CN112801751A - Personalized scenic spot recommendation method of multitask graph neural network - Google Patents
Personalized scenic spot recommendation method of multitask graph neural network Download PDFInfo
- Publication number
- CN112801751A CN112801751A CN202110155597.7A CN202110155597A CN112801751A CN 112801751 A CN112801751 A CN 112801751A CN 202110155597 A CN202110155597 A CN 202110155597A CN 112801751 A CN112801751 A CN 112801751A
- Authority
- CN
- China
- Prior art keywords
- user
- scenic spot
- neural network
- graph
- recommendation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 108
- 238000000034 method Methods 0.000 title claims abstract description 37
- 239000013598 vector Substances 0.000 claims abstract description 56
- 238000012549 training Methods 0.000 claims abstract description 27
- 230000006870 function Effects 0.000 claims description 25
- 230000014509 gene expression Effects 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 14
- 230000006835 compression Effects 0.000 claims description 11
- 238000007906 compression Methods 0.000 claims description 11
- 230000004927 fusion Effects 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 10
- 230000003993 interaction Effects 0.000 claims description 7
- 239000000126 substance Substances 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 2
- 238000005406 washing Methods 0.000 claims description 2
- 230000002452 interceptive effect Effects 0.000 abstract description 3
- 238000005457 optimization Methods 0.000 abstract description 3
- 238000007418 data mining Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 7
- 238000011161 development Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009933 burial Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000004630 mental health Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
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
- 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
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/14—Travel agencies
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Finance (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Primary Health Care (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to the field of big data mining, and particularly relates to a personalized scenic spot recommendation method of a multitask graph neural network, which comprises the following steps: acquiring interactive data, user attribute data and scenic spot attribute data of a user and a scenic spot; establishing a scenic spot knowledge map and a user knowledge map according to the user and the scenic spot data; learning vector representation of entities and relations in the knowledge graph through two graph neural networks, and accordingly constructing a deep neural network to predict scores of the user on scenic spots; training three networks by recommending a network scoring task and a multi-task alternate training mode of representing a learning task by a user and a scenic spot knowledge graph to complete model optimization; according to the invention, scenic spot and user attribute information are introduced, a knowledge map is constructed, the network is trained in a multi-task alternative training mode, the relation between the user and the characteristics of the scenic spot is accurately learned, the multi-task alternative training network can enhance the expandability of the model, the overfitting of the model is avoided, and the recommendation performance can be effectively improved.
Description
Technical Field
The invention belongs to the field of big data mining, and particularly relates to a personalized scenic spot recommendation method of a multitask graph neural network.
Background
With the development of society, the living standard of people is continuously improved, so that people like traveling more and more. At present, the development of the domestic tourism industry is in the key period of transformation and upgrading to global tourism and modern tourism, the tourism industry belongs to an information-intensive industry, has the characteristics of strong comprehensiveness and high relevance, and is a necessary choice for realizing transformation and upgrading of the tourism industry by using multi-domain mass tourism information and developing business and service mode innovation by using information technologies such as internet, cloud computing and the like. On the other hand, the rapid development of tourism brings great business opportunities to the tourism industry, and simultaneously, the method also meets the challenges. With the continuous acceleration of intelligent tourism construction, mass tourism data such as information acquisition, consumption comment, product recommendation and the like are generated. For the obtained travel data, how to apply mature big data technology to mine the value in the travel data becomes the key point of intelligent travel development.
In order to realize intelligent tourism, the tourist resort can be recommended by a personalized recommendation technology. Personalized recommendation systems have been widely used in the field of e-commerce and have also met with great success, with Amazon sales accounting for 35% of all being helped by recommendation systems. Although personalized recommendation technology has been successful in e-commerce and other fields, its application in other fields is not as effective as e-commerce. Therefore, how to find out the information meeting the personalized requirements of the tourists from the massive travel service information through the recommendation system according to the user preference and recommend the information for the user becomes a problem to be solved urgently. The traditional recommendation technology comprises a collaborative filtering series technology and an FM recommendation technology, but the methods cannot effectively utilize auxiliary information to solve the problems of data cold start and sparsity, and have insufficient extraction on characteristics of tourist attractions and users and poor recommendation effect.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a personalized scenic spot recommendation method of a multitask graph neural network, which comprises the following steps: acquiring user data in real time, and preprocessing the acquired user data; inputting the preprocessed data into a trained recommendation model to obtain a recommendation result; the recommendation model is composed of a user graph neural network, a scenic spot neural network and a recommendation network and is a cross unit;
the process of training the recommendation model includes:
s1: acquiring original data, and preprocessing the original data; the original data comprises user attribute data, scenic spot attribute data and scenic spot interaction data;
s2: extracting a user characteristic set and a scenic spot characteristic set of the preprocessed data; constructing a user knowledge graph according to the user feature set, and constructing a scenic spot knowledge graph according to the scenic spot feature set;
s3: inputting triple data in the user knowledge graph into a user graph neural network for training, and learning the vector expression of the user in the user knowledge graph; inputting the triple data in the scenic spot knowledge graph into a scenic spot graph neural network for training, and learning vector expression of the scenic spot in the scenic spot knowledge graph;
s4: respectively inputting the user potential features extracted by the user map neural network and the scenic spot potential features extracted by the scenic spot map neural network into a recommendation network through a cross unit to obtain potential feature vectors after user fusion and potential feature vectors after scenic spot fusion; forming a prediction score of the user for the scenic spot according to the fused user potential feature vector and the fused scenic spot potential feature vector;
s5: in the training process of the recommendation model, multi-task training is carried out on a recommendation network score prediction task, a user map neural network representation learning task of a user knowledge map, and a scenic spot map neural network representation learning task of the scenic spot knowledge map;
s6: calculating a loss function of the model in a multitasking process, wherein the loss function of the model comprises scenic region diagram neural network loss, user diagram neural network loss, recommendation network loss and regular term loss;
s7: and when the loss function value of the model is minimum, finishing the training of the model.
Preferably, the process of preprocessing the user data includes: cleaning user data, and deleting invalid data and abnormal data; the data after washing were normalized by z-score.
Preferably, the extracted user feature set comprises a biological attribute feature and a social attribute feature; the extracted scenic spot feature set comprises scenic spot resource features and scenic spot leading function features.
Preferably, the structure of the user graph neural network comprises two parts, namely a neural network comprising L-layer full connection and a neural network comprising H-layer full connection; the neural network comprising L layers of full connection is used for extracting potential feature vectors of head entities and relations in the user knowledge graph; the H-layer full-connection neural network is used for extracting the potential feature vectors of the head entity and the relation from the feature extraction layer to perform high-order feature combination to form a predicted tail entity; wherein L, H is a model hyper-parameter.
Preferably, the structure of the scenic spot map neural network is the same as that of the user map neural network; the neural network comprising L layers of full connection is used for extracting head entities and relation potential feature vectors in the scenic spot knowledge graph; the neural network comprising H layer full connection is used for extracting the potential feature vectors of the head entity and the relation from the feature extraction layer to carry out high-order feature combination to form a predicted tail entity; wherein L, H is a model hyper-parameter.
Preferably, the structure of the recommendation network comprises two parts, namely a neural network comprising L-layer full connection and a neural network comprising H-layer full connection; the neural network comprising the L-layer full connection is used for extracting potential features of the user and the scenic spot input in the recommendation network, wherein the user corresponds to a head entity input by the user graph neural network, and the scenic spot corresponds to a head entity input by the scenic spot graph neural network; the neural network comprising H-layer full connection is used for extracting the potential feature vectors of the user and the scenic spot from the feature extraction layer, performing high-order feature combination, and predicting the score of the user on the scenic spot.
Preferably, the structure of the crossing unit comprises a user crossing unit and a scenic spot crossing unit; the user cross unit is used for connecting the user graph neural network and the recommendation network feature extraction layer, fusing the features extracted by the same user through the user graph neural network and the recommendation network through feature cross and feature compression, and obtaining a potential feature vector after user fusion; and the scenic spot crossing unit is used for connecting the scenic spot map neural network and the recommendation network feature extraction layer, and fusing the features extracted from the same scenic spot by using the scenic spot neural network and the recommendation network through feature crossing and feature compression to obtain a potential feature vector after scenic spot fusion.
Further, the expression of feature intersection and feature compression is:
the characteristics are crossed: cl＝vlel T
Feature compression:
preferably, the process of obtaining the personalized scores of the user on the scenic spot comprises the following steps:
preferably, the loss function is expressed as:
the invention has the beneficial effects that:
1) the method constructs the knowledge map by using the attribute data of the users and the scenic spots, learns the scenic spots and the user characteristic expression in the knowledge map through the graph neural network, introduces the knowledge information expressing the scenic spots and the users in the knowledge map into a recommendation network, accurately learns the relation between the users and the characteristics of the scenic spots and fully excavates the information of the data;
2) the invention designs two cross units as connecting links between the scenic spot map neural network and the recommendation network and between the user map neural network and the recommendation network, and learns the potential interactive characteristics of scenic spots and users in the two forms. The expandability of the model can be enhanced through a multi-task alternative training mode, overfitting of the model is avoided, and the recommendation performance can be effectively improved.
Drawings
FIG. 1 is a schematic representation of the steps of the process of the present invention;
FIG. 2 is a diagram of a user graph neural network architecture for the method of the present invention;
FIG. 3 is a diagram of a scenic map neural network architecture of the method of the present invention;
FIG. 4 is a diagram of a preferred network architecture for the method of the present invention;
FIG. 5 is a cross-cell block diagram of the method of the present invention;
fig. 6 is a general network architecture diagram of the method of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions in the embodiments of the present invention are described clearly and completely below with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a personalized scenic spot recommendation method of a multitask graph neural network, which mainly comprises the following steps: acquiring and preprocessing data; selecting characteristics to establish a knowledge graph of a user and a scenic spot; learning vector representation of entity nodes and relations in the knowledge graph by using a graph neural network; establishing a deep neural network by using historical interactive data of a given user on a scenic spot, and realizing personalized prediction of the rating of the user on the given scenic spot; designing two cross units to connect three networks, and effectively integrating information in knowledge maps of a given user and a given scenic spot into a recommendation system; and finally, training three networks in a multi-task alternate training mode of recommending network scoring tasks and representing learning tasks by users and scenic spot knowledge maps to complete model optimization and form personalized scores of the users for scenic spots.
A personalized scenic spot recommendation method of a multitask graph neural network comprises the following steps: acquiring user data in real time, and preprocessing the acquired user data; inputting the preprocessed data into a trained recommendation model to obtain a recommendation result; the recommendation model is composed of a user graph neural network, a scenic spot neural network and a recommendation network, and a cross unit.
As shown in fig. 1, the process of training the recommendation model includes:
s1: acquiring original data, and preprocessing the original data; the original data comprises user attribute data, scenic spot attribute data and scenic spot interaction data;
s2: extracting a user characteristic set and a scenic spot characteristic set of the preprocessed data; constructing a user knowledge graph according to the user feature set, and constructing a scenic spot knowledge graph according to the scenic spot feature set;
s3: inputting the (head entity, relation, tail entity) triples in the user knowledge graph into a user graph neural network for training, and learning the vector expression of the user in the user knowledge graph; inputting (head entity, relation, tail entity) triples in the scenic spot knowledge graph into a scenic spot graph neural network for training, and learning to realize vector expression of scenic spots in the scenic spot knowledge graph;
s4: and the design cross unit fuses the user potential features extracted by the user map neural network and the scenic spot potential features extracted by the scenic spot map neural network into a recommendation network to obtain the potential feature vectors after user fusion and the potential feature vectors after scenic spot fusion. And forming a prediction score of the user for the scenic region by using the fused user potential feature vector and the fused scenic region potential feature vector. (ii) a
S5: in each round of training, the recommended network scoring prediction task, the user map representation learning task of the user knowledge map by the user map neural network and the scenic spot representation learning task of the scenic spot knowledge map by the scenic spot map neural network are subjected to multi-task training. Specifically, when a given task is trained, the rest two network parameters are kept unchanged, the network parameters of the task are updated, and the last three tasks are alternately trained in sequence to complete the updating of the three network parameters until the model converges. (ii) a
S6: the loss function for guiding the personalized scenic spot recommendation method of the whole multitask graph neural network is accumulation of scenic spot graph neural network loss, user graph neural network loss, recommendation network loss and regular term loss. Acquiring user attribute data, scenic spot attribute data and user and scenic spot interaction data in various ways; the manner of obtaining includes, but is not limited to, obtaining travel website data, volunteer data, public transportation data, climate website data, map software data, social software data, etc. by using web crawlers, data burial, questionnaires, etc. Preprocessing the acquired data, including cleaning user data and deleting invalid data and abnormal data; because the data has the characteristic of data source diversification, in order to eliminate the problems of different dimensions among different source scalar data and the problem of value intervals among the same source scalar data, the data is subjected to z-score standardization, and the standardization formula is as follows:
where x represents raw data, u represents raw data mean, σ represents raw data standard deviation, and z represents processed data, whose mean is 0 and standard deviation is 1.
Selecting a user characteristic set according to the preprocessed data
Feature set of scenic spot
The scenic spot features comprise scenic spot resource features and scenic spot leading function features, and the user features comprise biological attribute features and social attribute features.
The scenic spot resource characteristics comprise natural tourism resources such as scenic spot landscape resources, geographical position resources, climate resources, greening resources, biological type resources and the like; religious cultural resources, historical cultural resources, national life and fashion resources, cultural relic resources and other human resources; scenic spot traffic resources, modern scientific and technological resources, modern construction resources, peripheral supporting facility resources and other social resources.
The main function characteristics of the scenic spot comprise a sightseeing scenic spot, a vacation scenic spot, a scientific and scientific scenic spot, an amusement scenic spot, an ecological scenic spot, a scientific and technological scenic spot, an adventure scenic spot and the like.
The user biological characteristics include age, gender, height, race, weight, language, physical and mental health.
The social characteristics of the user comprise a study, occupation, marital family, relationship, living city, income condition, social status, profession, religion, ethnicity and the like.
According to the characteristics, the knowledge graph is constructed in the form of triples (head entities, relations and tail entities).
As shown in FIG. 2 and FIG. 3, the user graph neural network and the scenic spot graph neural network take head entity head and relationship relation in the knowledge graph as input, and minimize and predict tail entity
Training the network by taking the distance t from the real tail entity as a target function to finally obtain a knowledge graph
And
vector expression of the intermediate entity. The user map neural network and the scenic spot map neural network both comprise lower L-layer full-connection layers for extracting potential features of the relationship between the user knowledge graph and the scenic spot knowledge graph, and the expression formula is as follows:
wherein the content of the first and second substances,
respectively passing through the lower L layer full connecting layerPotential feature vectors for the relationships in the post-user and scenic spot knowledge maps,
and representing a layer of fully connected layers, wherein W is a weight parameter of each layer, b is a bias term parameter, and sigma (x) is a nonlinear activation function. The user map neural network and the scenic spot map neural network comprise upper H-layer full-connection layers respectively used for obtaining vector expressions of tail entities in the user knowledge map and the scenic spot knowledge map
And
the expression is as follows:
wherein, | | is a vector concatenator, wL，eLThe potential feature vectors of the user and the scenic spot in the knowledge graph of the user and the scenic spot after passing through the lower L-layer full-connection layer are respectively.
As shown in fig. 4, the recommendation network includes a lower L-layer feature extraction layer, and interaction feature vectors of the knowledge graph and corresponding scenic spots and users in the recommendation network are learned through a cross unit in the feature extraction layer, so that information in the knowledge graph is merged into the recommendation network. The recommendation network also comprises an upper H-layer full-connection layer to learn high-order combination characteristics of the users and scenic spots, and finally, the scores are predicted and graded through a nonlinear activation function
The expression is as follows:
wherein u isL，vLRespectively are the feature vectors with potential interaction features of the knowledge graph and the recommended network obtained after the lower L-layer cross unit.
As shown in fig. 5, the proposed model of the present invention involves two cross units for connecting the lower L-layer feature extraction layers of three networks. And a crossing unit connecting the scenic spot map neural network and the recommendation network inputs the potential feature vectors of the scenic spots in the previous layer of recommendation network and the potential feature vectors of the previous layer of corresponding scenic spots in the map neural network, and learns the high-order potential interaction features of the scenic spots in the recommendation network and the map neural network through two steps of feature crossing and feature compression, so that the information of the scenic spots in the knowledge map is introduced into the recommendation system. The characteristic intersection and the characteristic compression satisfy that:
the characteristics are crossed: cl＝vlel T
Feature compression:
wherein the content of the first and second substances,
for the l-th layer potential feature vector of the scenic spot in the neural network,
and recommending the potential feature vectors of the ith layer of the scenic spot in the network.
The feature intersection matrix is the result of pairwise intersection of the potential features of the scenic spots in the recommendation network and the potential features of the scenic spots in the knowledge graph.
Is potential feature vector of the l +1 layer of scenic spot in the neural network,
the potential feature vector of the l +1 layer of the scenic spot in the network is recommended.
And
for the model parameters, d is the length of the potential feature vector. The intersection unit connecting the user map neural network and the recommendation network has the same structure as the intersection unit connecting the scenic spot map neural network and the recommendation network.
As shown in fig. 6, the three networks are alternately trained layer by layer, the loss function is defined as the sum of the losses of the three networks, and the expression of the loss function is:
wherein the content of the first and second substances,
in order to be a cross-entropy function,
λ1，λ2，λ3being a hyper-parameter of the model, WθIs a regularization term parameter. And when the model is alternately trained, keeping the two network parameters unchanged, and updating the other network parameter. And training three networks by recommending a network scoring task and a multi-task alternate training mode of representing a learning task by a user and a scenic spot knowledge graph, and finishing model optimization. By determining the model parameters, the personalized rating of a specific user to the scenic spot can be obtained, and thus the personalized scenic spot recommendation list of the given user can be obtained.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by instructions associated with hardware via a program, which may be stored in a computer-readable storage medium, and the storage medium may include: ROM, RAM, magnetic or optical disks, and the like.
The above-mentioned embodiments, which further illustrate the objects, technical solutions and advantages of the present invention, should be understood that the above-mentioned embodiments are only preferred embodiments of the present invention, and should not be construed as limiting the present invention, and any modifications, equivalents, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A personalized scenic spot recommendation method of a multitask graph neural network is characterized by comprising the following steps: acquiring user data in real time, and preprocessing the acquired user data; inputting the preprocessed data into a trained recommendation model to obtain a recommendation result; the recommendation model is composed of a user graph neural network, a scenic spot neural network and a recommendation network and is a cross unit;
the process of training the recommendation model includes:
s1: acquiring original data, and preprocessing the original data; the original data comprises user attribute data, scenic spot attribute data and scenic spot interaction data;
s2: extracting a user characteristic set and a scenic spot characteristic set of the preprocessed data; constructing a user knowledge graph according to the user feature set, and constructing a scenic spot knowledge graph according to the scenic spot feature set;
s3: inputting the triple data in the user knowledge graph into a user graph neural network for training, and learning the vector expression of the user in the user knowledge graph; inputting the triple data in the scenic spot knowledge map into a scenic spot map neural network for training, and learning vector expression of the scenic spot in the scenic spot knowledge map;
s4: respectively inputting the user potential features extracted by the user map neural network and the scenic spot potential features extracted by the scenic spot map neural network into a recommendation network through a cross unit to obtain potential feature vectors after user fusion and potential feature vectors after scenic spot fusion; forming a prediction score of the user for the scenic spot according to the fused user potential feature vector and the fused scenic spot potential feature vector;
s5: in the training process of the recommendation model, multi-task training is carried out on a recommendation network score prediction task, a user map neural network representation learning task of a user knowledge map and a scenic spot map neural network representation learning task of the scenic spot knowledge map;
s6: calculating a loss function of the model, wherein the loss function of the model comprises scenic region graph neural network loss, user graph neural network loss, recommended network loss and regular term loss;
s7: and when the loss function value of the model is minimum, finishing the training of the model.
2. The method as claimed in claim 1, wherein the preprocessing of the user data comprises: cleaning user data, and deleting invalid data and abnormal data; the data after washing were normalized by z-score.
3. The personalized scenic spot recommendation method of the multitask graph neural network as claimed in claim 1, wherein the extracted user feature set comprises a biological attribute feature and a social attribute feature; the extracted scenic spot feature set comprises scenic spot resource features and scenic spot leading function features.
4. The personalized scenic spot recommendation method of the multitask graph neural network as claimed in claim 1, wherein the user graph neural network structure comprises two parts including a neural network with L-layer full connection and a neural network with H-layer full connection; the neural network comprising L layers of full connection is used for extracting potential feature vectors of head entities and relations in the user knowledge graph; the H-layer full-connection neural network is used for extracting the potential feature vectors of the head entity and the relation from the feature extraction layer to perform high-order feature combination to form a predicted tail entity; wherein L, H is a model hyper-parameter.
5. The method of claim 1, wherein the neural network of the scenic spot map has the same structure as the neural network of the user map; the neural network comprising L layers of full connection is used for extracting head entities and relation potential feature vectors in the scenic spot knowledge graph; the neural network comprising H layer full connection is used for extracting the potential feature vectors of the head entity and the relation from the feature extraction layer to carry out high-order feature combination to form a predicted tail entity; wherein L, H is a model hyper-parameter.
6. The personalized scenic spot recommendation method based on the multitask graph neural network as claimed in claim 1, wherein the structure of the recommendation network comprises two parts, namely a neural network comprising L-layer full connection and a neural network comprising H-layer full connection; the neural network comprising the L-layer full connection is used for extracting potential features of the user and the scenic spot input in the recommendation network, wherein the user corresponds to a head entity input by the user graph neural network, and the scenic spot corresponds to a head entity input by the scenic spot graph neural network; the neural network comprising H-layer full connection is used for extracting the potential feature vectors of the user and the scenic spot from the feature extraction layer, performing high-order feature combination, and predicting the score of the user on the scenic spot.
7. The personalized scenic spot recommendation method of the multitask graph neural network as claimed in claim 1, wherein the structure of the cross unit comprises a user cross unit and a scenic spot cross unit; the user cross unit is used for connecting the user graph neural network and the recommendation network feature extraction layer, fusing the features extracted by the same user through the user graph neural network and the recommendation network through feature cross and feature compression, and obtaining a potential feature vector after user fusion; and the scenic spot crossing unit is used for connecting the scenic spot map neural network and the recommendation network feature extraction layer, and fusing the features extracted from the same scenic spot by using the scenic spot neural network and the recommendation network through feature crossing and feature compression to obtain a potential feature vector after scenic spot fusion.
8. The method as claimed in claim 7, wherein the expressions of feature intersection and feature compression are as follows:
the characteristics are crossed:
feature compression:
wherein the content of the first and second substances,
the l-th layer of potential feature vectors representing scenic spots in the neural network of the graph,
representing potential feature vectors at the l-th level of the scenic spot in the recommended network,
is a feature cross matrix;
a layer l +1 potential feature vector representing a scenic spot in the recommendation network,
the l +1 level potential feature vectors representing scenic spots in the neural network of the graph,
for model parameters, d represents the latent featuresThe length of the vector is such that,
indicating transposed symbols, V, E each indicate that the current interleaving unit is a user interleaving unit.
9. The method as claimed in claim 1, wherein the process of obtaining the personalized rating of the user to the scenic spot comprises: splicing the scenic spot fused by the cross units and the potential features of the user, inputting the spliced scenic spot and the potential features of the user into an H-layer fully-connected neural network, and forming a score through a nonlinear activation function
Wherein the content of the first and second substances,
representing the fully-connected layer of the H layer, | | is a vector concatenation symbol, wL，eLPotential feature vectors u of the users and the scenic spots in the knowledge maps of the users and the scenic spots after passing through the lower L-layer full-connection layer respectivelyL，vLAnd respectively obtaining potential feature vectors of the user and the scenic region after passing through the cross unit, wherein sigma (x) is a nonlinear activation function.
10. The method as claimed in claim 1, wherein the loss function is expressed as:
wherein L isRSLoss function, L, representing a recommended networkU-GNNRepresenting the loss function, L, of the neural network of the user graphI-GNNLoss function, L, representing scenic map neural networkREGA function representing the loss of the regular term,
representing predictive scores
And a true score yuvPhi (x) represents the difference function between the predicted tail entity and the real tail entity in the knowledge-graph, and (h)u,ru,tu) Representing entity relationships that exist in the user's knowledge graph, (h)u′,ru,tu') represents entity relationships that do not exist in the user's knowledge graph, (h)v,rv,tv) Representing the entity relationship existing in the scenic spot knowledge map, (h)v′,rv,tv') represent entity relationships that do not exist in the scenic spot knowledge-graph,
in order to be a knowledge-graph of the user,
the knowledge map of the scenic spot is obtained,
representing the parameter term of the regularization term, λ1、λ2、λ3Respectively, model hyper-parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110155597.7A CN112801751B (en) | 2021-02-04 | 2021-02-04 | Personalized scenic spot recommendation method of multitask graph neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110155597.7A CN112801751B (en) | 2021-02-04 | 2021-02-04 | Personalized scenic spot recommendation method of multitask graph neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112801751A true CN112801751A (en) | 2021-05-14 |
| CN112801751B CN112801751B (en) | 2022-12-23 |
Family
ID=75814246
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110155597.7A Active CN112801751B (en) | 2021-02-04 | 2021-02-04 | Personalized scenic spot recommendation method of multitask graph neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112801751B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113505311A (en) * | 2021-07-12 | 2021-10-15 | 中国科学院地理科学与资源研究所 | Scenic spot interaction recommendation method based on' potential semantic space |
| CN113553510A (en) * | 2021-07-30 | 2021-10-26 | 华侨大学 | Text information recommendation method and device and readable medium |
| CN113722611A (en) * | 2021-08-23 | 2021-11-30 | 讯飞智元信息科技有限公司 | Method, device and equipment for recommending government affair service and computer readable storage medium |
| CN115712734A (en) * | 2022-11-21 | 2023-02-24 | 之江实验室 | Sparse knowledge graph embedding method and device based on meta-learning |
| CN117077870A (en) * | 2023-10-12 | 2023-11-17 | 北京德润誉达科技有限公司 | Water resource digital management method based on artificial intelligence |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107729444A (en) * | 2017-09-30 | 2018-02-23 | 桂林电子科技大学 | Recommend method in a kind of personalized tourist attractions of knowledge based collection of illustrative plates |
| CN110489547A (en) * | 2019-07-11 | 2019-11-22 | 桂林电子科技大学 | A kind of tourist attractions recommended method and device based on hybrid supervised learning |
| CN110555112A (en) * | 2019-08-22 | 2019-12-10 | 桂林电子科技大学 | interest point recommendation method based on user positive and negative preference learning |
| CN110795571A (en) * | 2019-10-24 | 2020-02-14 | 南宁师范大学 | Cultural tourism resource recommendation method based on deep learning and knowledge graph |
| CN110955834A (en) * | 2019-11-27 | 2020-04-03 | 西北工业大学 | Knowledge graph driven personalized accurate recommendation method |
| US20200160215A1 (en) * | 2018-11-16 | 2020-05-21 | NEC Laboratories Europe GmbH | Method and system for learning numerical attributes on knowledge graphs |
| CN111949885A (en) * | 2020-08-27 | 2020-11-17 | 桂林电子科技大学 | Personalized recommendation method for scenic spots |
| CN112084383A (en) * | 2020-09-07 | 2020-12-15 | 中国平安财产保险股份有限公司 | Information recommendation method, device and equipment based on knowledge graph and storage medium |
| CN112163165A (en) * | 2020-10-21 | 2021-01-01 | 腾讯科技（深圳）有限公司 | Information recommendation method, device, equipment and computer readable storage medium |
| CN112182412A (en) * | 2020-11-26 | 2021-01-05 | 南京吉拉福网络科技有限公司 | Method, computing device, and computer storage medium for recommending physical examination items |
| CN112269882A (en) * | 2020-10-12 | 2021-01-26 | 西安工程大学 | Tourist attraction recommendation method oriented to knowledge map |
-
2021
- 2021-02-04 CN CN202110155597.7A patent/CN112801751B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107729444A (en) * | 2017-09-30 | 2018-02-23 | 桂林电子科技大学 | Recommend method in a kind of personalized tourist attractions of knowledge based collection of illustrative plates |
| US20200160215A1 (en) * | 2018-11-16 | 2020-05-21 | NEC Laboratories Europe GmbH | Method and system for learning numerical attributes on knowledge graphs |
| CN110489547A (en) * | 2019-07-11 | 2019-11-22 | 桂林电子科技大学 | A kind of tourist attractions recommended method and device based on hybrid supervised learning |
| CN110555112A (en) * | 2019-08-22 | 2019-12-10 | 桂林电子科技大学 | interest point recommendation method based on user positive and negative preference learning |
| CN110795571A (en) * | 2019-10-24 | 2020-02-14 | 南宁师范大学 | Cultural tourism resource recommendation method based on deep learning and knowledge graph |
| CN110955834A (en) * | 2019-11-27 | 2020-04-03 | 西北工业大学 | Knowledge graph driven personalized accurate recommendation method |
| CN111949885A (en) * | 2020-08-27 | 2020-11-17 | 桂林电子科技大学 | Personalized recommendation method for scenic spots |
| CN112084383A (en) * | 2020-09-07 | 2020-12-15 | 中国平安财产保险股份有限公司 | Information recommendation method, device and equipment based on knowledge graph and storage medium |
| CN112269882A (en) * | 2020-10-12 | 2021-01-26 | 西安工程大学 | Tourist attraction recommendation method oriented to knowledge map |
| CN112163165A (en) * | 2020-10-21 | 2021-01-01 | 腾讯科技（深圳）有限公司 | Information recommendation method, device, equipment and computer readable storage medium |
| CN112182412A (en) * | 2020-11-26 | 2021-01-05 | 南京吉拉福网络科技有限公司 | Method, computing device, and computer storage medium for recommending physical examination items |
Non-Patent Citations (5)
| Title |
|---|
| HONGWEI WANG等: "Multi-task feature learning for knowledge graph enhanced recommendation", 《WWW "19: THE WORLD WIDE WEB CONFERENCE》 * |
| 朱瑞等: "一种基于KCNN和MKR的两阶段深度学习多任务推荐模型", 《陕西师范大学学报(自然科学版)》 * |
| 知乎-国家二级摸鱼运动: "多任务学习+知识图谱+推荐系统", 《HTTPS://ZHUANLAN.ZHIHU.COM/P/109241655》 * |
| 程淑玉等: "融合知识图谱与循环神经网络的推荐模型", 《小型微型计算机系统》 * |
| 高仰等: "融合知识图谱和短期偏好的推荐算法", 《计算机科学与探索》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113505311A (en) * | 2021-07-12 | 2021-10-15 | 中国科学院地理科学与资源研究所 | Scenic spot interaction recommendation method based on' potential semantic space |
| CN113553510A (en) * | 2021-07-30 | 2021-10-26 | 华侨大学 | Text information recommendation method and device and readable medium |
| CN113553510B (en) * | 2021-07-30 | 2023-06-20 | 华侨大学 | Text information recommendation method and device and readable medium |
| CN113722611A (en) * | 2021-08-23 | 2021-11-30 | 讯飞智元信息科技有限公司 | Method, device and equipment for recommending government affair service and computer readable storage medium |
| CN113722611B (en) * | 2021-08-23 | 2024-03-08 | 讯飞智元信息科技有限公司 | Recommendation method, device and equipment for government affair service and computer readable storage medium |
| CN115712734A (en) * | 2022-11-21 | 2023-02-24 | 之江实验室 | Sparse knowledge graph embedding method and device based on meta-learning |
| CN115712734B (en) * | 2022-11-21 | 2023-10-03 | 之江实验室 | Sparse knowledge graph embedding method and device based on meta learning |
| CN117077870A (en) * | 2023-10-12 | 2023-11-17 | 北京德润誉达科技有限公司 | Water resource digital management method based on artificial intelligence |
| CN117077870B (en) * | 2023-10-12 | 2023-12-22 | 北京德润誉达科技有限公司 | Water resource digital management method based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112801751B (en) | 2022-12-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112801751B (en) | Personalized scenic spot recommendation method of multitask graph neural network | |
| Ahani et al. | Market segmentation and travel choice prediction in Spa hotels through TripAdvisor’s online reviews | |
| Alshmrany | Adaptive learning style prediction in e-learning environment using levy flight distribution based CNN model | |
| Van Meeteren | A prehistory of the polycentric urban region: excavating Dutch applied geography, 1930–60 | |
| Nilashi et al. | Online reviews analysis for customer segmentation through dimensionality reduction and deep learning techniques | |
| Luo et al. | Exploring destination image through online reviews: an augmented mining model using latent Dirichlet allocation combined with probabilistic hesitant fuzzy algorithm | |
| Wu et al. | Interpretable tourism demand forecasting with temporal fusion transformers amid COVID-19 | |
| Petrauskas et al. | CWW elements to enrich SWOT analysis | |
| Noorian | A BERT-based sequential POI recommender system in social media | |
| Chan et al. | Artificial intelligence in tourism and hospitality | |
| Hossain et al. | SPaFE: A crowdsourcing and multimodal recommender system to ensure travel safety in a city | |
| KR102552856B1 (en) | Method, device and system for automating creation of content template and extracting keyword for platform service that provide content related to commerce | |
| CN115344794A (en) | Scenic spot recommendation method based on knowledge map semantic embedding | |
| Anas et al. | Machine learning based personality classification for carpooling application | |
| Samsudeen et al. | Context-specific discussion of Airbnb usage knowledge graphs for improving private social systems | |
| Sánchez-Ancajima et al. | Applications of Intelligent Systems in Tourism: Relevant Methods | |
| Zhang et al. | Visual analytics of route recommendation for tourist evacuation based on graph neural network | |
| Bose | Data mining in tourism | |
| Kim et al. | Personalized POI embedding for successive POI recommendation with large-scale smart card data | |
| Wang | Emotion analysis-based decision support system for public perception evaluation in urban planning and design using social media text | |
| ŞEKER | Evolution of Machine Learning in Tourism: A Comprehensive Review of Seminal Research | |
| Pai et al. | Value evaluation of cultural tourism tourists’ psychological expectation based on machine learning data mining | |
| 鄭舒心 | Research on GM-LSTM Hybrid Model for Tourism Prediction Based on One Belt and One Road | |
| Nie | Research on development strategy of ethnic sports tourism resources based on stochastic forest algorithm | |
| Jiang et al. | Seize market opportunities: market segmentation, profile and monitoring through user-generated content |
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 |
Effective date of registration: 20240408 Address after: Room 1007-1, 10th Floor, Building B7, Block B, Phase II, Zhongdian Software Park, No. 18 Jianshan Road, High tech Development Zone, Changsha City, Hunan Province, 410000 Patentee after: Hunan Shuzhi Cultural Tourism Development Co.,Ltd. Country or region after: China Address before: 400065 Chongwen Road, Nanshan Street, Nanan District, Chongqing Patentee before: CHONGQING University OF POSTS AND TELECOMMUNICATIONS Country or region before: China |
|
| TR01 | Transfer of patent right |