CN112733040B - Travel itinerary recommendation method - Google Patents
Travel itinerary recommendation method Download PDFInfo
- Publication number
- CN112733040B CN112733040B CN202110112444.4A CN202110112444A CN112733040B CN 112733040 B CN112733040 B CN 112733040B CN 202110112444 A CN202110112444 A CN 202110112444A CN 112733040 B CN112733040 B CN 112733040B
- Authority
- CN
- China
- Prior art keywords
- travel
- relevance
- nodes
- user
- city
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000003058 natural language processing Methods 0.000 claims abstract description 9
- 239000011159 matrix material Substances 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 230000009193 crawling Effects 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 238000002620 method output Methods 0.000 claims description 2
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 7
- 230000006399 behavior Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a travel itinerary recommendation method, which comprises the steps of using travel comment data published on a social media website, extracting mass user travel footprint big data, using travel itineraries of users as corpora, calculating the relevance of each node in the travel itineraries by adopting a word embedding model in natural language processing, constructing a network through the relevance of the travel nodes, and generating and recommending the travel itineraries by using an improved minimum spanning tree method added with space distance constraint. The invention reduces the excessive marginal information and the user constraint condition required when generating the travel itinerary, and is suitable for recommending the travel itinerary for most users.
Description
Technical Field
The invention relates to the technical field of recommendation, in particular to a travel journey recommendation method.
Background
With the increasingly improved living standard of people, tourism becomes a living mode selected by more people at leisure, meanwhile, along with the development of the mobile internet, people can record own journey through check-in behaviors during traveling, or release the feeling of the people on the way of traveling to a social media website or platform after traveling, so that a large amount of data with position information is generated, for users of the social media website or platform, it is difficult and tedious to acquire contents meaningful for the journey from mass data, and therefore, how to extract useful value information from the mass data has important significance for users to go out.
In the existing travel recommendation method, some researchers take the spatial distance as an important influence factor for generating the travel, calculate the spatial distance between travel nodes in a data set, take the spatial distance as an edge weight for constructing a network, use a minimum spanning tree method after determining a starting point, and generate the travel according to the constructed network. Some researchers use a clustering method to cluster the travel nodes with the spatial position information in the user travel, and select some nodes in each category according to the spatial distance to generate the travel. However, these methods ignore the behavior preference information of the user for traveling and lack interpretability. Some researchers construct a network by counting the number of a large number of user travel routes, add weight to nodes according to the frequency of each travel node in all the routes, and calculate the probability that each node becomes the next destination through a Markov chain after selecting a starting point, thereby generating the travel route. Some researchers generate tour routes based on user preferences, a sight spot knowledge base (sight spot type, distance between sight spots and the like) needs to be built in advance, the knowledge base can provide a large amount of text information, the researchers calculate and mine the user preferences through a theme model based on the tour route records of the users, select sight spots meeting the user requirements, integrate the user preferences and the current position information of the users into a probability behavior model by combining a shortest path algorithm or a Markov chain, evaluate the probability of visiting a certain sight spot in a user data set through the model, and select the sight spots with high probability to generate the tour routes. The methods require excessive marginal information, require a great amount of constraint conditions for users when generating the travel itineraries, and are not suitable for recommending the travel itineraries for most users.
Aiming at the problems in the existing research, a travel journey recommendation method is provided to better serve travel selection of a user and development planning of the travel industry. The method comprises the steps of using travel comment data published by a user on a social media website, extracting a user travel route and dividing the user travel route into a city travel route and a sight spot travel route of the user, using the travel routes as linguistic data, calculating the relevance of each node in the travel route by adopting a word embedding model in natural language processing, constructing a hierarchical network comprising a city relevance network and a sight spot relevance network according to the relevance of the travel nodes, calculating a city node distance matrix and a sight spot node distance matrix respectively based on the spatial position coordinates of each node in the hierarchical network, and finally generating the travel route by using a minimum spanning tree method added with spatial distance constraint.
Disclosure of Invention
The invention aims to provide a travel journey recommendation method for solving the problems in the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention comprises the following steps:
crawling tour comment data published by a user on a social media website, dividing a user journey, extracting user tour footprint big data, and respectively acquiring tour journeys of space nodes;
b, according to the tourism travel of the space nodes, calculating the relevance of the space nodes of different levels by adopting a word embedding model in natural language processing, taking the relevance as the weight of a connecting node, constructing a space network of the nodes through the relevance among the tourism space nodes as a basis for generating the tourism travel, and combining the space networks of the nodes of different levels into a hierarchical network;
c, generating a travel journey based on a hierarchical network by using an improved minimum spanning tree method added with space distance constraint;
d, generating a tour according to the retrieval condition of the user and the hierarchical network, sequencing according to the set condition, and recommending the tour to the user, wherein the set condition comprises distance priority, travel time priority and distance priority, and the tour is generated based on the hierarchical network, and the generation method comprises the following steps:
(1) urban node distance matrix is calculated based on spatial positions of nodes in different-level spatial networks
And sight point node distance matrix
Where N is the number of cities in the network and M is in the networkThe number of the scenic spots is,
representing nodes of a city
And city node
The spatial distance between them, and similarly,
representing points of sight
And point of view node
The spatial distance therebetween;
(2) and improving a minimum spanning tree model by taking the distance matrix as a space distance constraint condition, and using the model in a hierarchical network to generate the travel journey.
Further, the user travel footprint big data is extracted based on travel comment data published by the user on the social media website, travel of the same user in a certain time period is calculated as a travel according to travel time, and therefore the travel big data is obtained and divided into travel travels under different levels of space nodes.
Further, the method for calculating the weight in the travel journey comprises the following steps:
(1) calculating the relevance of nodes in the tour journey of the user, wherein the calculation of the relevance is based on the tour journey of the user at the level of the city and the sight spot, and the relevance between the city nodes and the relevance between the sight spots in the tour journey are calculated by respectively inputting the journey of the user at the level of the city and the sight spot into a word embedding model by using a word embedding model in a natural language processing method;
the word embedding model method is composed of an input layer, a projection layer and an output layer;
aiming at the travel journey of the user, putting each journey record into an input layer;
setting training parameters of the word embedding model method;
setting the vector size of the word embedding model method output layer;
calculating the relevance value between the nodes by a cosine similarity method;
(2) and after the relevance among the tourism nodes is obtained, constructing a spatial network of the city and the scenic spots by taking the relevance as the connection weight among the nodes, and associating the scenic spots in each city with the city to construct a hierarchical network.
Further, the method for generating the travel itinerary and recommending the travel itinerary to the user in the step C includes:
(1) calculating a city node distance matrix and a scenic spot node distance matrix based on the spatial position of each node in the spatial networks of different levels;
(2) adding the distance matrix as a space distance constraint condition into a minimum spanning tree model, and using the model in a hierarchical network constructed by calculating relevance to generate a travel route;
(3) and recommending the travel itineraries to the user based on the input conditions (such as the starting point and the like), wherein the recommended travel itineraries comprise main itineraries which are main in cities, and sight spot itineraries in each city are used as secondary itineraries.
In the minimum spanning tree Prim algorithm, a vertex is arbitrarily selected from a graph and added into a tree T initially, the tree only contains one vertex at the moment, then a vertex closest to a vertex set in the current T is selected, the vertex and a corresponding edge are added into the T, the number of the vertices and the number of the edges in the T are increased by 1 after each operation, and the like.
Because the network constructed by the invention takes the relevance among the nodes as the edge weight and has larger distance influence among the spatial nodes, an improved minimum spanning tree method added with spatial distance constraint is provided as a stroke generation algorithm.
And recommending the travel itineraries to the user based on the input conditions (such as the starting point and the like), wherein the recommended travel itineraries comprise main itineraries which are main in cities, and sight spot itineraries in each city are used as secondary itineraries.
Compared with the prior art, the invention has the beneficial effects that:
the invention reduces the excessive marginal information and the user constraint condition required when generating the travel itinerary, and is suitable for recommending the travel itinerary for most users.
Drawings
FIG. 1 is a schematic diagram of an improved minimum spanning tree algorithm;
FIG. 2 is a flow chart of the travel itinerary recommendation of the present invention;
FIG. 3 is a schematic diagram illustrating capturing of user travel comment data in the embodiment;
FIG. 4 is a diagram of a user city and a scenic spot travel record in this embodiment;
FIG. 5 is a schematic view of the Word2Vec model framework;
FIG. 6 is a schematic diagram of a city relevance matrix in the embodiment;
FIG. 7 is a schematic diagram of a city relevance network in the embodiment;
FIG. 8 is a diagram of hierarchical network in this embodiment;
FIG. 9 is a schematic diagram illustrating an output of a trip recommendation in the present embodiment;
wherein a is a city main journey and b is a scenic spot main journey.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
In this embodiment, the modified minimum spanning tree algorithm is shown in fig. 1. Taking the city space network as an example, a certain city node
And adding the node with the highest score value into the tree T after the vertex is added into the tree T and the relevance among the nodes and the influence of the spatial distance are considered, and repeating the process until the length of the spanning tree set reaches the predetermined size.
Referring to fig. 2, the present invention includes the steps of:
and A, crawling the travel comment data published by the user on the social media website, extracting the travel footprint big data of the user, calculating the travel of the same user in a certain time period as a travel route according to the travel time, thereby obtaining the travel route big data, and dividing the travel route big data into the travel routes under different levels of space nodes (such as cities and scenic spots). The raw data is shown in fig. 3, and the processed experimental data is shown in fig. 4;
b, calculating the relevance of each node in the segmented user tour by adopting a word embedding model, and constructing a spatial network of the nodes through the relevance among the tour nodes;
in this embodiment, the Word embedding model Word2Vec in the natural language processing is used to calculate the relevance of each node in the travel journey, and the Word2Vec model is shown in fig. 5:
the relevance calculation method comprises an input layer, a projection layer and an output layer, and the Skip-gram model under the Word2Vec model framework is used in the invention. Similar to natural language processing, each journey is taken as a statement, each tourism node in the journey is taken as a word forming the statement, then the sentence is input into a Skip-gram model and is set with parameters for training, after the training is finished, the relevance among vectors representing space nodes output by the model is calculated by using cosine similarity, and finally a relevance matrix among the space nodes is obtained. The relevance of the city level nodes is shown in fig. 6, and the sight point levels also obtain a similar relevance matrix;
after the relevance of each space node in the travel journey is calculated, a city and scenery spot space network is constructed through the relevance among the travel nodes, the relevance is used as the connection weight among the nodes, and the scenery spot network is constructed on the basis of the network constructed through the relevance among the city nodes as shown in fig. 7. The hierarchical network constructed by combining the city and sight point spatial networks is shown in fig. 8. It should be noted that the thickness of the same color line in the hierarchical network represents the size of the association between the nodes at the same level.
C, generating a travel route based on a hierarchical network by using a minimum spanning tree method added with space distance constraint;
after the urban relevance network and the scenery spot relevance network are built, the urban node distance matrix and the scenery spot node distance matrix are calculated respectively based on the spatial position of each node in the two networks, the distance matrix is used as spatial distance constraint and added into a minimum spanning tree model, and the model is used for generating a tourism journey in a hierarchical network.
D, recommending a travel journey to the user based on input conditions (such as starting points and the like);
usually, a user visits some scenic spots in a city and then goes to some scenic spots in the next city, according to the travel generation method, a main travel mainly based on the city is generated, and on the basis, a travel is generated in each city as a secondary travel. Using the trip generation method, we will generate top @ K trips (a complete route containing a primary trip and a secondary trip) as an option to recommend to the user. The user is recommended a travel itinerary as shown in FIG. 9 when we enter that the starting point is Xining.
The invention extracts the tourism travels of the user under cities and scenic spots, takes the travels as linguistic data, calculates the relevance of each node in the tourism travels by adopting a word embedding model in natural language processing, excavates the relation among all the tourism nodes through relevance calculation, constructs a hierarchical network comprising a city relevance network and a scenic spot relevance network through the relevance of the tourism nodes, finally generates the tourism travels by using an improved minimum spanning tree method added with space distance constraint, and recommends the tourism travels to the user based on input conditions (such as starting points).
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (3)
1. A travel itinerary recommendation method is characterized in that,
the method comprises the following steps:
crawling tour comment data published by a user on a social media website, dividing a user journey, extracting user tour footprint big data, and respectively acquiring tour journeys of space nodes;
b, according to the travel itineraries of the space nodes, calculating the relevance of the space nodes of different levels by adopting a word embedding model in natural language processing, taking the relevance as the weight of a connecting node, constructing a space network of the nodes through the relevance among the travel space nodes as a basis for generating the travel itineraries, and combining the space networks of the nodes of different levels into a hierarchical network;
c, generating a travel journey based on a hierarchical network by using an improved minimum spanning tree method added with space distance constraint;
d, generating a tour according to the retrieval condition of the user and the hierarchical network, sequencing according to the set condition, and recommending the tour to the user, wherein the set condition comprises distance priority, travel time priority and distance priority, and the tour is generated based on the hierarchical network, and the generation method comprises the following steps:
(1) urban node distance matrix is calculated based on spatial positions of nodes in different-level spatial networks
And sight point node distance matrix
Wherein N is the number of cities in the network, M is the number of scenic spots in the network,
representing nodes of a city
And city node
The spatial distance between the two plates is less than the total distance,
representing points of sight
And point of view node
The spatial distance therebetween;
(2) and improving a minimum spanning tree model by taking the distance matrix as a space distance constraint condition, and using the model in a hierarchical network to generate the travel journey.
2. The method of claim 1, wherein the step of calculating the weight of the travel itinerary comprises:
(1) calculating the relevance of nodes in the tour journey of the user, wherein the calculation of the relevance is based on the tour journey of the user at the level of the city and the sight spot, and the relevance between the city nodes and the relevance between the sight spots in the tour journey are calculated by respectively inputting the journey of the user at the level of the city and the sight spot into a word embedding model by using a word embedding model in a natural language processing method;
the word embedding model method is composed of an input layer, a projection layer and an output layer;
aiming at the travel journey of the user, putting each journey record into an input layer;
setting training parameters of the word embedding model method;
setting the vector size of the word embedding model method output layer;
calculating the relevance value between the nodes by a cosine similarity method;
(2) and after the relevance among the tourism nodes is obtained, constructing a spatial network of the city and the scenic spots by taking the relevance as the connection weight among the nodes, and associating the scenic spots in each city with the city to construct a hierarchical network.
3. The method for recommending a travel itinerary according to claim 1, wherein in step C, the method for generating a travel itinerary and recommending it to the user comprises:
(1) calculating a city node distance matrix and a scenic spot node distance matrix based on the spatial position of each node in the spatial networks of different levels;
(2) adding the distance matrix as a space distance constraint condition into a minimum spanning tree model, and using the model in a hierarchical network constructed by calculating relevance to generate a travel route;
(3) recommending the travel itineraries to the user based on the input conditions, wherein the recommended travel itineraries comprise main itineraries which are main in cities, and scenic spot itineraries inside each city are used as secondary itineraries.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110112444.4A CN112733040B (en) | 2021-01-27 | 2021-01-27 | Travel itinerary recommendation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110112444.4A CN112733040B (en) | 2021-01-27 | 2021-01-27 | Travel itinerary recommendation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112733040A CN112733040A (en) | 2021-04-30 |
| CN112733040B true CN112733040B (en) | 2021-07-30 |
Family
ID=75595353
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110112444.4A Active CN112733040B (en) | 2021-01-27 | 2021-01-27 | Travel itinerary recommendation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112733040B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113505311B (en) * | 2021-07-12 | 2022-03-11 | 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 |
| CN117456588B (en) * | 2023-12-20 | 2024-04-09 | 福建先行网络服务有限公司 | Wisdom museum user management system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101131738A (en) * | 2006-08-25 | 2008-02-27 | 佛山市顺德区顺达电脑厂有限公司 | Travel route planning system and method thereof |
| CN101390096A (en) * | 2006-02-27 | 2009-03-18 | 微软公司 | Training a ranking function using propagated document relevance |
| CN103823914A (en) * | 2013-05-24 | 2014-05-28 | 东南大学 | Touring line planning method |
| WO2018217863A1 (en) * | 2017-05-23 | 2018-11-29 | Intel Corporation | Methods and apparatus for enhancing a binary weight neural network using a dependency tree |
| WO2019112566A1 (en) * | 2017-12-05 | 2019-06-13 | Google Llc | Machine learning model for predicting speed based on vehicle type |
| CN110175720A (en) * | 2019-05-30 | 2019-08-27 | 上海苍潇穹宇数据科技有限公司 | Tour schedule planing method and application |
| CN110555174A (en) * | 2019-09-16 | 2019-12-10 | 湖南科技大学 | r-tree-based track path recommendation method |
| CN110851714A (en) * | 2019-11-07 | 2020-02-28 | 安徽大学 | Text recommendation method and system based on heterogeneous topic model and word embedding model |
| CN111259133A (en) * | 2020-01-17 | 2020-06-09 | 成都信息工程大学 | Personalized recommendation method integrating multiple information |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2815153A1 (en) * | 2013-05-06 | 2014-11-06 | Ibm Canada Limited - Ibm Canada Limitee | Document order management via binary tree projection |
| US10817552B2 (en) * | 2017-03-27 | 2020-10-27 | Microsoft Technology Licensing, Llc | Input-output example encoding |
-
2021
- 2021-01-27 CN CN202110112444.4A patent/CN112733040B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101390096A (en) * | 2006-02-27 | 2009-03-18 | 微软公司 | Training a ranking function using propagated document relevance |
| CN101131738A (en) * | 2006-08-25 | 2008-02-27 | 佛山市顺德区顺达电脑厂有限公司 | Travel route planning system and method thereof |
| CN103823914A (en) * | 2013-05-24 | 2014-05-28 | 东南大学 | Touring line planning method |
| WO2018217863A1 (en) * | 2017-05-23 | 2018-11-29 | Intel Corporation | Methods and apparatus for enhancing a binary weight neural network using a dependency tree |
| WO2019112566A1 (en) * | 2017-12-05 | 2019-06-13 | Google Llc | Machine learning model for predicting speed based on vehicle type |
| CN110175720A (en) * | 2019-05-30 | 2019-08-27 | 上海苍潇穹宇数据科技有限公司 | Tour schedule planing method and application |
| CN110555174A (en) * | 2019-09-16 | 2019-12-10 | 湖南科技大学 | r-tree-based track path recommendation method |
| CN110851714A (en) * | 2019-11-07 | 2020-02-28 | 安徽大学 | Text recommendation method and system based on heterogeneous topic model and word embedding model |
| CN111259133A (en) * | 2020-01-17 | 2020-06-09 | 成都信息工程大学 | Personalized recommendation method integrating multiple information |
Non-Patent Citations (2)
| Title |
|---|
| 基于最小生成树和聚类算法的旅游线路规划;梁珂等;《测绘技术装备》;20160430;第18卷(第4期);第45-48页 * |
| 网络空间异构网关联模型及方法;王菁等;《指挥信息系统与技术》;20180430;第9卷(第2期);第49-54页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112733040A (en) | 2021-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110287336B (en) | Tourist map construction method for tourist attraction recommendation | |
| JP7182585B2 (en) | program | |
| CN110134885B (en) | Interest point recommendation method, device, equipment and computer storage medium | |
| CN106202010A (en) | The method and apparatus building Law Text syntax tree based on deep neural network | |
| Moncla et al. | Reconstruction of itineraries from annotated text with an informed spanning tree algorithm | |
| JP2019504410A (en) | Travel guide generation method and system | |
| CN112733040B (en) | Travel itinerary recommendation method | |
| CN104794171B (en) | Mark the method and device of picture geographical location information | |
| CN106940726B (en) | Creative automatic generation method and terminal based on knowledge network | |
| JP2010039710A (en) | Information collection device, travel guiding device, travel guiding system and computer program | |
| CN103440314A (en) | Semantic retrieval method based on Ontology | |
| CN106096000A (en) | A kind of user based on mobile Internet travel optimization recommend method and system | |
| CN113535917A (en) | Intelligent question-answering method and system based on travel knowledge map | |
| CN110532464B (en) | Tourism recommendation method based on multi-tourism context modeling | |
| CN111914157A (en) | Travel scheme generation method and system based on user preference | |
| Luo et al. | Exploring destination image through online reviews: an augmented mining model using latent Dirichlet allocation combined with probabilistic hesitant fuzzy algorithm | |
| CN114490926A (en) | Method and device for determining similar problems, storage medium and terminal | |
| CN115952339A (en) | NGboost-based geographic space-time knowledge extraction and map representation method | |
| CN113741759B (en) | Comment information display method and device, computer equipment and storage medium | |
| CN113486649B (en) | Text comment generation method and electronic device | |
| Su et al. | Personalized route description based on historical trajectories | |
| CN114896353A (en) | Geocoding method, storage medium and system | |
| CN106709011A (en) | Positional concept hierarchy disambiguation calculation method based on spatial locating cluster | |
| Kalpakchi et al. | SpaceRefNet: a neural approach to spatial reference resolution in a real city environment | |
| Takemiya et al. | Computationally determining the salience of decision points for real-time wayfinding support |
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 |