommendation method based on decoupling multi-behavior characterization learning | |
| CN114861065B (en) | Personalized recommendation method of cascade residual error graph convolution network based on multiple behaviors | |
| CN114610989B (en) | Personalized thesis recommendation method and system based on heterogeneous graph dynamic information compensation | |
| CN115344794A (en) | Scenic spot recommendation method based on knowledge map semantic embedding | |
| CN109299291A (en) | A kind of Ask-Answer Community label recommendation method based on convolutional neural networks | |
| Grigorev | Machine Learning Bookcamp: Build a Portfolio of Real-life Projects | |
| Trivedi | Machine Learning Fundamental Concepts |
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 |