CN113159892A - Commodity recommendation method based on multi-mode commodity feature fusion - Google Patents

Commodity recommendation method based on multi-mode commodity feature fusion Download PDF

Info

Publication number
CN113159892A
CN113159892A CN202110444726.4A CN202110444726A CN113159892A CN 113159892 A CN113159892 A CN 113159892A CN 202110444726 A CN202110444726 A CN 202110444726A CN 113159892 A CN113159892 A CN 113159892A
Authority
CN
China
Prior art keywords
commodity
user
representation
word
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
Application number
CN202110444726.4A
Other languages
Chinese (zh)
Other versions
CN113159892B (en
Inventor
蔡国永
宋亚飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guilin University of Electronic Technology
Original Assignee
Guilin University of Electronic Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guilin University of Electronic Technology filed Critical Guilin University of Electronic Technology
Priority to CN202110444726.4A priority Critical patent/CN113159892B/en
Publication of CN113159892A publication Critical patent/CN113159892A/en
Application granted granted Critical
Publication of CN113159892B publication Critical patent/CN113159892B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/205—Parsing
    • G06F40/216—Parsing using statistical methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • 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
    • G06N3/045—Combinations of networks
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/01—Probabilistic graphical models, e.g. probabilistic networks

Abstract

The invention belongs to the field of commodity recommendation, and particularly relates to a commodity recommendation method based on multi-mode commodity feature fusion. The commodity recommendation method comprises the following steps: constructing a user-commodity bipartite graph according to a commodity sequence purchased by a user, and obtaining vector representation of user nodes and vector representation of commodity nodes through graph convolution; extracting features of comment texts obtained by the commodities through a convolutional neural network to obtain vector representation of the commodity comments; extracting the characteristics of the title and the description information of the commodity through a convolutional neural network to obtain vector representation of the commodity content; connecting the vector representations of the commodity nodes, the comments and the contents to obtain a final representation of the commodity, and taking the vector representation of the user node as a final representation of the user; calculating the similarity between the user final representation and the commodity final representation according to the dot product for sequencing the candidate commodities; parameters in the method are provided through Bayes personalized sorting loss optimization. According to the method, the problem of data sparsity in commodity recommendation can be greatly relieved by utilizing the multi-modal characteristics of the commodities, and the recommendation accuracy is improved.

Description

Commodity recommendation method based on multi-mode commodity feature fusion
Technical Field
The invention relates to a commodity recommendation method, and belongs to the field of commodity recommendation.
Background
Most of the existing commodity recommendation methods only utilize the id of a commodity to extract a collaborative signal hidden in interaction between a user and the commodity in the process of modeling the commodity, so that the commodity is modeled, which generally faces a serious data sparsity problem and greatly restricts the performance of a recommendation system. Although there is some work to take into account review information to capture the product characteristic information contained in the review while mitigating the data sparsity problem, the title and description information of the product itself is rarely utilized. However, comment information is given by users, where information contained in different comments often has different informativeness due to differences in user expression habits and points of interest, and even a lot of noise information may be contained. Unlike review information, the title and description of the item is typically written by the merchant, which may include more and more comprehensive characteristics of the item, and may be more specialized and accurate in presentation. Therefore, when modeling a commodity in recommendation, on the basis of the commodity id and the commodity comment information, the combination of the commodity title and the description information can help to achieve better recommendation performance.
Disclosure of Invention
In order to solve the problems, the invention provides a commodity recommendation method based on multi-mode commodity feature fusion, which comprises the following steps:
s1: constructing a user-commodity bipartite graph according to a commodity sequence purchased by a user in history, and obtaining vector representation of user nodes and vector representation of commodity nodes through graph convolution;
s2: obtaining a comment document of a commodity, and extracting vector representation of the commodity comment through a convolutional neural network;
s3: acquiring the title and description information of the commodity, and extracting vector representation of the commodity content through a convolutional neural network;
s4: obtaining a final representation of the user and a final representation of the good;
s5: calculating the similarity between the user and the commodity;
s6: parameters in the method are provided through Bayes personalized sorting loss optimization.
Further, the constructing the user-commodity bipartite graph in S1 includes:
s11: obtaining a user historical commodity purchase sequence according to implicit feedback or explicit feedback, constructing a user-commodity bipartite graph through the historical commodity purchase sequence, and using a user-commodity adjacency matrix
Figure BDA0003036390090000021
Figure BDA0003036390090000022
Is represented by the formula (I) in which nuAnd npThe number of users and the number of commodities,
Figure BDA0003036390090000023
is a user-commodity interaction matrix, RTIs the transpose of the R and is,
Figure BDA0003036390090000024
s12: in order to utilize the information of the nodes in the user-commodity bipartite graph, an identity matrix is added to A
Figure BDA0003036390090000025
Meanwhile, to avoid gradient disappearance or gradient explosion during training, a diagonal matrix is used
Figure BDA0003036390090000026
Carrying out normalization processing, wherein the value on the diagonal line is the degree of each node in the user-commodity bipartite graph, thereby obtaining
Figure BDA0003036390090000027
Further, the obtaining of the vector representation of the user node and the vector representation of the commodity node in S1 includes:
s13: and carrying out neighbor propagation and aggregation operation on the user-commodity bipartite graph through graph convolution to obtain vector representation of the user node and vector representation of the commodity node.
Further, the specific steps of the graph convolution in S13 are as follows:
s131: converting the unique corresponding id of each user and each commodity into a dense vector through an embedding layer to obtain a user characteristic vector
Figure BDA0003036390090000028
And commodity feature vector
Figure BDA0003036390090000029
Where d is the dimension of the feature vector;
s132: building an embedded table
Figure BDA00030363900900000210
To represent a feature matrix of the user-commodity bipartite graph;
s133: aggregating features of node neighbors using graph convolution of the t layers, wherein the propagation process is defined as:
Figure BDA0003036390090000031
s134: by convolution of the t layers, is obtained from
Figure BDA0003036390090000032
To
Figure BDA0003036390090000033
The t feature matrixes are connected to obtain a final feature matrix
Figure BDA0003036390090000034
Figure BDA0003036390090000035
E is then divided into two parts of the feature matrix
Figure BDA0003036390090000036
Figure BDA0003036390090000037
And
Figure BDA0003036390090000038
vector representations as user nodes, respectively
Figure BDA0003036390090000039
And vector representation of commodity nodes
Figure BDA00030363900900000310
Further, the extracting vector representation of the commodity comment in S2 includes:
s21: integrating comments obtained from each commodity into a comment document of the commodity, and performing preprocessing such as word segmentation, word shape restoration, stop word removal, word removal with extremely high occurrence frequency, word with extremely low occurrence frequency and the like on the comment document of the commodity;
s22: feature extraction is carried out on the commodity comment document through a text feature extractor, and vector representation of the commodity comment is obtained
Figure BDA00030363900900000311
Further, the text feature extractor in S22 includes:
s221: representing a sequence of words of the input text as [ w ]1，w2，...，wl]Where l is the length of the input text;
s222: converting the word sequence representation of S5 into a word vector representation sequence by a word embedding layer
Figure BDA00030363900900000312
Wherein d isvIs the word embedding dimension;
s223: processing the word vector representation sequence using a convolutional neural network to obtain a context sheetWord vector representation sequence [ c ]1，c2，...，cl]Wherein the context of the ith word represents ciThe calculation method comprises the following steps: c. Ci＝LeakyReLU(Wt×v(i-k)：(i+k)+bt)；
S224: computing a weight [ alpha ] for each word vector representation in a sequence of context word vector representations using an attention mechanism1，α2，…，αl]The sequence of context word vector representations is then multiplied by the corresponding weights to obtain a final representation of the input text
Figure BDA0003036390090000041
Wherein alpha isiThe calculation method comprises the following steps:
Figure BDA0003036390090000042
Figure BDA0003036390090000043
further, the extracting the vector representation of the commodity content in S3 includes:
s31: acquiring the title and description information of the commodity, and carrying out preprocessing such as word segmentation, word shape restoration, stop word removal, word removal with extremely high occurrence frequency, word with extremely low occurrence frequency and the like on the information;
s32: extracting the title and description information of the commodity through the same text characteristic extractor in S22 to obtain the vector representation of the commodity content
Figure BDA0003036390090000044
Further, the obtaining of the user final representation and the commodity final representation in S4 includes:
s41: expressing the vector of the commodity node as epVector representation of comments arVector representation of content atConnecting to obtain a final expression p of the commodity; representing the node of the user as euAs the final representation u of the user.
Further, the calculating the similarity between the user and the commodity in S5 includes:
calculating the similarity of the user and the commodity through the dot product of the user final representation and the commodity final representation:
Figure BDA0003036390090000045
further, the parameters in the method for proposing the ranking loss optimization through bayesian personalization in S6 include:
Figure BDA0003036390090000046
drawings
Fig. 1 is a flow chart of a commodity recommendation method according to the present invention.
Fig. 2 is a schematic structural diagram of a commodity recommendation method according to the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
As shown in FIG. 1, the invention provides a commodity recommendation method based on multi-mode commodity feature fusion, which comprises the following steps:
step 1: constructing a user-commodity bipartite graph according to a commodity sequence purchased by a user in history, and obtaining vector representation of user nodes and vector representation of commodity nodes through graph convolution;
specifically, the graph convolution specifically comprises the following steps:
firstly, a user-commodity bipartite graph is constructed according to historical interaction of users and commodities, and a user-commodity adjacency matrix is used
Figure BDA0003036390090000051
Is represented by the formula (I) in which nuAnd npThe number of users and the number of commodities,
Figure BDA0003036390090000052
is a user-commodity interaction matrix, RTIs the transpose of the R and is,
Figure BDA0003036390090000053
Figure BDA0003036390090000054
in order to utilize the information of the nodes in the user-commodity bipartite graph, an identity matrix is added to A
Figure BDA0003036390090000055
Meanwhile, to avoid gradient disappearance or gradient explosion during training, a diagonal matrix is used
Figure BDA0003036390090000056
Carrying out normalization processing, wherein the value on the diagonal line is the degree of each node in the user-commodity bipartite graph, thereby obtaining
Figure BDA0003036390090000057
Then, the unique corresponding id of each user and each commodity is converted into a dense vector through an embedding layer, and a user characteristic vector is obtained
Figure BDA0003036390090000058
And commodity feature vector
Figure BDA0003036390090000059
Where d is the dimension of the feature vector; we build the following embedding Table E0To represent the feature matrix of the user-product bipartite graph:
Figure BDA00030363900900000510
then, we use the graph convolution of the t-layer to aggregate the features of the node neighbors, where the propagation process is defined as:
Figure BDA0003036390090000061
wherein
Figure BDA0003036390090000062
Is a trainable weight matrix and σ is the LeakyRelu activation function.
By convolution of the t layers, is obtained from
Figure BDA0003036390090000063
To
Figure BDA0003036390090000064
The t feature matrices are connected to obtain a final feature matrix E, and then the E is divided into two parts of the feature matrix
Figure BDA0003036390090000065
And
Figure BDA0003036390090000066
vector representations as user nodes, respectively
Figure BDA0003036390090000067
And vector representation of commodity nodes
Figure BDA0003036390090000068
Figure BDA0003036390090000069
Step 2: integrating comments obtained by each commodity into a comment document of the commodity, carrying out word segmentation, word shape restoration, stop word removal, extremely high word removal, extremely low word removal and other processing on the comment document of the commodity, and then processing the comment document of the commodity by using a text feature extractor to obtain vector representation of the commodity comment
Figure BDA00030363900900000610
Specifically, the text feature extractor comprises the following specific steps:
first, word embedding, representing the word sequence of the input text as [ w ]1，w2，...，wl]Where l is the length of the input text, which is then converted into a word vector representation sequence by the word embedding layer
Figure BDA00030363900900000611
Wherein d isvIs the word embedding dimension.
To exploit local context information in the input text, we process the word vector representation sequence using a convolutional neural network, resulting in a context word vector representation sequence [ c ]1，c2，...，cl]Wherein the context of the ith word represents ciThe calculation method comprises the following steps:
ci＝LeakyReLU(Wt×v(i-k)：(i+k)+bt)
wherein v is(i-k)：(i+k)Is the concatenation of word embeddings from the i-k word to the i + k word, WtAnd btRespectively convolution kernel and offset.
Considering that different words in the input text have different informativeness, we use the attention mechanism to compute a weight α for each word vector representation in the sequence of context word vector representations1，α2，…，αl]The sequence of context word vector representations is then multiplied by the corresponding weights to obtain a final representation of the input text
Figure BDA0003036390090000071
Wherein alpha isiThe calculation method comprises the following steps:
Figure BDA0003036390090000072
wherein WaAnd baAre respectively trainable weight matrices andoffset, q is the attention query vector.
And step 3: acquiring the title and description information of the commodity, performing word segmentation, word shape restoration, stop word removal, word with extremely high appearance frequency, word with extremely low appearance frequency and the like on the title and description information of the commodity, and processing the title and description information of the commodity by using the text feature extractor which is the same as the step 2 to obtain vector representation of the content of the commodity
Figure BDA0003036390090000073
And 4, step 4: expressing the vector of the commodity node as epVector representation of comments arVector representation of content atConnecting to obtain a final expression p of the commodity; representing the node of the user as euAs the final representation u of the user.
And 5: calculating the similarity of the user and the commodity through the dot product of the user final representation and the commodity final representation:
Figure BDA0003036390090000074
step 6: parameters in the proposed method are optimized using bayesian personalized ranking loss:
Figure BDA0003036390090000075
wherein
Figure BDA0003036390090000076
Representing the training data in pairs of training data,
Figure BDA0003036390090000077
representing the set of items purchased by user u,
Figure BDA0003036390090000078
indicating a set of goods not purchased by user u; σ is a sigmoid function; theta denotes all trainable model parameters, lambda controlL2 regularizes the strength to prevent overfitting.
The experimental data set is Amazon review three panels of data set CDs _ and _ Vinyl, Movies _ and _ TV and Books. The following table describes the statistics of three data sets:
Figure BDA0003036390090000081
for each data set, 70% of all its interactions were taken as training set, 10% as validation set, and 20% as test set.
Recall @ K and NDCG @ K were chosen as evaluation criteria, and in the experiment, K is 20.
The selected comparison method comprises the following steps: BPRMF, NGCF, deepconnn, the following table shows the corresponding experimental results:
Figure BDA0003036390090000082
from experimental results, it can be seen that the method provided by the invention achieves superior performance to the comparative method on all three data sets.

Claims (10)

1. A commodity recommendation method based on multi-mode commodity feature fusion is characterized by comprising the following steps:
1.1, constructing a user-commodity bipartite graph, and obtaining vector representation of user nodes and vector representation of commodity nodes through graph convolution;
1.2, obtaining a comment document of a commodity, and extracting vector representation of the commodity comment through a convolutional neural network;
1.3, acquiring the title and description information of the commodity, and extracting vector representation of the commodity content through a convolutional neural network;
1.4, obtaining a user final representation and a commodity final representation;
1.5 calculating the similarity between the user and the commodity;
1.6 parameters in the method are proposed through Bayes personalized ranking loss optimization.
2. The method for recommending commodities based on multi-modal fusion of commodity features according to claim 1, wherein the specific method for obtaining the vector representation of the user node and the commodity node in 1.1 is as follows:
2.1, constructing a user-commodity bipartite graph according to the historical records of commodities purchased by users;
and 2.2, carrying out neighbor propagation and aggregation on the user-commodity bipartite graph through graph convolution to obtain vector representation of the user node and vector representation of the commodity node.
3. The method for recommending commodities based on multi-modal commodity feature fusion according to claim 2, wherein the specific steps for constructing the user-commodity bipartite graph in 2.1 are as follows:
3.1 constructing user-Commodity bipartite graph from historical interaction records of users and commodities, Using user-Commodity adjacency matrix
Figure FDA0003036390080000011
Is represented by the formula (I) in which nuAnd npThe number of users and the number of commodities,
Figure FDA0003036390080000012
is a user-commodity interaction matrix, RTIs the transpose of the R and is,
Figure FDA0003036390080000013
Figure FDA0003036390080000021
3.2 to exploit the information of the nodes themselves in the user-commodity bipartite graph, an identity matrix is added to A
Figure FDA0003036390080000022
Meanwhile, to avoid gradient disappearance or gradient explosion during training, a diagonal matrix is used
Figure FDA0003036390080000023
Carrying out normalization processing, wherein the value on the diagonal line is the degree of each node in the user-commodity bipartite graph, thereby obtaining
Figure FDA0003036390080000024
4. The commodity recommendation method based on multi-modal commodity feature fusion as claimed in claim 2, wherein the specific steps of the 2.2 middle graph convolution are as follows:
4.1 converting the unique corresponding id of each user and each commodity into a dense vector through an embedding layer to obtain a user characteristic vector
Figure FDA0003036390080000025
And commodity feature vector
Figure FDA0003036390080000026
Where d is the dimension of the feature vector;
4.2 building Embedded tables
Figure FDA0003036390080000027
To represent a feature matrix of the user-commodity bipartite graph;
4.3 use the graph convolution of the t layers to aggregate the characteristics of the node neighbors, wherein the propagation process is defined as:
Figure FDA0003036390080000028
4.4 obtaining the data from t layers by graph convolution
Figure FDA0003036390080000029
To
Figure FDA00030363900800000210
The t feature matrixes are connected to obtain a final feature matrix
Figure FDA00030363900800000211
Figure FDA00030363900800000212
E is then divided into two parts of the feature matrix
Figure FDA00030363900800000213
And
Figure FDA00030363900800000214
vector representations as user nodes, respectively
Figure FDA00030363900800000215
And vector representation of commodity nodes
Figure FDA00030363900800000216
5. The method for recommending commodities based on multi-modal fusion of commodity features according to claim 1, wherein the vector representation of commodity comments in 1.2 is extracted as follows:
5.1 integrating all comments obtained by each commodity into a comment document of the commodity, and carrying out preprocessing such as word segmentation, word form restoration, stop word removal, word removal with extremely high occurrence frequency, word with extremely low occurrence frequency and the like on the comment document of the commodity;
5.2 extracting the characteristics of the commodity comment documents through a text characteristic extractor to obtain vector representation of the commodity comments
Figure FDA0003036390080000031
6. The method for recommending commodities based on multi-modal fusion of commodity features according to claim 5, wherein said 5.2 Chinese text feature extractor comprises the following steps:
6.1 representing the word sequence of the input text as [ w1，w2，…，wl]Where l is the length of the input text;
6.2 converting word sequence representation into word vector representation sequence by word embedding layer
Figure FDA0003036390080000032
Wherein d isvIs the word embedding dimension;
6.3 processing the word vector representation sequence using a convolutional neural network to obtain a context word vector representation sequence c1，c2，...，cl]Wherein the context of the ith word represents ciThe calculation method comprises the following steps: c. Ci＝LeakyReLU(Wt×v(i-k)：(i+k)+bt)；
6.4 calculate a weight [ α ] for each word vector representation in the sequence of context word vector representations using the attention mechanism1，α2，...，αl]The sequence of context word vector representations is then multiplied by the corresponding weights to obtain a final representation of the input text
Figure FDA0003036390080000033
Wherein alpha isiThe calculation method comprises the following steps:
Figure FDA0003036390080000034
Figure FDA0003036390080000035
7. the method for recommending commodities based on multi-modal fusion of commodity features according to claim 1, wherein the vector representation of commodity contents in 1.3 is extracted by the following method:
7.1, acquiring the title and description information of the commodity, and carrying out preprocessing such as word segmentation, word shape restoration, stop word removal, word removal with extremely high occurrence frequency, word with extremely low occurrence frequency and the like on the information;
7.2 extracting the title and description information of the commodity through the text feature extractor in claim 6 to obtain the vector representation of the commodity content
Figure FDA0003036390080000036
8. The method for recommending commodities based on multi-modal fusion of commodity features according to claim 1, wherein the specific method for obtaining the final user representation and the final commodity representation in 1.4 is as follows:
8.1 representing the vectors of the commodity nodes by epVector representation of comments arVector representation of content atConnecting to obtain a final expression p of the commodity; representing the vector of the user node as euAs the final representation u of the user.
9. The method for recommending commodities based on multi-modal fusion of commodity features according to claim 1, wherein said calculation formula of similarity between user and commodity is:
Figure FDA0003036390080000041
where u is the final representation of the user,
Figure FDA0003036390080000046
representing the transpose of u and p the final representation of the good.
10. The method for recommending commodities based on multi-modal commodity feature fusion according to claim 1, wherein the specific formula of the parameters in the method for proposing loss optimization through Bayesian personalized ranking is as follows:
Figure FDA0003036390080000042
wherein
Figure FDA0003036390080000043
Representing the training data in pairs of training data,
Figure FDA0003036390080000044
representing the set of items purchased by user u,
Figure FDA0003036390080000045
indicating a set of goods not purchased by user u; σ is a sigmoid function; θ represents all trainable model parameters and λ controls the L2 regularization strength to prevent overfitting.
CN202110444726.4A 2021-04-24 2021-04-24 Commodity recommendation method based on multi-mode commodity feature fusion Active CN113159892B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110444726.4A CN113159892B (en) 2021-04-24 2021-04-24 Commodity recommendation method based on multi-mode commodity feature fusion

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110444726.4A CN113159892B (en) 2021-04-24 2021-04-24 Commodity recommendation method based on multi-mode commodity feature fusion

Publications (2)

Publication Number Publication Date
CN113159892A true CN113159892A (en) 2021-07-23
CN113159892B CN113159892B (en) 2022-05-06

Family

ID=76870143

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110444726.4A Active CN113159892B (en) 2021-04-24 2021-04-24 Commodity recommendation method based on multi-mode commodity feature fusion

Country Status (1)

Country Link
CN (1) CN113159892B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114936901A (en) * 2022-05-21 2022-08-23 山东大学 Visual perception recommendation method and system based on cross-modal semantic reasoning and fusion
CN114943588A (en) * 2022-06-15 2022-08-26 厦门大学 Commodity recommendation method based on noise data of graph neural network
CN117786234A (en) * 2024-02-28 2024-03-29 云南师范大学 Multimode resource recommendation method based on two-stage comparison learning

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106227815A (en) * 2015-07-22 2016-12-14 Tcl集团股份有限公司 The personalized application program function of a kind of multi-modal clue recommends method and system thereof
CN109559209A (en) * 2019-01-18 2019-04-02 深圳创新奇智科技有限公司 A kind of electric business clothes based on multi-modal information, which are worn, takes recommended method
CN110263256A (en) * 2019-06-21 2019-09-20 西安电子科技大学 Personalized recommendation method based on multi-modal heterogeneous information
EP3557499A1 (en) * 2018-04-20 2019-10-23 Facebook, Inc. Assisting users with efficient information sharing among social connections
CN111222332A (en) * 2020-01-06 2020-06-02 华南理工大学 Commodity recommendation method combining attention network and user emotion

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106227815A (en) * 2015-07-22 2016-12-14 Tcl集团股份有限公司 The personalized application program function of a kind of multi-modal clue recommends method and system thereof
EP3557499A1 (en) * 2018-04-20 2019-10-23 Facebook, Inc. Assisting users with efficient information sharing among social connections
CN109559209A (en) * 2019-01-18 2019-04-02 深圳创新奇智科技有限公司 A kind of electric business clothes based on multi-modal information, which are worn, takes recommended method
CN110263256A (en) * 2019-06-21 2019-09-20 西安电子科技大学 Personalized recommendation method based on multi-modal heterogeneous information
CN111222332A (en) * 2020-01-06 2020-06-02 华南理工大学 Commodity recommendation method combining attention network and user emotion

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114936901A (en) * 2022-05-21 2022-08-23 山东大学 Visual perception recommendation method and system based on cross-modal semantic reasoning and fusion
CN114943588A (en) * 2022-06-15 2022-08-26 厦门大学 Commodity recommendation method based on noise data of graph neural network
CN117786234A (en) * 2024-02-28 2024-03-29 云南师范大学 Multimode resource recommendation method based on two-stage comparison learning
CN117786234B (en) * 2024-02-28 2024-04-26 云南师范大学 Multimode resource recommendation method based on two-stage comparison learning

Also Published As

Publication number Publication date
CN113159892B (en) 2022-05-06

Similar Documents

Publication Publication Date Title
CN113159892B (en) Commodity recommendation method based on multi-mode commodity feature fusion
CN111222332B (en) Commodity recommendation method combining attention network and user emotion
CN111797321B (en) Personalized knowledge recommendation method and system for different scenes
CN110765260A (en) Information recommendation method based on convolutional neural network and joint attention mechanism
Clinchant et al. A domain adaptation regularization for denoising autoencoders
CN112417306B (en) Method for optimizing performance of recommendation algorithm based on knowledge graph
CN109033294B (en) Mixed recommendation method for integrating content information
CN112650929B (en) Graph neural network recommendation method integrating comment information
CN109460508B (en) Efficient spam comment user group detection method
CN112100512A (en) Collaborative filtering recommendation method based on user clustering and project association analysis
CN109086375A (en) A kind of short text subject extraction method based on term vector enhancing
CN112800344B (en) Deep neural network-based movie recommendation method
WO2020034880A1 (en) Logistics object information processing method, device and computer system
CN112085525A (en) User network purchasing behavior prediction research method based on hybrid model
CN110727855A (en) Personalized recommendation method based on improved factorization machine
CN112150238A (en) Deep neural network-based commodity recommendation method and system
CN116596570A (en) Information comparison system of same product in different E-commerce platforms based on big data analysis algorithm
CN111079011A (en) Deep learning-based information recommendation method
CN106599304B (en) Modular user retrieval intention modeling method for small and medium-sized websites
CN110321565B (en) Real-time text emotion analysis method, device and equipment based on deep learning
CN111930926A (en) Personalized recommendation algorithm combined with comment text mining
CN113159891B (en) Commodity recommendation method based on fusion of multiple user representations
CN114942974A (en) E-commerce platform commodity user evaluation emotional tendency classification method
CN115659961A (en) Method, apparatus and computer storage medium for extracting text viewpoints
CN114997959A (en) Electronic intelligent product marketing recommendation method

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
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20210723

Assignee: Guangxi wisdom Valley Technology Co.,Ltd.

Assignor: GUILIN University OF ELECTRONIC TECHNOLOGY

Contract record no.: X2022450000202

Denomination of invention: A Product Recommendation Method Based on Multimodal Product Feature Fusion

Granted publication date: 20220506

License type: Common License

Record date: 20221125

EE01 Entry into force of recordation of patent licensing contract