CN106951563A - A kind of tourist hot spot event influence degree forecasting system - Google Patents

A kind of tourist hot spot event influence degree forecasting system Download PDF

Info

Publication number
CN106951563A
CN106951563A CN201710214727.3A CN201710214727A CN106951563A CN 106951563 A CN106951563 A CN 106951563A CN 201710214727 A CN201710214727 A CN 201710214727A CN 106951563 A CN106951563 A CN 106951563A
Authority
CN
China
Prior art keywords
event
hot spot
tourist
module
index
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
Application number
CN201710214727.3A
Other languages
Chinese (zh)
Inventor
王子剑
李震川
陈龙
曹磊
庞子龙
严武
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Nuoyue Intelligence Co ltd
Original Assignee
Shanghai Nuoyue Intelligence Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Nuoyue Intelligence Co ltd filed Critical Shanghai Nuoyue Intelligence Co ltd
Priority to CN201710214727.3A priority Critical patent/CN106951563A/en
Publication of CN106951563A publication Critical patent/CN106951563A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G06F16/3344—Query execution using natural language analysis
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Development Economics (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Databases & Information Systems (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention provides a kind of tourist hot spot event influence degree forecasting system, including input module, neural network module and output module；The input module is used for the relevant parameter for inputting positive event, neutral event and negative event；The parameter includes the related propagation time section index of event, event propagation area count, event and makes a difference crowd's number, event network of relation propagation times, media to event report number of times, venue location attention rate；The neural network module is used for according to the parameter prediction tourist hot spot event influence index；The output module is used to show the tourist hot spot event influence index.This programme can predict the influence degree that focus incident is brought.

Description

A kind of tourist hot spot event influence degree forecasting system
Technical field
The present invention relates to focus incident influence degree electric powder prediction, more particularly to a kind of tourist hot spot event influence journey Spend forecasting system.
Background technology
With information technology high speed development and widely use, the travel information based on internet turn into instantly consumer get over Come the trip option and foundation more favored.The relevant information of network not only shows the travel information of correlation, even more passes through social matchmaker Selection of the channels such as body, dissemination of news to tourist produces direct or indirect influence.
Network, the tourism relevant information of media are often given and locally even bring material impact, base in whole travel industry In the monitoring and warning of this type of information be instantly tourism practitioner be badly in need of counte-rplan.Traditional public sentiment monitoring system is only capable of representing The generation of the related focus incident of tourism and propagation condition, can not calculate the direct or indirect shadow that these focus incidents are brought Ring, it is impossible to find the correlation rule with tourist industry related economic index.
The content of the invention
In view of this, it is the technical problem to be solved in the present invention is to provide a kind of prediction of tourist hot spot event influence degree System, can predict the influence degree that focus incident is brought.
The technical proposal of the invention is realized in this way：
A kind of tourist hot spot event influence degree forecasting system, including input module, neural network module and output module；
The input module is used for the parameter for inputting positive event, neutral event and negative event；
The parameter includes the related propagation time section index of event, event propagation area count, event and made a difference crowd Number, event network of relation propagation times, media report number of times, venue location attention rate to event；
The neural network module is used for according to the parameter prediction tourist hot spot event influence index；
The output module is used to show the tourist hot spot event influence index.
It is preferred that, the neural network module is long memory deep learning training model module in short-term.
It is preferred that, also including assessment module；
The assessment module belongs to positive event or neutral event or negative event for advance judgement event.Assessment module Including positive negativity word dictionary and decision method, it containing positivity word quantity more than negativity word quantity is positive thing that assessment method, which is, Part, more than positivity word quantity is negative event containing negativity word quantity, and remaining is neutral event.
It is preferred that, input module is provided with select unit；
The select unit is used for the time dimension for selecting the relevant parameter of the positive event, neutral event and negative event Degree.
It is preferred that, the tourist hot spot event influence index includes：
Tourist site stream of people figureofmerit and/or GDP indexs and/or business activity number index.
Event influence degree forecasting system in tourist hot spot proposed by the present invention, by input positive event, neutral event and Make a difference crowd's number, event of the related propagation time section index of the event of negative event, event propagation area count, event is related Internet communication number of times, media report the parameters such as number of times, venue location attention rate to event, by neural network module according to institute Parameter prediction tourist hot spot event influence index is stated, so as to export tourist hot spot event influence index, focus incident is predicted The influence degree brought.
Brief description of the drawings
Fig. 1 is the structured flowchart for the tourist hot spot event influence degree forecasting system that the embodiment of the present invention is proposed.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made Embodiment, belongs to the scope of protection of the invention.
As shown in figure 1, the embodiment of the present invention proposes a kind of tourist hot spot event influence degree forecasting system 1, including it is defeated Enter module 101, neural network module 102 and output module 103；
Input module 101 is used for the relevant parameter for inputting positive event, neutral event and negative event；
Parameter includes the related propagation time section index of event, event propagation area count, event and made a difference crowd's number, thing Part network of relation propagation times, media report number of times, venue location attention rate to event；
Neural network module 102 is used for according to parameter prediction tourist hot spot event influence index；
Output module 103 is used to show tourist hot spot event influence index.
It can be seen that, the embodiment of the present invention propose tourist hot spot event influence degree forecasting system, by input positive event, The neutral event propagation time section index related to the event of negative event, event propagation area count, event make a difference crowd Number, event network of relation propagation times, media report the parameters such as number of times, venue location attention rate to event, pass through nerve net Network module is according to parameter prediction tourist hot spot event influence index, so as to export tourist hot spot event influence index, prediction The influence degree that focus incident is brought.
Wherein, propagation time section index IbThere is Ib=wp, w represent period level weights, and p represents that the period event is passed Broadcast the product of the ratio of number and total event number.W weights can be divided according to the period, and specific divide can be divided into more than 2 periods, Each period assigns corresponding weights between 0 to 1.It is 1 that all period weights, which are added summation,.
Event propagation area count refers to the event Internet communication and the regional number summation of media report information source, and its scope can For the whole world, the whole nation, province, city etc., granularity can be country, province, city, area below scope granularity level etc..
Event makes a difference crowd's quantity that crowd's number self-explanatory characters' part is directly affected.
Event network of relation propagation times refer to the quantity of the event message on mainstream network and mobile social information channel, can Representative channel is selected to be counted.
Media report that number of times refers to the quantity of the event message on mainstream network and mobile media to event, can select with generation The media of table are counted.
Venue location attention rate represents venue location area attention rate index If.The index can be by its this area's population Measure NdWith state size of population NgRatio, which is taken the logarithm, tries to achieve：If=log (Nd/Ng)。
In a preferred embodiment of the invention, neural network module is long memory deep learning training pattern die in short-term Block.
Long memory deep learning training model module in short-term, is by classical LSTM length memory deep learning model algorithm in short-term Constitute, passage time sequence inputting obtains the neural network model of corresponding time series output.
Wherein, general sequential fitting algorithm, recursion cycle deep learning god can be used in long memory depth neutral net in short-term Substituted through network etc..
In a preferred embodiment of the invention, tourist hot spot event influence degree forecasting system also includes evaluation mould Block；
Assessment module belongs to positive event or neutral event or negative event for advance judgement event.Assessment module includes Positive negativity word dictionary and decision method, it containing positivity word quantity more than negativity word quantity is positive event that assessment method, which is, is contained There is negativity word quantity to be more than positivity word quantity as negative event, remaining is neutral event
Assessment module can analyze event description text by natural language understanding technology, be gone by keyword emotion attribute Evaluate the ownership of the event.
In a preferred embodiment of the invention, input module is provided with select unit；
Select unit is used for the time dimension for selecting the relevant parameter of positive event, neutral event and negative event.
Wherein, time dimension unit foundation can be day, week or moon etc. or the same time point of different time sections Year-on-year sequence, or similar events time point, can be selected according to concrete condition.By selection time dimension, it can make Predict that output result time width is more flexible, can reach 1 day extendible time measure to the several years.
In a preferred embodiment of the invention, event influence index in tourist hot spot includes：
Tourist site stream of people figureofmerit and/or GDP indexs and/or business activity number index.
Wherein, tourist site stream of people figureofmerit and/or GDP indexs and/or business activity number index are important influence indexs, It can intuitively judge to influence journey by exporting tourist site stream of people figureofmerit and/or GDP indexs and/or business activity number index Degree；Alternatively, it is also possible to as needed, tourist site stream of people figureofmerit and/or GDP indexs and/or business activity number index are expanded Onto other indexs, the class index of not limited to this 2.
In summary, the embodiment of the present invention can at least realize following effect：
In embodiments of the present invention, the propagation related to the event of negative event by inputting positive event, neutral event Period index, event propagation area count, event make a difference crowd's number, event network of relation propagation times, media to event The parameters such as number of times, venue location attention rate are reported, are influenceed by neural network module according to parameter prediction tourist hot spot event Index, so as to export tourist hot spot event influence index, the influence degree that prediction focus incident is brought.
In embodiments of the present invention, input module is provided with select unit, so as to according to concrete condition seclected time dimension Degree；By selection time dimension, prediction output result time width can be made more flexible, can reach 1 day it is extendible to the several years Time measure.
It is last it should be noted that：Presently preferred embodiments of the present invention is the foregoing is only, the skill of the present invention is merely to illustrate Art scheme, is not intended to limit the scope of the present invention.Any modification for being made within the spirit and principles of the invention, Equivalent, improvement etc., are all contained in protection scope of the present invention.

Claims (5)

1. a kind of tourist hot spot event influence degree forecasting system, it is characterised in that including input module, neural network module and Output module；
The input module is used for the parameter for inputting positive event, neutral event and negative event；
The parameter includes the related propagation time section index of event, event propagation area count, event and made a difference crowd's number, thing Part network of relation propagation times, media report number of times, venue location attention rate to event；
The neural network module is used for according to the parameter prediction tourist hot spot event influence index；
The output module is used to show the tourist hot spot event influence index.
2. event influence degree forecasting system in tourist hot spot as claimed in claim 1, it is characterised in that the neutral net mould Block is long memory deep learning training model module in short-term.
3. event influence degree forecasting system in tourist hot spot as claimed in claim 1, it is characterised in that also including evaluation mould Block；
The assessment module belongs to positive event or neutral event or negative event for advance judgement event.
4. event influence degree forecasting system in tourist hot spot as claimed in claim 1, it is characterised in that input module is provided with Select unit；
The select unit is used for the time dimension for selecting the relevant parameter of the positive event, neutral event and negative event.
5. the tourist hot spot event influence degree forecasting system as described in claim any one of 1-4, it is characterised in that the trip Trip focus incident influence index includes：
Tourist site stream of people figureofmerit and/or GDP indexs and/or business activity number index.
CN201710214727.3A 2017-04-01 2017-04-01 A kind of tourist hot spot event influence degree forecasting system Pending CN106951563A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710214727.3A CN106951563A (en) 2017-04-01 2017-04-01 A kind of tourist hot spot event influence degree forecasting system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710214727.3A CN106951563A (en) 2017-04-01 2017-04-01 A kind of tourist hot spot event influence degree forecasting system

Publications (1)

Publication Number Publication Date
CN106951563A true CN106951563A (en) 2017-07-14

Family

ID=59475695

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710214727.3A Pending CN106951563A (en) 2017-04-01 2017-04-01 A kind of tourist hot spot event influence degree forecasting system

Country Status (1)

Country Link
CN (1) CN106951563A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015017676A1 (en) * 2013-07-31 2015-02-05 Locator Ip, Lp System and method for gaming and hedging weather
CN104809634A (en) * 2015-05-11 2015-07-29 中国旅游研究院 Tourism data research and monitoring system
CN104902292A (en) * 2015-05-20 2015-09-09 无锡天脉聚源传媒科技有限公司 Television report-based public opinion analysis method and system
CN105956770A (en) * 2016-05-03 2016-09-21 中国科学院大学 Stock market risk prediction platform and text excavation method thereof

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015017676A1 (en) * 2013-07-31 2015-02-05 Locator Ip, Lp System and method for gaming and hedging weather
CN104809634A (en) * 2015-05-11 2015-07-29 中国旅游研究院 Tourism data research and monitoring system
CN104902292A (en) * 2015-05-20 2015-09-09 无锡天脉聚源传媒科技有限公司 Television report-based public opinion analysis method and system
CN105956770A (en) * 2016-05-03 2016-09-21 中国科学院大学 Stock market risk prediction platform and text excavation method thereof

Similar Documents

Publication Publication Date Title
Mukhtarov et al. The influence of information and communication technologies on public participation in urban water governance: A review of place-based research
Pons et al. Impact of Corporate Social Responsibility in mining industries
Starbird et al. Chatter on the red: what hazards threat reveals about the social life of microblogged information
CN106021508A (en) Sudden event emergency information mining method based on social media
Kim et al. An index-based robust decision making framework for watershed management in a changing climate
Patlins Improvement of sustainability definition facilitating sustainable development of public transport system
CN105721279B (en) A kind of the relationship cycle method for digging and system of subscribers to telecommunication network
Codina et al. Built environment bikeability as a predictor of cycling frequency: Lessons from Barcelona
Yabe et al. Integrating information from heterogeneous networks on social media to predict post-disaster returning behavior
CN106570763A (en) User influence evaluation method and system
Bendle The structures and flows of a large tourist itinerancy network
Lin et al. An agent-based approach to human migration movement
Lu et al. Characterizing new channels of communication: A case study of municipal 311 requests in Edmonton, Canada
Chetty et al. Where is the Land of Opportunity
Du et al. Data mining of social media for urban resilience study: A case of rainstorm in Xi'an
Barros et al. Evaluative image 2.0: A web mapping approach to capture people’s perceptions of a city
CN106951563A (en) A kind of tourist hot spot event influence degree forecasting system
Coria et al. CT4RDD: Classification trees for research on digital divide
Kim et al. Voices of transitions: Korea's online news media and user comments on the energy transition
Marcotte et al. Participatory water management modelling in the Athabasca River Basin
Wei et al. An analysis of conflict and cooperation dynamics over water events in the Lancang-Mekong River Basin
Qianzi et al. Research on the Perception of Cultural Ecosystem Services in Urban Parks via Analyses of Online Comment Data.
Bojic et al. Sublinear scaling of country attractiveness observed from Flickr dataset
Oliveri et al. Tourist mobility and destination competitiveness
Pino et al. Assessment and visualization of geographically distributed event-related sentiments by mining social networks and news

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20170714

RJ01 Rejection of invention patent application after publication