CN106600482A - Multi-source social data fusion multi-angle travel information perception and intelligent recommendation method - Google Patents
Multi-source social data fusion multi-angle travel information perception and intelligent recommendation method Download PDFInfo
- Publication number
- CN106600482A CN106600482A CN201611251837.9A CN201611251837A CN106600482A CN 106600482 A CN106600482 A CN 106600482A CN 201611251837 A CN201611251837 A CN 201611251837A CN 106600482 A CN106600482 A CN 106600482A
- Authority
- CN
- China
- Prior art keywords
- landscape
- travel
- information
- comment
- text
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000004927 fusion Effects 0.000 title claims abstract description 9
- 230000008447 perception Effects 0.000 title abstract description 5
- 238000005065 mining Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims 1
- 238000012552 review Methods 0.000 description 2
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 1
- VAYOSLLFUXYJDT-RDTXWAMCSA-N Lysergic acid diethylamide Chemical compound C1=CC(C=2[C@H](N(C)C[C@@H](C=2)C(=O)N(CC)CC)C2)=C3C2=CNC3=C1 VAYOSLLFUXYJDT-RDTXWAMCSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 239000013256 coordination polymer Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a multi-source social data fusion multi-angle travel information perception and intelligent recommendation method and aims to solve a technical problem of poor practicality of a travel information recommendation method in the prior art. According to the method, an independent dictionary is established for each scenic spot; at least one landscape word and commentary sentences having high information entropy are selected from all commentary texts, the acquired commentary text data are utilized, in combination with landscape word sets, characteristics corresponding to each landscape are dug, a sequence mode digging method is utilized to extract a travel route from each travel note, and lastly a voting method is utilized to take a route with highest heat as the recommendation information; through comparing test similarities between image contexts and commentary texts, representative images corresponding to the landscape are selected through voting. The method is advantaged in that the sequence mode digging method is utilized to process texts of the blog travel notes, the travel route most popular to travelers is finally acquired, the more comprehensive auxiliary information is provided for the travelers, and good practicality is realized.
Description
Technical field
The invention belongs to recommendation field of travelling, more particularly to a kind of multi-angle travel information sense of multi-source social data fusion
Know and intelligent recommendation method.
Background technology
In recent years, with the fast development of tourist industry, the visitor from all over the world is liked after travelling by social activity
Expressing the view with regard to scenic spot, the information of this kind of groups contribution can help other users to carry out tour arrangement to media.Travelling
Comment and blog travel notes are the social tourism sharing modes of two kinds of main flows, can be as the reliable knowledge of travel information summary
Source.In the face of growing comment and travel notes, it is also very desirable to which a kind of information Perception and intelligent recommendation method are processing magnanimity trip
Trip information simultaneously provides the user accurately travelling reference.
Document " Understand the City Better:Multimodal Aspect-Opinion
Summarization for Travel.WISE 2014, Part II, LNCS 8787, pp.381-394,2014 " discloses one
Plant the method for carrying out visualizing summary to scenic spot using travel review and blog travel notes.The method mainly includes three steps：It is first
First the sentence for containing much information is picked out in travel review, the feature related to scenic spot is further excavated on this basis, finally
Select most representational image in blog travel notes to visualize features described above.Found according to investigation, blog trip
The tourism route information of visitor is actually further comprises in note.And the method described in document simply regards blog travel notes as image
Data source, directly filters out the content of text included in blog travel notes, it is impossible to further excavate the abundant information for wherein including, real
Existing method is excessively simple, it is difficult to meet user's request.
The content of the invention
In order to overcome the shortcomings of that existing travel information recommends method poor practicability, the present invention to provide a kind of multi-source social data
The multi-angle travel information of fusion is perceived and intelligent recommendation method.The method sets up single dictionary for each scenic spot first；Again
Select from all comment texts including at least a landscape word and the comment sentence with high comentropy, using the comment for obtaining
Text data, with reference to landscape set of words, excavates the corresponding feature of each landscape, using sequential mode mining method from per trip
In note extract a tourism route, finally using vote method using temperature highest route as recommendation information；By comparing
Text similarity between image context and comment text, ballot selects representational image corresponding with landscape.Due to
Employ Sequential Pattern Mining Algorithm to process the textual portions of blog travel notes, finally give the trip for most being welcome by visitor
Trip route, for visitor more fully auxiliary information is provided, and practicality is good.
The technical solution adopted for the present invention to solve the technical problems：A kind of multi-angle tourism of multi-source social data fusion
Information Perception and intelligent recommendation method, are characterized in comprising the following steps：
Step one, for target scenic spot, according to scenic spot title using web crawlers obtain in tourism social intercourse system with it is described
The related all comments in scenic spot and travel notes data, extract text data in comment, the text image data in travel notes and on
Context information, and participle pretreatment is carried out to text, the Chinese stop-word of filtering useless is that single word is set up at each scenic spot
Allusion quotation；
Step 2, select from all comment texts including at least a landscape word and the comment sentence with high comentropy
The comentropy of son, wherein sentence is equal to the summation of each word information entropy in sentence；
Step 3, the comment text data obtained using step 2, with reference to landscape set of words, excavate each landscape corresponding
Feature, wherein feature include nouns and adjectives；
Step 4, a tourism route is extracted from every travel notes using sequential mode mining method, finally using ballot
Method is using temperature highest route as recommendation information；
Step 5, by the text similarity between movement images context and comment text, ballot is selected and landscape pair
The representational image answered.
The invention has the beneficial effects as follows：The method sets up single dictionary for each scenic spot first；Again from all comment texts
Select in this including at least a landscape word and the comment sentence with high comentropy, using the comment text data for obtaining, knot
Landscape set of words is closed, the corresponding feature of each landscape is excavated, one is extracted from every travel notes using sequential mode mining method
Bar tourism route, finally by the use of ballot method using temperature highest route as recommendation information；By movement images context
Text similarity and comment text between, ballot selects representational image corresponding with landscape.As a result of sequence
Pattern mining algorithm is processed the textual portions of blog travel notes, has finally given the tourism route most welcome by visitor, is
Visitor provides more fully auxiliary information, and practicality is good.
The present invention is elaborated with reference to the accompanying drawings and detailed description.
Description of the drawings
Fig. 1 is the flow process of the multi-angle travel information perception with intelligent recommendation method of multi-source social data fusion of the present invention
Figure.
Specific embodiment
With reference to Fig. 1.The multi-angle travel information of multi-source social data fusion of the present invention perceives concrete with intelligent recommendation method
Step is as follows：
Step one, for scenic spot " Summer Palace ", according to keyword " Summer Palace " using web crawlers from popular comment and ant
Cell site obtains related comment and travel notes data, extract text data in comment, the text image data in travel notes with
And landscape set of wordsParticiple pretreatment, the Chinese stopping of filtering useless are carried out to text using participle instrument
Word, single dictionary is set up according to comment text for each scenic spot.
Step 2, to select from all comment texts related to " Summer Palace " and at least have a landscape word and have
The comment sentence of high comentropy, the wherein comentropy of sentence are equal to the summation of the comentropy of each word in sentence, and landscape is scenic spot
Humane or natural landscape at interior one.
Step 3, the comment text data obtained using previous step, with reference to landscape set of wordsAccording to
Landscape n related sentence setFeature Words are extracted for the landscape, set W, including nouns and adjectives is constituted.
Step 4, tourism route refer to visitor from entering until leaving the route that scenic spot is followed, and being one includes some scapes
See the ordered sequence of title.One trip is extracted from every travel notes by connection and cut operator using sequential mode mining method
Trip route, finally by ballot using temperature highest route as recommendation information.
Step 5, specifically include two steps：(1) image clustering：Extract first in travel notes and include contextual information cI's
Image I, obtains the image collection I with regard to sight spot PPWith set of context CP.Then in set IPUpper utilization spectral clustering, based on regarding
Feel that content characteristic vector is classified as visual different cluster LP={ l1,l2,...,ll, if certain contextual information cIQuilt
It is labeled as liThen represent the result of the image clustering being adjacent in liIn.(2) ballot selects image clustering：To SnIn each
Sentence s, it is theoretical from C according to cosinePIt is middle to search most like contextual information cI, choose the image cluster L that may be associated in a votea。
By the text similarity between movement images context and comment text, ballot selects representational figure corresponding with landscape
Picture.So far, the image cluster L being associated with each landscape has been obtaineda, then can be by affine propagation algorithm from image set
Group LaRepresentational image is selected for each landscape-Characterizations combination.
Claims (1)
1. a kind of multi-angle travel information of multi-source social data fusion is perceived and intelligent recommendation method, it is characterised in that include with
Lower step：
Step one, for target scenic spot, according to scenic spot title using web crawlers obtain in tourism social intercourse system with the scenic spot
All comments of correlation and travel notes data, the text data, the text image data in travel notes and context in extraction comment
Information, and participle pretreatment is carried out to text, the Chinese stop-word of filtering useless is that single dictionary is set up at each scenic spot；
Step 2, select from all comment texts including at least a landscape word and the comment sentence with high comentropy, its
The comentropy of middle sentence is equal to the summation of each word information entropy in sentence；
Step 3, the comment text data obtained using step 2, with reference to landscape set of words, excavate the corresponding spy of each landscape
Levy, wherein feature includes nouns and adjectives；
Step 4, a tourism route is extracted from every travel notes using sequential mode mining method, finally using voting method
Using temperature highest route as recommendation information；
Step 5, by the text similarity between movement images context and comment text, ballot selects corresponding with landscape
Representational image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611251837.9A CN106600482A (en) | 2016-12-30 | 2016-12-30 | Multi-source social data fusion multi-angle travel information perception and intelligent recommendation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611251837.9A CN106600482A (en) | 2016-12-30 | 2016-12-30 | Multi-source social data fusion multi-angle travel information perception and intelligent recommendation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106600482A true CN106600482A (en) | 2017-04-26 |
Family
ID=58605237
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611251837.9A Pending CN106600482A (en) | 2016-12-30 | 2016-12-30 | Multi-source social data fusion multi-angle travel information perception and intelligent recommendation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106600482A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108897778A (en) * | 2018-06-04 | 2018-11-27 | 四川创意信息技术股份有限公司 | A kind of image labeling method based on multi-source big data analysis |
| CN109062980A (en) * | 2018-07-01 | 2018-12-21 | 东莞市华睿电子科技有限公司 | One kind commenting on approximate social client account recommended method based on sight spot |
| CN109857838A (en) * | 2019-02-12 | 2019-06-07 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating information |
| CN110263257A (en) * | 2019-06-24 | 2019-09-20 | 北京交通大学 | Multi-source heterogeneous data mixing recommended models based on deep learning |
| CN111191127A (en) * | 2019-12-24 | 2020-05-22 | 重庆特斯联智慧科技股份有限公司 | Travel recommendation method and system based on correlation analysis algorithm |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104794171A (en) * | 2015-03-31 | 2015-07-22 | 百度在线网络技术（北京）有限公司 | Method and device for marking geographical location information of picture |
| CN104881472A (en) * | 2015-05-28 | 2015-09-02 | 华南理工大学 | Combined recommendation method of traveling scenic spots based on network data collection |
-
2016
- 2016-12-30 CN CN201611251837.9A patent/CN106600482A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104794171A (en) * | 2015-03-31 | 2015-07-22 | 百度在线网络技术（北京）有限公司 | Method and device for marking geographical location information of picture |
| CN104881472A (en) * | 2015-05-28 | 2015-09-02 | 华南理工大学 | Combined recommendation method of traveling scenic spots based on network data collection |
Non-Patent Citations (1)
| Title |
|---|
| TONG GUO等: "Leveraging Heterogeneous Crowdsourced Data for Scenic Spot Profiling and Recommendation", 《PCM 2016, PART II, LNCS 9917》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108897778A (en) * | 2018-06-04 | 2018-11-27 | 四川创意信息技术股份有限公司 | A kind of image labeling method based on multi-source big data analysis |
| CN109062980A (en) * | 2018-07-01 | 2018-12-21 | 东莞市华睿电子科技有限公司 | One kind commenting on approximate social client account recommended method based on sight spot |
| CN109857838A (en) * | 2019-02-12 | 2019-06-07 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating information |
| CN110263257A (en) * | 2019-06-24 | 2019-09-20 | 北京交通大学 | Multi-source heterogeneous data mixing recommended models based on deep learning |
| CN110263257B (en) * | 2019-06-24 | 2021-08-17 | 北京交通大学 | Deep learning based recommendation method for processing multi-source heterogeneous data |
| CN111191127A (en) * | 2019-12-24 | 2020-05-22 | 重庆特斯联智慧科技股份有限公司 | Travel recommendation method and system based on correlation analysis algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106600482A (en) | Multi-source social data fusion multi-angle travel information perception and intelligent recommendation method | |
| CN103955529B (en) | A kind of internet information search polymerize rendering method | |
| CN103729402B (en) | Method for establishing mapping knowledge domain based on book catalogue | |
| Jiang et al. | Learning from contextual information of geo-tagged web photos to rank personalized tourism attractions | |
| CN103544255B (en) | Text semantic relativity based network public opinion information analysis method | |
| US20100205176A1 (en) | Discovering City Landmarks from Online Journals | |
| CN107330100A (en) | Combine the two-way search method of image text of embedded space based on multi views | |
| CN106649663B (en) | A kind of video copying detection method based on compact video characterization | |
| CN102456054B (en) | A kind of searching method and system | |
| Tuan et al. | Multimodal fusion with BERT and attention mechanism for fake news detection | |
| Li et al. | Multi-View Visual Semantic Embedding. | |
| CN111222049A (en) | Top-k similarity searching method on semantically enhanced heterogeneous information network | |
| CN105528437A (en) | Question-answering system construction method based on structured text knowledge extraction | |
| CN105849720A (en) | Visual semantic complex network and method for forming network | |
| CN104636408A (en) | News authentication early warning method and system based on user generated content | |
| CN109978016A (en) | A kind of network user identity recognition methods | |
| Chen et al. | Rethinking benchmarks for cross-modal image-text retrieval | |
| Devkota et al. | Utilizing user generated contents to describe tourism areas of interest | |
| Min et al. | Multimodal spatio-temporal theme modeling for landmark analysis | |
| Bartie et al. | Identifying related landmark tags in urban scenes using spatial and semantic clustering | |
| CN106776569A (en) | Tourist hot spot and its Feature Extraction Method and system in mass text | |
| CN109740097A (en) | A kind of Web page text extracting method of logic-based chained block | |
| Chai-Allah et al. | Mining crowdsourced text to capture hikers' perceptions associated with landscape features and outdoor physical activities | |
| Dahyot et al. | Information visualisation for social media analytics | |
| CN108710650B (en) | Topic mining method for forum text |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170426 |
|
| WD01 | Invention patent application deemed withdrawn after publication |