CN111291261B - Cross-domain recommendation method integrating labels and attention mechanisms and implementation system thereof - Google Patents

Cross-domain recommendation method integrating labels and attention mechanisms and implementation system thereof Download PDF

Info

Publication number
CN111291261B
CN111291261B CN202010068923.6A CN202010068923A CN111291261B CN 111291261 B CN111291261 B CN 111291261B CN 202010068923 A CN202010068923 A CN 202010068923A CN 111291261 B CN111291261 B CN 111291261B
Authority
CN
China
Prior art keywords
domain
user
vector
resource
field
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.)
Active
Application number
CN202010068923.6A
Other languages
Chinese (zh)
Other versions
CN111291261A (en
Inventor
钱忠胜
涂宇
朱懿敏
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.)
Dragon Totem Technology Hefei Co ltd
Shanghai Juhui Network Technology Co ltd
Original Assignee
Jiangxi University of Finance and Economics
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 Jiangxi University of Finance and Economics filed Critical Jiangxi University of Finance and Economics
Priority to CN202010068923.6A priority Critical patent/CN111291261B/en
Publication of CN111291261A publication Critical patent/CN111291261A/en
Application granted granted Critical
Publication of CN111291261B publication Critical patent/CN111291261B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search customisation based on user profiles and personalisation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/044Recurrent networks, e.g. Hopfield networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/045Combinations of networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • G06N3/084Backpropagation, e.g. using gradient descent
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2216/00Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
    • G06F2216/03Data mining
    • YGENERAL 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
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02DCLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Biophysics (AREA)
  • Evolutionary Computation (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses a cross-domain recommendation method integrating labels and an attention mechanism and an implementation system thereof, wherein the recommendation method comprises the steps of firstly selecting and constructing cross-domain fusion labels, and respectively carrying out weighted summation on label vectors of a source domain and a target domain to obtain resource vectors; secondly, obtaining preferences of a user in a source field and a target field according to an interest mining algorithm based on an attention mechanism; then, learning label mapping between the source domain and the target domain according to a cross-domain label mapping algorithm based on the BP neural network to obtain comprehensive preference of a user in the target domain; and finally, recommending the items with high comprehensive preference similarity with the user in the target field to the user through a cross-field recommendation algorithm integrating the label mapping and the attention mechanism. By comprehensively considering the preferences of the user in different fields through cross-field recommendation, the problem of cold start of the user in target field recommendation is improved; meanwhile, in the cross-domain recommendation system, recommendation results are diversified by analyzing preferences of users in different domains.

Description

Cross-domain recommendation method integrating labels and attention mechanisms and implementation system thereof
Technical Field
The invention relates to the technical field of information recommendation methods and systems, in particular to a cross-domain recommendation method integrating labels and attention mechanisms and an implementation system thereof.
Background
With the rapid development of internet technology, the number of various social application software such as QQ, weChat, microblog and the like is rapidly increased, and various information is presented to people, so that the daily life of people is greatly enriched. However, there are some unavoidable problems in this process, such as information flooding and information getting lost. To help each user get better resources, personalized recommendation techniques have evolved. Currently, related researchers apply personalized recommendation techniques to resource recommendation in various fields, including fields such as e-commerce, location-based services, medical treatment, and the like, in addition to movies, music, sports, and the like. The application scope of the personalized recommendation technology in the future is wider and wider.
Most conventional recommendation algorithms focus on the explicit preference of the user for items, i.e. numerical scoring. As electronic commerce systems continue to expand, users ' scoring data becomes very sparse, and simply analyzing the user's scoring data is insufficient to fully understand the user's needs. The implicit preferences of the user, such as browsing records, clicking records and label information of the user, contain rich information, and can obviously improve the recommendation result.
At present, most of recommendation technologies are single-domain recommendation technologies, namely, users are recommended only by using interests of the users in a single domain, and recommendation technologies combining multiple domains are few. In single-field recommendation, the problems of sparse data, cold start of users, cold start of commodities and the like often exist, so that the performance of a recommendation system is reduced, and the recommendation accuracy is reduced.
Disclosure of Invention
In view of the foregoing, it is necessary to provide a cross-domain recommendation method and implementation system thereof that enables a fusion tag and attention mechanism with more diversified features of a recommendation structure by analyzing user preferences in different domains.
A cross-domain recommendation method integrating labels and attention mechanisms comprises the following steps:
selecting and constructing a cross-domain fusion label, fusing two similar domains into a new domain, taking the new domain as a source domain recommended by the cross-domain, and respectively carrying out weighted summation on label vectors of the source domain and the target domain to obtain a resource vector of each resource;
secondly, learning a time sequence relation between a user and a resource through a long-short-term memory algorithm LSTM according to an interest mining algorithm based on an attention mechanism, and introducing the attention mechanism to obtain the preference of the user in a specified time period of a source field and a target field;
thirdly, according to a cross-domain label mapping algorithm based on the BP neural network, a label mapping between a source domain and a target domain is learned through a three-layer BP neural network, and after a preference vector of a user source domain is mapped to the target domain, the preference vector of the user source domain and the preference vector of the user in the target domain are weighted and summed to obtain comprehensive preference of the user in the target domain;
and step four, a cross-domain recommendation algorithm integrating tag mapping and an attention mechanism calculates the similarity between the resource vector which is not browsed by the user in the target domain and the comprehensive preference of the user according to the comprehensive preference of the user in the source domain and the target domain, and recommends the first N items to the user.
Further, the selecting and constructing a cross-domain fusion label flow in the step one includes:
step 1-1, preprocessing data in a source field and a target field;
collecting commonly used labels in two similar fields A and B and a target field C as custom labels DT, retrieving resources related to the custom labels to obtain resource labels RT corresponding to the resources, removing repeated labels to obtain RT-DT matrixes, wherein each column of the matrixes is custom label DT vectors, each action resource label RT vector, and uniformly measuring the rest custom label vectors;
step 1-2, selecting and constructing a cross-domain fusion tag;
analyzing similarity of the same custom tag DT vector and the same resource tag RT vector in the A, B field, and calculating similarity of the same DT vector and the same RT vector in the user A and B resources by using cosine similarity, wherein the similarity is shown in a formula (1):
Figure SMS_1
Figure SMS_2
wherein ,
Figure SMS_3
and
Figure SMS_4
Represents the same DT or RT in the A-domain and B-domain, respectively,>
Figure SMS_5
Figure SMS_6
labels->
Figure SMS_7
and
Figure SMS_8
Vector representations of (a); to ensure recommended quality, labels with similarity below a threshold are culled;
in each field of constructed tag vectors, the custom tag DT and the resource tag RT are filtered, and the same resource tag RT vector is weighted and summed according to the interests of users in each field to obtain an A-B field tag vector matrix, as shown in the formula (2) and the formula (3):
Figure SMS_9
Figure SMS_10
Figure SMS_11
Figure SMS_12
wherein ,
Figure SMS_13
to fuse tags across domains->
Figure SMS_14
For labels->
Figure SMS_15
Is a vector representation of (c).
The resource labels RT of the resources are ordered according to the number of times the labels are marked by users, the labels in front are more closely related to the resources than the labels in back, and the labels of each resource are assigned with weights according to the formula (4):
Figure SMS_16
Figure SMS_17
the corresponding weight of each tag vector of all the resources is obtained by using the formula (4) for the A-B field and the C field, and then the weight summation of the tag vectors is carried out to obtain the resource vector of each resource, as shown in the formula (5):
Figure SMS_18
Figure SMS_19
wherein ,
Figure SMS_20
tag vector for each tag of a resource, +.>
Figure SMS_21
Is a resource vector of resources.
Further, the data preprocessing of the source domain and the target domain in the step 1-1 comprises the following steps:
step 1-1-1, respectively acquiring labels from texts of A, B domain resources by using a TF-IDF technology, and extracting labels which are commonly used by m users and are simultaneously displayed in two domains, namely a custom label DT, from the acquired labels, wherein the labels can better represent resource characteristics and are marked as DTs; then searching the resources related to DT in A, B field, displaying the label corresponding to each resource, namely resource label RT, and recording as RTs;
step 1-1-2, the labels commonly used by N users are collected from the C field by using TF-IDF technology and are marked as DTt. Then searching the resources related to the DT, and displaying the label corresponding to each resource, and marking the label as RTt;
step 1-1-3, for the collected labels, finishing word segmentation by using an NLPIR Chinese word segmentation system, removing repeated labels, and counting the occurrence frequency of each RT in the resources corresponding to each DT, wherein the larger the vector value is, the tighter the relation between RT and DT is;
step 1-1-4, because the total number of resources retrieved by different DTs is different, dividing each component of all DT vectors by the largest component of the vector to obtain a DT vector with uniform metrics.
Further, the interest mining algorithm based on the attention mechanism in the second step includes the following steps:
learning a timing relationship between a user and a resource using a long-short-term memory algorithm, assuming that an update interval of a memory cell layer is a time step
Figure SMS_22
Figure SMS_23
Is the memory cell layer at time->
Figure SMS_24
Is input to the computer;
Figure SMS_25
And->
Figure SMS_26
Is a weight matrix;
Figure SMS_27
Is a bias vector; the method comprises the following steps:
step 2-1, at each time step
Figure SMS_28
Multiplying the input information of the input gate by the weight value, adding the offset, and calculating to obtain a control variable +.>
Figure SMS_29
And a new input vector->
Figure SMS_30
Specifically, the method is shown as a formula (6) and a formula (7):
Figure SMS_31
Figure SMS_32
Figure SMS_33
Figure SMS_34
step 2-2, at each time step
Figure SMS_35
Calculating the control variable +.>
Figure SMS_36
And candidate state->
Figure SMS_37
Multiplication, namely multiplying forgetting gate input information by weight, adding the product of the input gate input information and the weight, and then taking the memory unit state from +.>
Figure SMS_38
Update to->
Figure SMS_39
Specifically, the method is shown as a formula (8) and a formula (9):
Figure SMS_40
Figure SMS_41
Figure SMS_42
Figure SMS_43
step 2-3, continuously calculating the value of the output gate in the updated memory cell state, specifically as shown in the following formulas (10) and (11):
Figure SMS_44
Figure SMS_45
Figure SMS_46
Figure SMS_47
step 2-4, calculating a loss function and minimizing it using a gradient descent method, as shown in formula (12):
Figure SMS_48
Figure SMS_49
after being calculated by a long-short-term memory algorithm LSTM layer, each time step hidden state of the LSTM is used as an output result to be output to an attention layer so as to capture the dependency relationship among sequences, and a context vector representation corresponding to an output sequence i is obtained after weighted summation
Figure SMS_50
Description of specific formulasAs shown in the formula (13) and the formula (14):
Figure SMS_51
Figure SMS_52
Figure SMS_53
Figure SMS_54
wherein ,
Figure SMS_55
is LSTM NoiOutput of individual time steps,/->
Figure SMS_56
Represent the firstiTime step and No. HjThe normalized weight is output in each time step, and the similarity calculation function adopts matrix transformation represented by W.
Further, according to the interest mining algorithm based on the attention mechanism, after all resource vectors of the histories of the user in the source domain and the target domain are calculated through the LSTM layer and the attention layer respectively, preference vectors of the user in the source domain and the target domain are obtained.
Further, the cross-domain label mapping algorithm based on the BP neural network in the third step comprises the following procedures:
the label mapping between different fields is learned through a three-layer BP neural network, firstly, n labels which are used most by a user are respectively collected in an A-B field and a C field, the weight of each label in the two fields is respectively calculated according to a formula (4), and then the feature vectors of the user in the A-B field and the C field are respectively calculated through the weights, wherein the feature vectors are specifically shown as a formula (15) and a formula (16):
Figure SMS_57
Figure SMS_58
Figure SMS_59
Figure SMS_60
wherein ,
Figure SMS_61
for the feature vector of the user in the A-B field, < >>
Figure SMS_62
and
Figure SMS_63
The weight of each label in the A-B field and the characteristic vector of the label are obtained;
Figure SMS_64
For the feature vector of the user in the C field, +.>
Figure SMS_65
and
Figure SMS_66
The weight of each label in the C field and the characteristic vector of the label are obtained;
then, by
Figure SMS_67
For inputting vectors, ++>
Figure SMS_68
For the actual output vector, learning +.>
Figure SMS_69
and
Figure SMS_70
The mapping is shown as the following formulas (17) - (21):
the mapping relation between the input layer and the hidden layer is shown in the formula (17):
Figure SMS_71
Figure SMS_72
the activation function through the hidden layer is shown in equation (18):
Figure SMS_73
Figure SMS_74
the mapping relationship from the hidden layer to the output layer is shown in the formula (19):
Figure SMS_75
Figure SMS_76
the activation function through the output layer is shown in equation (20):
Figure SMS_77
Figure SMS_78
the loss function of the BP neural network is shown as a formula (21):
Figure SMS_79
Figure SMS_80
wherein in the formulas (14) and (16),
Figure SMS_81
nthe number of hidden layer units for BP neural network, i.e.
Figure SMS_82
, wherein ,
Figure SMS_83
For the number of input layer units, < > for>
Figure SMS_84
Is the number of output layer elements. />
Further, the number of hidden layer units of the BP neural networknThe method is determined by adopting a golden section method.
Further, the cross-domain recommendation algorithm fusing the tag mapping and the attention mechanism in the fourth step specifically includes the following steps:
step 4-1, setting the user preference vector of the history record in the A-B field after being processed by the LSTM layer and the attention layer as
Figure SMS_85
The user preference vector of the history record in the C field after being processed by the LSTM network is +.>
Figure SMS_86
The mapping network between the source domain and the target domain is +.>
Figure SMS_87
Will be +.>
Figure SMS_88
and
Figure SMS_89
Weighted summation to obtain final user resource vector:
Figure SMS_90
Figure SMS_91
wherein ,
Figure SMS_92
resource vector representing user->
Figure SMS_93
Representing the number of target domain resources in the user history,
Figure SMS_94
representing the number of source domain resources in the user history;
step 4-2, after the final user resource vector is obtained by calculation, calculating the similarity between the user resource vector and the resource vector in the target field in the resource library, wherein the similarity is specifically shown as a formula (23):
Figure SMS_95
Figure SMS_96
wherein ,
Figure SMS_97
representing user resource vector, ++>
Figure SMS_98
A resource vector representing a target domain in a resource pool.
Further, in the calculation of the final user resource vector, according to different browsing amounts of the user in the target field, the similarity of the resource vector which is not browsed in the target field by the user is directly affected; when the data volume browsed by the user in the target field is small, the preference mapping of the user in the source field can be used for obtaining the preference calculation of the user in the target field, and the similarity of the resource vectors not browsed by the user in the target field; when the browsing data quantity of the user in the target field is far greater than that of the user in the source field, the data sparsity does not exist, which is equivalent to obtaining a final recommendation result directly according to the browsed resource vector in the target field.
And a system for implementing a cross-domain recommendation method of a fusion tag and an attention mechanism, where the system is configured to implement a cross-domain recommendation method of a fusion tag and an attention mechanism according to any one of the above, and the system includes:
the method comprises the steps of obtaining resource labels of resources corresponding to the custom labels by utilizing commonly used custom labels in two similar fields A and B based on a label cross-domain resource fusion algorithm module, analyzing the similarity of the custom label DT vector and the same resource label RT vector in the A, B field, and eliminating the resource label vector with the similarity lower than a threshold value; respectively carrying out weighted summation on resource tag vectors of a source field and a target field C which are formed by two similar fields A and B to obtain resource vectors of each resource of the source field and the target field;
the interest mining algorithm module based on the attention mechanism obtains preference vectors of the user in the source field and the target field by utilizing all resource vectors of the history records of the user in the source field and the target field and through deep learning of an LSTM layer and an attention layer of the long-term memory algorithm;
the cross-domain label mapping algorithm module based on the BP neural network is used for mapping the preference vector of the user source domain to the target domain by using the three-layer BP neural network to obtain the comprehensive preference of the user in the target domain;
and the cross-domain recommendation algorithm module is used for combining the preferences of the user in the source domain and the target domain to obtain the comprehensive preferences of the user in the target domain, and then calculating the similarity between the resource vector which is not browsed in the target domain by the user and the comprehensive preferences of the user to obtain a recommendation list of the user in the target domain.
In the cross-domain recommendation method of the fusion tag and the attention mechanism and the implementation system thereof, the cross-domain fusion tag is constructed by fusing the item tags of two similar domains, the two similar domains are fused into a new domain, the new domain is used as a source domain of the cross-domain recommendation, and then a domain with lower correlation degree is used as a target domain, so that the data of the source domain of the cross-domain recommendation is richer. The current preference of the user is calculated in the source field and the target field respectively through the attention introducing mechanism, so that the recommendation result is more time-efficient. The mapping relation of the overall preference of the user in the source field and the target field is obtained through the BP neural network, the mapping relation is applied to the current preference of the user, the mapping relation is mapped from the source field to the target field, and the final recommendation result is more accurate by combining with the independent recommendation result of the target field.
Drawings
Fig. 1 is a schematic structural diagram of an implementation system of a cross-domain recommendation method of a fusion tag and an attention mechanism according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of a three-layer BP neural network of an implementation system of a cross-domain recommendation method of the fusion tag and the attention mechanism according to the embodiment of the present invention.
Detailed Description
In this embodiment, a cross-domain recommendation method and an implementation system thereof that integrate a label and an attention mechanism are taken as an example, and the present invention will be described in detail below with reference to specific embodiments and accompanying drawings.
Referring to fig. 1 and fig. 2, a cross-domain recommendation method for fusing a tag and an attention mechanism is shown in an embodiment of the present invention.
The cross-domain resource recommendation is realized by using the labels and the attention mechanism, and the comprehensive preference of the user in the target domain is obtained by mapping the preference of the user in the source domain to the target domain and combining the preference of the user in the target domain.
Because of the sparsity of the data in a single field, the accuracy of recommendation is reduced, and if the data in a plurality of fields can be combined, the reliability of a recommendation result can be greatly improved. If the data of the user in the target field is sparse, the preference of the source field can be obtained through the mapping network to obtain the corresponding target field preference, and if the data of the user in the source field is sparse, the data of the user in the source field can be solved by fusing a similar field. If the data richness of the user in the target field is much higher than the data of the user in the fused source field, the preference of the user can be learned directly through the data of the user in the target field.
Two similar fields are fused into a new field by constructing a cross-field label vector, and the new field is used as a source field of cross-field recommendation. Firstly, extracting labels of each field by using a natural language processing method, customizing corresponding label vectors, fusing the label vectors with similarity exceeding a specified threshold in the two fields, and customizing cross-field fusion labels. Second, by introducing an attention mechanism in combination with LSTM, user preferences over a specified period of time are calculated in the source domain and the target domain, respectively. And thirdly, a BP neural network is used for learning a mapping relation between the source domain label and the target domain label, and data of the target domain and the source domain are combined, so that a recommendation result is more accurate. Finally, an overall framework of a cross-domain recommendation model is described, the obtained user source domain preferences are mapped to the target domain through a learned mapping network, and a final result is obtained by combining the user source domain preferences with the user target domain preferences.
1. Cross-domain resource fusion of labels
The fields are not isolated, a certain relation exists between the fields, and when the similarity exceeds a certain degree, the fields can be combined into a new field. The number of resources in the new domain is the sum of the number of resources in two similar domains, and the sum is used as a source domain recommended across domains, so that the information of the source domain can be enriched.
1.1 data Pre-processing
The method is characterized in that A and B are two similar fields, the combined field of A and B is taken as a source field, the other field C with larger span is taken as a target field, and the processing steps are as follows:
1) The TF-IDF technology is used for respectively acquiring labels from texts of the A and B domain resources, and then m labels which are commonly used by users and are simultaneously displayed in the two domains, namely custom labels (DT for short), are extracted from the acquired labels, and the labels can well represent the resource characteristics and are marked as DTs. Then, the resources related to DT are searched in A, B field, and then the label corresponding to each resource, i.e. the resource label (RT for short), is displayed and is recorded as the RTs.
2) The TF-IDF technique was used to collect N labels commonly used by users from the C field, denoted DTt. And then searching the resources related to the DT, and displaying the label corresponding to each resource, and recording as RTt.
3) And for the collected labels, finishing word segmentation by using an NLPIR Chinese word segmentation system, removing repeated labels, and counting the occurrence frequency of each RT in the resources corresponding to each DT, wherein the larger the vector value is, the tighter the relation between RT and DT is.
4) Because the total number of resources retrieved by different DTs is different, dividing each component of all DT vectors by the largest component of the vector results in a uniformly measured DT vector.
1.2 selection and construction of Cross-Domain fusion tags
We need to analyze the correlation of the same DT vector and the same RT vector in A, B domain, which can be exploited and cross-domain recommended only if the correlation is large enough. If the same DT vector in the a-field and the B-field or the single components of the same RT vector are similar they cannot be said to be highly correlated, but if all the components are similar, then the correlation of the two is considered to be sufficiently high. And calculating the similarity of the same DT vector and the same RT vector in the resources of the user A and the user B by using the cosine similarity, as shown in the formula (1).
Figure SMS_99
Figure SMS_100
wherein ,
Figure SMS_101
and
Figure SMS_102
Represents the same DT or RT in the A-domain and B-domain, respectively,>
Figure SMS_103
Figure SMS_104
labels->
Figure SMS_105
and
Figure SMS_106
Is a vector representation of (c). To ensure recommended quality, labels with similarity below a threshold are culled.
After the label vector of each field is constructed and the DT and RT are screened, the same RT vector is weighted and summed according to the interests of the user in each field, and the A-B field label vector matrix is obtained, as shown in the formula (2) and the formula (3).
Figure SMS_107
Figure SMS_108
Figure SMS_109
Figure SMS_110
wherein ,
Figure SMS_111
to fuse tags across domains->
Figure SMS_112
For labels->
Figure SMS_113
Is a vector representation of (c).
The RT of the resource is ordered according to the number of times the tag is marked by the user, the preceding tag is more closely related to the resource than the following tag, and the tag of each resource is assigned a weight according to equation (4).
Figure SMS_114
Figure SMS_115
And (3) respectively using the formula (4) to obtain the weight corresponding to each tag vector of all the resources in the A-B field and the C field, and then carrying out weighted summation on the tag vectors to obtain the resource vector of each resource, wherein the weight is shown in the formula (5).
Figure SMS_116
Figure SMS_117
wherein ,
Figure SMS_118
tag vector for each tag of a resource, +.>
Figure SMS_119
As a resource vector of resources, the process is shown in algorithm 1.
Figure SMS_120
2. Interest mining algorithm based on attention mechanism
The attention points of different people to the resources are different, some people may like the resources of the history subject, some people like the resources of the science fiction class, and some people like the resources of the reasoning class. To accurately discover the user's preferences, the present software uses LSTM to learn the timing relationship between the user and the resource. See in particular the model below.
Assume that each time step is
Figure SMS_121
The memory cell layer will be updated and assume:
1)
Figure SMS_122
is the memory cell layer at time->
Figure SMS_123
I.e. the user's browsing record.
2)
Figure SMS_124
And->
Figure SMS_125
Is a weight matrix.
3)
Figure SMS_126
Is a bias vector. The method comprises the following steps:
(1) at each time step
Figure SMS_127
Multiplying the input information of the input gate by the weight value, adding the offset, and calculating to obtain a control variable ∈of the input gate>
Figure SMS_128
And a new input vector->
Figure SMS_129
Specifically, the formula (6) and the formula (7) are shown. />
Figure SMS_130
Figure SMS_131
Figure SMS_132
Figure SMS_133
(2) At each time step
Figure SMS_134
The control variable +.>
Figure SMS_135
And candidate state->
Figure SMS_136
Multiplication, namely multiplying forgetting gate input information by weight, adding the product of the input gate input information and the weight, and then taking the memory unit state from +.>
Figure SMS_137
Update to->
Figure SMS_138
Specifically, the formula (8) and the formula (9) are shown.
Figure SMS_139
Figure SMS_140
Figure SMS_141
Figure SMS_142
(3) After the updated memory cell state, the output gate value can be continuously calculated, specifically shown in the following formulas (10) and (11).
Figure SMS_143
Figure SMS_144
Figure SMS_145
Figure SMS_146
(4) The loss function is calculated and minimized using a gradient descent method as shown in equation (12).
Figure SMS_147
Figure SMS_148
After passing through the LSTM layer, the hidden state of each time step of the LSTM is an output result, and at the moment, each time step of the LSTM output is output to the attention layer, so that the dependency relationship among the sequences can be captured, and after weighted summation, the context vector representation corresponding to the output sequence i is obtained
Figure SMS_149
The specific formula descriptions are shown in the formula (13) and the formula (14).
Figure SMS_150
Figure SMS_151
Figure SMS_152
Figure SMS_153
wherein ,
Figure SMS_154
is LSTM NoiOutput of individual time steps,/->
Figure SMS_155
Represent the firstiTime step and No. HjThe normalized weights of the outputs of the time steps are used, and the similarity calculation function is represented by matrix transformation, which is represented by W. And finally, a full connection layer is used to obtain the final output probability. This process is shown in algorithm 2. />
Figure SMS_156
All resource vectors of the histories of the user in the source domain and the target domain respectively pass through the LSTM layer and the attention layer to obtain preference vectors of the user in the source domain and the target domain, the preference vectors of the user in the source domain are mapped to the target domain, and a final result is obtained by combining the preference of the user in the target domain, and the mapping process is specifically described in the next part.
3. Cross-domain label mapping algorithm based on BP neural network
There is also a certain correspondence between the interests of the user among different fields. For example, users who like to watch comedy are mostly biased to listen to rock-and-roll type music, while users who like to watch horror generally like to listen to music with more pronounced melody changes. The label mapping among different fields is learned through a three-layer BP neural network, firstly, n labels which are used most by a user are respectively collected in the A-B field and the C field, the weight of each label in the two fields is respectively calculated according to a formula (4), and then the feature vectors of the user in the A-B field and the C field are respectively calculated in a weighted mode, as shown in a formula (15) and a formula (16).
Figure SMS_157
Figure SMS_158
Figure SMS_159
Figure SMS_160
wherein ,
Figure SMS_161
for the feature vector of the user in the A-B field, < >>
Figure SMS_162
and
Figure SMS_163
Weights for each tag in A-B domain and the sameFeature vectors of the tags;
Figure SMS_164
For the feature vector of the user in the C field, +.>
Figure SMS_165
and
Figure SMS_166
The weight of each label in the C field and the characteristic vector of the label are obtained.
Then, by
Figure SMS_167
For inputting vectors, ++>
Figure SMS_168
For the actual output vector, learning +.>
Figure SMS_169
and
Figure SMS_170
The mapping is shown as the following formulas (17) - (21):
1) The mapping relation between the input layer and the hidden layer is shown in the formula (17):
Figure SMS_171
Figure SMS_172
2) The activation function through the hidden layer is shown in equation (18):
Figure SMS_173
Figure SMS_174
3) The mapping relationship from the hidden layer to the output layer is shown in the formula (19):
Figure SMS_175
Figure SMS_176
4) The activation function through the output layer is shown in equation (20):
Figure SMS_177
Figure SMS_178
5) The loss function of the BP neural network is shown as a formula (21):
Figure SMS_179
Figure SMS_180
wherein in the formulas (14) and (16),
Figure SMS_181
a concrete model structure is shown in fig. 2.
In the BP neural network, the number of hidden layer units is directly related to the requirements of the problem and the number of input and output units. Too few numbers and too few information are acquired, under-fitting occurs. Too many, increasing training time, overfitting is likely to occur and generalization ability is poor. The software uses the golden section method to determine the number of hidden layer units of the BP neural network. That is to say,
Figure SMS_182
, wherein ,
Figure SMS_183
For the number of input layer units, < > for>
Figure SMS_184
Is an output layer unitNumber of parts. Finally, a gradient descent method is used to minimize the loss function. This process is shown in algorithm 3.
Figure SMS_185
After mapping the preference vector of the user source domain to the target domain, the preference vector of the user in the target domain is weighted and summed with the preference vector of the user in the target domain in a certain manner to obtain the comprehensive preference of the user in the target domain, and the process is described in detail in the next part.
4. Cross-domain recommendation framework integrating tag mapping and attention mechanisms
From the first three sections, a cross-domain recommendation algorithm that fuses the tag mapping and the attention mechanism will be given below. After mapping the preference vector of the user source domain to the target domain, it needs to be weighted and summed with the preference vector of the user target domain in a certain way.
The meaning of cross-domain recommendation is to solve the problem of sparse data of users in the target domain. The data of the user in the target area is rich enough relative to the data of the source area, so that the data of the user in the target area is used more, the weight can be determined according to the resource number ratio of the user in the source area and the target area, and the whole framework of the algorithm is shown in figure 1.
Recording the user preference vector of the history record in the A-B field after being processed by the LSTM layer and the attention layer as
Figure SMS_186
The user preference vector of the history record in the C field after being processed by the LSTM network is +.>
Figure SMS_187
The mapping network between the source domain and the target domain is +.>
Figure SMS_188
Will be +.>
Figure SMS_189
and
Figure SMS_190
And (5) weighting and summing to obtain a final user resource vector.
Figure SMS_191
Figure SMS_192
wherein ,
Figure SMS_193
resource vector representing user->
Figure SMS_194
Representing the number of target domain resources in the user history,
Figure SMS_195
representing the number of source domain resources in the user history. If the data volume browsed by the user in the target field is small, the preference in the target field can be obtained through the preference mapping in the source field; if the data of the user in the target field is far more than the data of the user in the source field, the data sparsity does not exist, which is equivalent to obtaining a final result directly according to the result recommended in the single field.
After the final user resource vector is calculated, the similarity between the user resource vector and the resource vector of the target field in the resource library is calculated by using the formula (23), and the TOPN list is recommended to the user.
Figure SMS_196
Figure SMS_197
wherein ,
Figure SMS_198
representing user resource vector, ++>
Figure SMS_199
A resource vector representing a target domain in a resource pool. This process is shown in algorithm 4. />
Figure SMS_200
And the algorithm 4 combines the preference of the user source field with the preference of the target field to obtain the comprehensive preference of the user in the target field, calculates the similarity between the comprehensive preference and the resource vector which is not browsed by the user in the target field, and recommends the first N items to the user. The more resource rich areas have a greater impact on the end result.
And a system for implementing a cross-domain recommendation method of a fusion tag and an attention mechanism, where the system is configured to implement a cross-domain recommendation method of a fusion tag and an attention mechanism according to any one of the above, and the system includes:
the method comprises the steps of obtaining resource labels of resources corresponding to the custom labels by utilizing commonly used custom labels in two similar fields A and B based on a label cross-domain resource fusion algorithm module, analyzing the similarity of the custom label DT vector and the same resource label RT vector in the A, B field, and eliminating the resource label vector with the similarity lower than a threshold value; respectively carrying out weighted summation on resource tag vectors of a source field and a target field C which are formed by two similar fields A and B to obtain resource vectors of each resource of the source field and the target field;
the interest mining algorithm module based on the attention mechanism obtains preference vectors of the user in the source field and the target field by utilizing all resource vectors of the history records of the user in the source field and the target field and through deep learning of an LSTM layer and an attention layer of the long-term memory algorithm;
the cross-domain label mapping algorithm module based on the BP neural network is used for mapping the preference vector of the user source domain to the target domain by using the three-layer BP neural network to obtain the comprehensive preference of the user in the target domain;
and the cross-domain recommendation algorithm module is used for combining the preferences of the user in the source domain and the target domain to obtain the comprehensive preferences of the user in the target domain, and then calculating the similarity between the resource vector which is not browsed in the target domain by the user and the comprehensive preferences of the user to obtain a recommendation list of the user in the target domain.
In the cross-domain recommendation method of the fusion tag and the attention mechanism and the implementation system thereof, the cross-domain fusion tag is constructed by fusing the item tags of two similar domains, the two similar domains are fused into a new domain, the new domain is used as a source domain of the cross-domain recommendation, and then a domain with lower correlation degree is used as a target domain, so that the data of the source domain of the cross-domain recommendation is richer. The current preference of the user is calculated in the source field and the target field respectively through the attention introducing mechanism, so that the recommendation result is more time-efficient. The mapping relation of the overall preference of the user in the source field and the target field is obtained through the BP neural network, the mapping relation is applied to the current preference of the user, the mapping relation is mapped from the source field to the target field, and the final recommendation result is more accurate by combining with the independent recommendation result of the target field.
It should be noted that the above-mentioned embodiments are merely preferred embodiments of the present invention, and are not intended to limit the present invention, but various modifications and variations of the present invention will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (6)

1. The cross-domain recommendation method integrating the labels and the attention mechanisms is characterized by comprising the following steps of:
selecting and constructing a cross-domain fusion label, fusing two similar domains into a new domain, taking the new domain as a source domain recommended by the cross-domain, and respectively carrying out weighted summation on label vectors of the source domain and the target domain to obtain a resource vector of each resource;
secondly, learning a time sequence relation between a user and a resource through a long-short-term memory algorithm LSTM according to an interest mining algorithm based on an attention mechanism, and introducing the attention mechanism to obtain the preference of the user in a specified time period of a source field and a target field;
thirdly, according to a cross-domain label mapping algorithm based on the BP neural network, a label mapping between a source domain and a target domain is learned through a three-layer BP neural network, and after a preference vector of a user source domain is mapped to the target domain, the preference vector of the user source domain and the preference vector of the user in the target domain are weighted and summed to obtain comprehensive preference of the user in the target domain;
step four, a cross-domain recommendation algorithm integrating label mapping and an attention mechanism calculates the similarity between a resource vector which is not browsed by a user and the comprehensive preference of the user in the target domain according to the comprehensive preference of the user in the source domain and the target domain, and recommends the first N items to the user;
the selecting and constructing a cross-domain fusion label flow in the first step comprises the following steps:
step 1-1, preprocessing data in a source field and a target field:
collecting commonly used labels in two similar fields A and B and a target field C as custom labels DT, retrieving resources related to the custom labels to obtain resource labels RT corresponding to the resources, removing repeated labels to obtain RT-DT matrixes, wherein each column of the matrixes is custom label DT vectors, each action resource label RT vector, and uniformly measuring the rest custom label vectors;
step 1-2, selecting and constructing a cross-domain fusion tag;
analyzing similarity of the same custom tag DT vector and the same resource tag RT vector in the A, B field, and calculating similarity of the same DT vector and the same RT vector in the user A and B resources by using cosine similarity, wherein the similarity is shown in a formula (1):
Figure QLYQS_1
Figure QLYQS_2
wherein ,
Figure QLYQS_3
and
Figure QLYQS_4
Represents the same DT or RT in the A-domain and B-domain, respectively,>
Figure QLYQS_5
Figure QLYQS_6
labels->
Figure QLYQS_7
and
Figure QLYQS_8
Vector representations of (a); to ensure recommended quality, labels with similarity below a threshold are culled;
in each field of constructed tag vectors, the custom tag DT and the resource tag RT are filtered, and the same resource tag RT vector is weighted and summed according to the interests of users in each field to obtain an A-B field tag vector matrix, as shown in the formula (2) and the formula (3):
Figure QLYQS_9
Figure QLYQS_10
Figure QLYQS_11
Figure QLYQS_12
wherein ,
Figure QLYQS_13
to fuse tags across domains->
Figure QLYQS_14
For labels->
Figure QLYQS_15
Vector representations of (a);
the resource labels RT of the resources are ordered according to the number of times the labels are marked by users, the labels in front are more closely related to the resources than the labels in back, and the labels of each resource are assigned with weights according to the formula (4):
Figure QLYQS_16
Figure QLYQS_17
the corresponding weight of each tag vector of all the resources is obtained by using the formula (4) for the A-B field and the C field, and then the weight summation of the tag vectors is carried out to obtain the resource vector of each resource, as shown in the formula (5):
Figure QLYQS_18
Figure QLYQS_19
wherein ,
Figure QLYQS_20
tag vector for each tag of a resource, +.>
Figure QLYQS_21
A resource vector that is a resource;
the interest mining algorithm based on the attention mechanism in the second step comprises the following steps:
learning a timing relationship between a user and a resource using a long-short term memory algorithm, assuming that an update interval of a memory cell layer is timeIntermediate step
Figure QLYQS_22
Figure QLYQS_23
Is the memory cell layer at time->
Figure QLYQS_24
Is input to the computer;
Figure QLYQS_25
And->
Figure QLYQS_26
Is a weight matrix;
Figure QLYQS_27
is a bias vector; the method comprises the following steps:
step 2-1, at each time step
Figure QLYQS_28
Multiplying the input information of the input gate by the weight value, adding the offset, and calculating to obtain a control variable ∈of the input gate>
Figure QLYQS_29
And a new input vector->
Figure QLYQS_30
Specifically, the method is shown as a formula (6) and a formula (7):
Figure QLYQS_31
Figure QLYQS_32
Figure QLYQS_33
Figure QLYQS_34
step 2-2, at each time step
Figure QLYQS_35
Calculating the control variable +.>
Figure QLYQS_36
And candidate state->
Figure QLYQS_37
Multiplication, namely multiplying forgetting gate input information by weight, adding the product of the input gate input information and the weight, and then taking the memory unit state from +.>
Figure QLYQS_38
Update to->
Figure QLYQS_39
Specifically, the method is shown as a formula (8) and a formula (9):
Figure QLYQS_40
Figure QLYQS_41
Figure QLYQS_42
Figure QLYQS_43
step 2-3, continuously calculating the value of the output gate in the updated memory cell state, specifically as shown in the following formulas (10) and (11):
Figure QLYQS_44
Figure QLYQS_45
Figure QLYQS_46
Figure QLYQS_47
step 2-4, calculating a loss function and minimizing it using a gradient descent method, as shown in formula (12):
Figure QLYQS_48
Figure QLYQS_49
after being calculated by a long-short-term memory algorithm LSTM layer, each time step hidden state of the LSTM is used as an output result to be output to an attention layer so as to capture the dependency relationship among sequences, and a context vector representation corresponding to an output sequence i is obtained after weighted summation
Figure QLYQS_50
The specific formula descriptions are shown in the formula (13) and the formula (14): />
Figure QLYQS_51
Figure QLYQS_52
Figure QLYQS_53
Figure QLYQS_54
wherein ,
Figure QLYQS_55
is LSTM NoiOutput of individual time steps,/->
Figure QLYQS_56
Represent the firstiTime step and No. HjThe normalized weight of the output of each time step, and the similarity calculation function adopts matrix transformation represented by W;
the cross-domain label mapping algorithm based on the BP neural network in the third step comprises the following steps:
the label mapping between different fields is learned through a three-layer BP neural network, firstly, n labels which are used most by a user are respectively collected in an A-B field and a C field, the weight of each label in the two fields is respectively calculated according to a formula (4), and then the feature vectors of the user in the A-B field and the C field are respectively calculated through the weights, wherein the feature vectors are specifically shown as a formula (15) and a formula (16):
Figure QLYQS_57
Figure QLYQS_58
Figure QLYQS_59
Figure QLYQS_60
wherein ,
Figure QLYQS_61
for the feature vector of the user in the A-B field, < >>
Figure QLYQS_62
and
Figure QLYQS_63
The weight of each label in the A-B field and the characteristic vector of the label are obtained;
Figure QLYQS_64
For the feature vector of the user in the C field, +.>
Figure QLYQS_65
and
Figure QLYQS_66
The weight of each label in the C field and the characteristic vector of the label are obtained;
then, by
Figure QLYQS_67
For inputting vectors, ++>
Figure QLYQS_68
For the actual output vector, learning +.>
Figure QLYQS_69
and
Figure QLYQS_70
The mapping is shown as the following formulas (17) - (21):
the mapping relation between the input layer and the hidden layer is shown in the formula (17):
Figure QLYQS_71
Figure QLYQS_72
the activation function through the hidden layer is shown in equation (18):
Figure QLYQS_73
Figure QLYQS_74
the mapping relationship from the hidden layer to the output layer is shown in the formula (19):
Figure QLYQS_75
Figure QLYQS_76
the activation function through the output layer is shown in equation (20):
Figure QLYQS_77
Figure QLYQS_78
the loss function of the BP neural network is shown as a formula (21):
Figure QLYQS_79
Figure QLYQS_80
wherein in the formulas (14) and (16),
Figure QLYQS_81
nthe number of hidden layer units for BP neural network, i.e.
Figure QLYQS_82
, wherein ,
Figure QLYQS_83
For the number of input layer units, < > for>
Figure QLYQS_84
The number of the output layer units;
the cross-domain recommendation algorithm fusing the label mapping and the attention mechanism in the fourth step specifically comprises the following steps:
step 4-1, setting the user preference vector of the history record in the A-B field after being processed by the LSTM layer and the attention layer as
Figure QLYQS_85
The user preference vector of the history record in the C field after being processed by the LSTM network is +.>
Figure QLYQS_86
The mapping network between the source domain and the target domain is +.>
Figure QLYQS_87
Will be +.>
Figure QLYQS_88
and
Figure QLYQS_89
Weighted summation to obtain final user resource vector:
Figure QLYQS_90
Figure QLYQS_91
wherein ,
Figure QLYQS_92
resource vector representing user->
Figure QLYQS_93
Representing the number of target domain resources in the user history, < >>
Figure QLYQS_94
Representing the number of source domain resources in the user history;
step 4-2, after the final user resource vector is obtained by calculation, calculating the similarity between the user resource vector and the resource vector in the target field in the resource library, wherein the similarity is specifically shown as a formula (23):
Figure QLYQS_95
Figure QLYQS_96
wherein ,
Figure QLYQS_97
representing user resource vector, ++>
Figure QLYQS_98
A resource vector representing a target domain in a resource pool.
2. The cross-domain recommendation method of a fusion tag and attention mechanism of claim 1, wherein the data preprocessing of the source domain and the target domain in step 1-1 comprises the steps of:
step 1-1-1, respectively acquiring labels from texts of A, B domain resources by using a TF-IDF technology, and extracting labels which are commonly used by m users and are simultaneously displayed in two domains, namely a custom label DT, from the acquired labels, wherein the labels can better represent resource characteristics and are marked as DTs; then searching the resources related to DT in A, B field, displaying the label corresponding to each resource, namely resource label RT, and recording as RTs;
step 1-1-2, acquiring labels commonly used by N users from the C field by using a TF-IDF technology, namely DTt, then searching resources related to DT, and displaying labels corresponding to each resource, namely RTt;
step 1-1-3, for the collected labels, finishing word segmentation by using an NLPIR Chinese word segmentation system, removing repeated labels, and counting the occurrence frequency of each RT in the resources corresponding to each DT, wherein the larger the vector value is, the tighter the relation between RT and DT is;
step 1-1-4, because the total number of resources retrieved by different DTs is different, dividing each component of all DT vectors by the largest component of the vector to obtain a DT vector with uniform metrics.
3. The cross-domain recommendation method of the fusion tag and the attention mechanism according to claim 1, wherein according to the attention mechanism-based interest mining algorithm, all resource vectors of the histories of the user in the source domain and the target domain are calculated through an LSTM layer and an attention layer respectively, and preference vectors of the user in the source domain and the target domain are obtained.
4. The cross-domain recommendation method of merging labels and attention mechanisms of claim 1, wherein the number of hidden layer units of a BP neural networknThe method is determined by adopting a golden section method.
5. The cross-domain recommendation method of a fusion tag and an attention mechanism according to claim 1, wherein in the calculation of the final user resource vector, the similarity of the resource vector which is not browsed in the target domain by the user is directly affected according to the difference of browsing amounts of the user in the target domain; when the data volume browsed by the user in the target field is small, the preference mapping of the user in the source field can be used for obtaining the preference calculation of the user in the target field, and the similarity of the resource vectors not browsed by the user in the target field; when the browsing data quantity of the user in the target field is far greater than that of the user in the source field, the data sparsity does not exist, which is equivalent to obtaining a final recommendation result directly according to the browsed resource vector in the target field.
6. A system for implementing cross-domain recommendation of a fusion tag and an attention mechanism for implementing a cross-domain recommendation method of a fusion tag and an attention mechanism as claimed in any one of claims 1 to 5, the system comprising:
the method comprises the steps of obtaining resource labels of resources corresponding to the custom labels by utilizing commonly used custom labels in two similar fields A and B based on a label cross-domain resource fusion algorithm module, analyzing the similarity of the custom label DT vector and the same resource label RT vector in the A, B field, and eliminating the resource label vector with the similarity lower than a threshold value; respectively carrying out weighted summation on resource tag vectors of a source field and a target field C which are formed by two similar fields A and B to obtain resource vectors of each resource of the source field and the target field;
the interest mining algorithm module based on the attention mechanism obtains preference vectors of the user in the source field and the target field by utilizing all resource vectors of the history records of the user in the source field and the target field and through deep learning of an LSTM layer and an attention layer of the long-term memory algorithm;
the cross-domain label mapping algorithm module based on the BP neural network is used for mapping the preference vector of the user source domain to the target domain by using the three-layer BP neural network to obtain the comprehensive preference of the user in the target domain;
and the cross-domain recommendation algorithm module is used for combining the preferences of the user in the source domain and the target domain to obtain the comprehensive preferences of the user in the target domain, and then calculating the similarity between the resource vector which is not browsed in the target domain by the user and the comprehensive preferences of the user to obtain a recommendation list of the user in the target domain.
CN202010068923.6A 2020-01-21 2020-01-21 Cross-domain recommendation method integrating labels and attention mechanisms and implementation system thereof Active CN111291261B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010068923.6A CN111291261B (en) 2020-01-21 2020-01-21 Cross-domain recommendation method integrating labels and attention mechanisms and implementation system thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010068923.6A CN111291261B (en) 2020-01-21 2020-01-21 Cross-domain recommendation method integrating labels and attention mechanisms and implementation system thereof

Publications (2)

Publication Number Publication Date
CN111291261A CN111291261A (en) 2020-06-16
CN111291261B true CN111291261B (en) 2023-05-26

Family

ID=71018207

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010068923.6A Active CN111291261B (en) 2020-01-21 2020-01-21 Cross-domain recommendation method integrating labels and attention mechanisms and implementation system thereof

Country Status (1)

Country Link
CN (1) CN111291261B (en)

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111813924B (en) * 2020-07-09 2021-04-09 四川大学 Category detection algorithm and system based on extensible dynamic selection and attention mechanism
CN111737582B (en) * 2020-07-29 2020-12-08 腾讯科技(深圳)有限公司 Content recommendation method and device
CN111931061B (en) * 2020-08-26 2023-03-24 腾讯科技(深圳)有限公司 Label mapping method and device, computer equipment and storage medium
CN112035743B (en) 2020-08-28 2021-10-15 腾讯科技(深圳)有限公司 Data recommendation method and device, computer equipment and storage medium
CN114422859B (en) * 2020-10-28 2024-01-30 贵州省广播电视信息网络股份有限公司 Deep learning-based ordering recommendation system and method for cable television operators
CN112100509B (en) * 2020-11-17 2021-02-09 腾讯科技(深圳)有限公司 Information recommendation method, device, server and storage medium
CN112464097B (en) * 2020-12-07 2023-06-06 广东工业大学 Multi-auxiliary-domain information fusion cross-domain recommendation method and system
CN112417298B (en) * 2020-12-07 2021-06-29 中山大学 Cross-domain recommendation method and system based on a small number of overlapped users
CN112541132B (en) * 2020-12-23 2023-11-10 北京交通大学 Cross-domain recommendation method based on multi-view knowledge representation
CN113127737B (en) * 2021-04-14 2021-09-14 江苏科技大学 Personalized search method and search system integrating attention mechanism
CN115098931B (en) * 2022-07-20 2022-12-16 江苏艾佳家居用品有限公司 Small sample analysis method for mining personalized requirements of indoor design of user
CN116012118B (en) * 2023-02-28 2023-08-29 荣耀终端有限公司 Product recommendation method and device
CN116070034B (en) * 2023-03-03 2023-11-03 江西财经大学 Graph convolution network recommendation method combining self-adaptive period and interest quantity factor
CN116843394B (en) * 2023-09-01 2023-11-21 星河视效科技(北京)有限公司 AI-based advertisement pushing method, device, equipment and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105138624A (en) * 2015-08-14 2015-12-09 北京矩道优达网络科技有限公司 Personalized recommendation method based on user data of on-line courses
CN107122399A (en) * 2017-03-16 2017-09-01 中国科学院自动化研究所 Combined recommendation system based on Public Culture knowledge mapping platform
CN107291815A (en) * 2017-05-22 2017-10-24 四川大学 Recommend method in Ask-Answer Community based on cross-platform tag fusion
JP2017204289A (en) * 2017-06-28 2017-11-16 凸版印刷株式会社 Electronic flyer recommendation system, electronic flyer recommendation server, and program
WO2018176413A1 (en) * 2017-03-31 2018-10-04 Microsoft Technology Licensing, Llc Providing news recommendation in automated chatting
CN110232153A (en) * 2019-05-29 2019-09-13 华南理工大学 A kind of cross-cutting recommended method based on content

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10659422B2 (en) * 2012-04-30 2020-05-19 Brightedge Technologies, Inc. Content management systems

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105138624A (en) * 2015-08-14 2015-12-09 北京矩道优达网络科技有限公司 Personalized recommendation method based on user data of on-line courses
CN107122399A (en) * 2017-03-16 2017-09-01 中国科学院自动化研究所 Combined recommendation system based on Public Culture knowledge mapping platform
WO2018176413A1 (en) * 2017-03-31 2018-10-04 Microsoft Technology Licensing, Llc Providing news recommendation in automated chatting
CN107291815A (en) * 2017-05-22 2017-10-24 四川大学 Recommend method in Ask-Answer Community based on cross-platform tag fusion
JP2017204289A (en) * 2017-06-28 2017-11-16 凸版印刷株式会社 Electronic flyer recommendation system, electronic flyer recommendation server, and program
CN110232153A (en) * 2019-05-29 2019-09-13 华南理工大学 A kind of cross-cutting recommended method based on content

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
TA-BLSTM: Tag Attention-based Bidirectional Long Short-Term Memory for Service Recommendation in Mashup Creation;Min Shi;《2019 International Joint Conference on Neural Networks (IJCNN)》;20190719;全文 *
基于深度学习的推荐系统研究综述;黄立威等;《计算机学报》;20180305(第07期);全文 *

Also Published As

Publication number Publication date
CN111291261A (en) 2020-06-16

Similar Documents

Publication Publication Date Title
CN111291261B (en) Cross-domain recommendation method integrating labels and attention mechanisms and implementation system thereof
Zhou et al. Atrank: An attention-based user behavior modeling framework for recommendation
CN110263265B (en) User tag generation method, device, storage medium and computer equipment
CN108763362B (en) Local model weighted fusion Top-N movie recommendation method based on random anchor point pair selection
CN108363804B (en) Local model weighted fusion Top-N movie recommendation method based on user clustering
CN110503531B (en) Dynamic social scene recommendation method based on time sequence perception
CN107357793B (en) Information recommendation method and device
CN107220365A (en) Accurate commending system and method based on collaborative filtering and correlation rule parallel processing
CN105512180B (en) A kind of search recommended method and device
CN113139141B (en) User tag expansion labeling method, device, equipment and storage medium
Lai et al. Topic time series analysis of microblogs
Zheng et al. Personalized fashion recommendation from personal social media data: An item-to-set metric learning approach
Cai et al. Multi-View Active Learning for Video Recommendation.
Kim et al. Exploiting web images for video highlight detection with triplet deep ranking
CN111460251A (en) Data content personalized push cold start method, device, equipment and storage medium
CN112749330A (en) Information pushing method and device, computer equipment and storage medium
Yang et al. Social tag embedding for the recommendation with sparse user-item interactions
CN111681107A (en) Real-time personalized financial product recommendation algorithm based on Embedding
CN118069927A (en) News recommendation method and system based on knowledge perception and user multi-interest feature representation
Unger et al. Inferring contextual preferences using deep encoder-decoder learners
CN115545349B (en) Time sequence social media popularity prediction method and device based on attribute sensitive interaction
Solomon et al. Predicting application usage based on latent contextual information
dos Santos et al. Clustering learning objects for improving their recommendation via collaborative filtering algorithms
Li et al. Correlating stressor events for social network based adolescent stress prediction
CN114529399A (en) User data processing method, device, computer equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20231013

Address after: 200120, Room 505, 5th Floor, Building 8, No. 399 Jianyun Road, Pudong New Area, Shanghai

Patentee after: Shanghai Juhui Network Technology Co.,Ltd.

Address before: 230000 floor 1, building 2, phase I, e-commerce Park, Jinggang Road, Shushan Economic Development Zone, Hefei City, Anhui Province

Patentee before: Dragon totem Technology (Hefei) Co.,Ltd.

Effective date of registration: 20231013

Address after: 230000 floor 1, building 2, phase I, e-commerce Park, Jinggang Road, Shushan Economic Development Zone, Hefei City, Anhui Province

Patentee after: Dragon totem Technology (Hefei) Co.,Ltd.

Address before: 330000 No.169 Shuanggang East Street, Nanchang Economic and Technological Development Zone, Jiangxi Province

Patentee before: JIANGXI University OF FINANCE AND ECONOMICS